58 results for “Model Context Protocol”

List Grid

What you seeeverything

Recent Oldest Added A–Z

All types58 Papers19 Repos12 Articles9 Threads9 Advisories6 Write-ups2 Other1

“Model Context Protocol”

x.comthread🛡️ Security

Rohan Paul (@rohanpaul_ai) on X

Rohan Paul's X post summarizes the paper "Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol", from TikTok researchers. It reports that MCP-using agents often finish the requested task, then quietly call an attacker-controlled logging tool that records the query, server reply and final answer. The attack works through natural-language tool descriptions that agents read when choosing and ordering tools. The visible text is truncated.

Model Context ProtocolLLM

Log-To-Leakprompt injectionTikTok+1

AI Security· Added 29 Oct 2026, published 28 Oct 2026

x.compaper🛡️ Security

Cryptography and Security Papers (@FSFG) on X

Log-To-Leak is an arXiv paper (cs.CR, cs.AI) by Yuepeng Hu, Chongyu Fan, Sirat Samyoun and Jian Du on prompt injection attacks against tool-using LLM agents through the Model Context Protocol. The title points to a logging-based data leakage channel. The fetched page holds only the title, authors and arXiv link, with no abstract, so the method and results are not visible here.

Model Context ProtocolLLM

Log-To-Leakprompt injection

AI Security· Added 29 Oct 2026, published 28 Oct 2026

x.comthread🛡️ Security

Kizuno18 (@Kizuno18) on X

Thread by Kizuno18 on the move from local stdio/Docker Model Context Protocol servers to remote HTTP/SSE endpoints in enterprise infrastructure. It names three trade-offs: credential boundary inversion (short-lived OAuth/JWT tokens instead of long-lived admin tokens on workstations), tool schema bloat solved by deferred discovery, and governance via HCP Terraform policy-as-code (Sentinel/OPA), audit trails and approvals. It is opinion, with no data or implementation detail.

Model Context ProtocolTerraformDocker+2

Sentinelblast radiuspolicy-as-code+1

AI Security, Identity & Access, DevSecOps· Added 29 Oct 2026, published 27 Oct 2026

x.comthread🧠 AI

Kizuno18 (@Kizuno18) on X

Kizuno18's X post argues that the move from local stdio and Docker MCP servers to remote HTTP/SSE endpoints matures the Model Context Protocol in enterprise infrastructure. It lists three trade-offs: short-lived OAuth/JWT bearer tokens replace mounted admin credentials, deferred tool discovery avoids roughly 20k tokens of eager schema loading, and HCP Terraform enforces Sentinel/OPA policy, audit trails and approvals server-side. Opinion post with no benchmarks or code.

Model Context ProtocolDockerTerraform+5

Kizuno18HCP TerraformOPA

mcp· Added 29 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🛡️ Security

Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol

Log-To-Leak is a prompt-injection attack on tool-using LLM agents that abuses Model Context Protocol tool metadata to trigger an attacker-controlled logging call after the last legitimate call, leaking the user query, server name, server response and agent response. Evaluated on five MCP servers and four agents, it reaches 62.64-100% attack success with 76.55-95.64% logging accuracy. Three defenses leave over 55% residual ASR on GitHub MCP with GPT-4o.

Model Context ProtocolGitHubGPT-4o+1

Log-To-Leaktool poisoningprompt injection

AI Security· Added 28 Oct 2026, published 26 Oct 2026

x.comthread🧠 AI

Big Bull (@BIGBULLapp) on X

5ire is a desktop AI assistant and MCP client that connects to OpenAI, Anthropic, Google, Mistral, Grok, DeepSeek and Ollama from one window. It has a local knowledge base and tool calls over Model Context Protocol. The tools feature needs Python, Node and uv installed because it runs a local MCP server; without them it works only as a chat client.

Model Context ProtocolPythonNode.js+3

5ireOpenAIAnthropic+4

mcp, llm-apps· Added 25 Oct 2026, published 24 Oct 2026

x.comthread🧠 AI

Big Bull (@BIGBULLapp) on X

A post by BIGBULLapp on X about a TensorBlock GitHub index of Model Context Protocol servers, described as a TypeScript list so agents call tools someone has already wired up. It cites 1470 forks, 943 stars and 15 open issues. The author notes that curated lists go stale when a server changes its schema. The repository name is truncated in the post.

Model Context ProtocolGitHubTypeScript

TensorBlock

mcp· Added 24 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🧠 AI

Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance

MCP-Injector is a protocol-aware fault-injection middleware for Model Context Protocol tool calls, with permanent, transient and intermittent faults on seedable schedules. Its fault model comes from 57,240 issue and PR threads across 1,774 open-source MCP repositories. In a 1,350-cell experiment, faults cut task-completion score by 60% (8.08 to 3.23 of 10), and the 120B gpt-oss model was no more resilient than the 20B. Agent stacks differed in how well they absorbed faults.

Model Context ProtocolOpenAI Agents SDKLangChain+2

MCP-Injectorgpt-oss-120bOpenAI

mcp, evals, agents, research· Added 26 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🛡️ Security

Agentic AI Defense: Decode-Time Provenance Binding for MCP

Decode-time provenance binding is a defense for Model Context Protocol agent pipelines against cross-modal trust laundering, where instructions hidden in an email-signature image via LSB, DCT or metadata steganography get decoded by a tool. It combines HMAC-authenticated trust labels, a provenance ledger and context-taint tracking to block critical tool calls. On a real MCP testbed with 24 adaptive payloads, attack success fell from 100% undefended (62.5% for keyword and regex filters) to 0%.

Model Context Protocol

indirect prompt injectioncross-modal trust launderingsteganography+5

AI Security· Added 26 Oct 2026, published 22 Oct 2026

github.comrepo🛡️ Security

OWASP/MCP-Security-Testing-Guide

OWASP MCP Security Testing Guide is a living, GPL-3.0 collection treating the Model Context Protocol as a security boundary from user through model, MCP client, MCP server and tool to the target system. It covers threats, secure development, host/client controls, supply chain, enterprise gateways, detection, incident response, taxonomy, public incidents, case studies and review checklists, with 79 tests in Chapter 3 (sections 3.1–3.19). It includes a finding template, and it links the MCP Goat lab for safe practice. It is useful to AppSec, red team and SOC people assessing MCP deployments.

Model Context ProtocolLLM

OWASPMCP Goat

AI Security, AppSec· Added 17 Oct 2026

decrypt.coarticle🧠 AI

Chinese Startup StepFun Launches a Phone Built Around an AI Agent, Not Apps

Decrypt reports on StepFun's STEPX Neo phone (3,999 yuan, launched Oct. 13), which runs Step AOS 1.0, an OS built around a system-level agent called Amoo. Phone functions are exposed as small blocks the agent calls via Model Context Protocol. Amoo keeps separate user and task-learning memories, runs simple commands on a small on-device model and sends harder multi-app requests to a larger cloud model. Nearly 100 partners including Alipay, Tencent and Meituan handle payments and bookings on their own platforms, unlike the screen-reading approach of ByteDance's Doubao agent. The article also covers StepFun's Step 5 Preview (600B parameters, 27B active, 1M-token context) and the open-source Step 3.5 Flash.

Model Context ProtocolAndroidLinux+2

StepFunSTEPX NeoStep AOS 1.0+14

agents, models· Published and added 17 Oct 2026

x.comthread🧠 AI

Francis Santerre (@santerref) on X

Tweet announcing that the MCP Adapter is now a canonical plugin on WordPress.org (version 0.7.0). It bridges the WordPress Abilities API to the Model Context Protocol, with a default server at /wp-json/mcp/mcp-adapter-default-server. Only abilities a site marks public are exposed, so the security review comes down to auditing the ability list.

Model Context ProtocolWordPressMCP Adapter+1

Abilities API

mcp· Added 16 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🛡️ Security

Thinking in Graphs: Neo4j-Backed Exploit-Chain Reasoning for LLM Penetration-Testing Agents

Presents ChainGraph, a pattern that externalizes exploit-chain reasoning for LLM pentest agents (Claude Code, Codex) into a Neo4j property graph exposed via the Model Context Protocol. Findings, attack steps, credentials, assets and tamper-evident evidence receipts are typed nodes with pre/post-condition edges, queried with Cypher and Graph Data Science for next-step inference, entry-to-crown-jewel pathing, chain-severity promotion, provenance and chokepoints. On a synthetic GOAD-style multi-forest Active Directory engagement, three Medium findings become Critical once chained, betweenness centrality identifies break-points, and reasoning payload drops ~98% (token proxy); results are single-run and illustrative.

Neo4jModel Context ProtocolClaude Code+3

ChainGraphGOADchain-severity score+1

Offensive Security, AI Security· Added 17 Oct 2026, published 14 Oct 2026

x.comthread🛡️ Security

Phillip Shoemaker (@pbsIdentity) on X

Social thread reacting to a newly disclosed high-severity OAuth vulnerability in the Model Context Protocol Python SDK, where a malicious MCP server could manipulate the authorization flow and steal credentials used by an agent. The author uses it to argue that delegated agent authority needs provenance (who granted it, to which agent, for which service and resource, whether it is transferable or replayable, and when it expires) and that machine-to-machine trust must be auditable by humans. Gives no CVE ID or technical exploit detail.

Model Context ProtocolPythonOAuth

confused deputy

AI Security, Identity & Access· Added 13 Oct 2026, published 12 Oct 2026

x.comthread🧠 AI

=dennis; (@Xidea404) on X

A tweet from @Xidea404 pointing to the ADI Chain MCP Server documentation on docs.adi.foundation. The server lets AI agents interact with the ADI blockchain through the Model Context Protocol. The tweet carries no technical detail itself, so what the server exposes can't be confirmed from it. It is a pointer to a blockchain-specific MCP connector.

Model Context Protocol

ADI ChainADI Foundation

mcp· Published and added 12 Oct 2026

modelcontextprotocol.ioadvisory🧠 AI

MCP spec 2026-07-28 changelog (stateless protocol, MRTR, Sampling/Roots deprecated)

Official changelog for the Model Context Protocol 2026-07-28 specification. Major changes: protocol-level sessions and the initialize handshake are removed to make MCP stateless, with version and capabilities carried in _meta on every request, plus a new server/discover RPC and subscriptions/listen replacing the GET stream and resource subscribe calls. It introduces Multi Round-Trip Requests (InputRequiredResult) in place of server-initiated sampling, roots and elicitation requests, moves tasks into an extension, and deprecates Roots, Sampling, Logging, HTTP+SSE and Dynamic Client Registration. Minor changes add cache hints (ttlMs/cacheScope), new Mcp-Method/Mcp-Name headers, OpenTelemetry trace context, RFC 9207 iss validation and an error-code allocation policy.

Model Context ProtocolOAuthOpenTelemetry+4

SEP-2567SEP-2575SEP-2322+13

mcp· Added 10 Oct 2026

github.comadvisory🧠 AI

MCP specification 2026-07-28 stable release

GitHub release announcing the stable 2026-07-28 revision of the Model Context Protocol specification, published from the modelcontextprotocol/modelcontextprotocol repository. The release page itself only points to the official MCP website for the spec and to a changelog for the detailed changes. It matters as the canonical version marker that MCP client, server and SDK implementers track for protocol changes.

Model Context ProtocolGitHub

mcp· Added 9 Oct 2026

vulnerablemcp.infowriteup🧠 AI

ETDI: Comprehensive MCP Security Framework

ETDI (Enhanced Tool Definition Interface) is a proposed security extension to the Model Context Protocol that adds cryptographically signed and versioned tool definitions, OAuth 2.0 scope-based permissions, Cedar-policy-driven context-aware access control (via engines like Amazon Verified Permissions/OPA), and call-stack verification to stop tool chaining and privilege escalation. It is designed to counter two named MCP threat classes — Tool Poisoning (spoofed/impersonated tool definitions) and Rug Pull attacks (post-approval silent modification of tool behavior) — with concrete pseudocode for signature verification, version/integrity checking, and policy evaluation. The page functions as an implementation guide for MCP client/server builders wanting to harden tool approval and invocation flows.

Model Context ProtocolOAuthCedar+1

ETDI

mcp· Added 8 Oct 2026

decrypt.coarticle🧠 AI

Google Wants Gemini to Be Your Next Coworker—Complete With Its Own Email Address

Decrypt reports on Google Cloud's newly announced Gemini Agent, a long-running AI agent that operates across Gmail, Docs, Sheets, Slides, Drive, Chat, Calendar, Microsoft 365 and Slack, and can run for hours or days on a single goal. The feature allows managers to spin up coworker agents with their own Workspace email address, calendar, Drive storage and directory listing, each given a cryptographically attested identity and a separate audit trail; agents connect to Salesforce, ServiceNow, Jira, Snowflake, BigQuery and any Model Context Protocol server, and are orchestrated across both Gemini and Anthropic's Claude models depending on cost and quality fit. Google pairs the launch with safety infrastructure, an Agent Sandbox, an AI network firewall called Agent Gateway, and real-time token-spend caps, citing a prior Claude Cowork VM-escape finding by Accomplish AI as the kind of containment failure it is designed to prevent.

GeminiClaudeGoogle Cloud+2

AnthropicThomas KurianGrok+9

agents, ai-infra· Published and added 8 Oct 2026

vulnerablemcp.infowriteup🛡️ Security

ETDI: Comprehensive MCP Security Framework

ETDI (Enhanced Tool Definition Interface) is a proposed security extension to the Model Context Protocol that defends against Tool Poisoning (spoofed/impersonated tool definitions) and Rug Pull attacks (silent post-approval modification of tool behavior) using cryptographic signing of tool definitions, immutable versioning with mandatory re-approval, OAuth 2.0 scopes, and Cedar/Amazon Verified Permissions-based policy-aware access control. The page includes detailed attack scenarios, a call-stack verification scheme to prevent tool-chaining privilege escalation, and implementation code for key management, signature verification, and policy evaluation.

Model Context ProtocolOAuthETDI+2

Tool PoisoningRug Pull attackCall Stack Verification

AI Security· Added 8 Oct 2026

arxiv.orgpaper🧠 AI

Applying Security by Design at the Point of Execution: How Governed Security Requirements Affect the Security of AI-Generated Code

The preprint tests whether security requirements from a governed security-by-design knowledge base (SbD-ToE), delivered to a code generator through a Model Context Protocol server at generation time, make AI-written code more secure. On DualGauge (59 Python tasks, LLM-judge scoring) the share of tasks passing all security tests rose from 44.1% to 78.0%. On BaxBench (28 backend scenarios with real exploits in containers) the share of functionally correct solutions with no successful exploit rose from 65% to 86%, comparable to the authors' Oracle Security Reminder (85%). The pre-specified joint secure-and-functional metric did not improve significantly, and the stricter code failed functional tests that fix values the task never states. The study used one model and one generation per task. The authors argue that current benchmarks only detect the weaknesses their evaluators were built for, and propose measuring conformance with the requirements that apply.

Model Context ProtocolPython

DualGaugeBaxBenchSbD-ToE+1

evals, mcp, coding-agents· Added 9 Oct 2026, published 7 Oct 2026

vulnerablemcp.inforepo🛡️ Security

The Vulnerable MCP Project — MCP vulnerability database

The Vulnerable MCP Project is a curated, continuously growing database of security vulnerabilities and attack techniques specific to the Model Context Protocol ecosystem. Entries cover concrete CVEs (e.g. CVE-2025-68143/68144/68145 in Anthropic's mcp-server-git), transport-layer SDK flaws (cross-client response leakage, missing DNS rebinding protection in the official TypeScript/Python SDKs), unauthenticated/0.0.0.0-bound servers enabling RCE (MCPJam inspector, MCP Inspector, Grafana MCP), command/path injection in dozens of third-party servers (gemini-mcp-tool, mcp-server-kubernetes, Framelink Figma MCP, Zen MCP, filesystem-mcp), SSRF chains reaching cloud metadata (MarkItDown MCP, mcp-fetch-server), and a large set of AI-specific attacks: tool poisoning, trigger-phrase data exfiltration, prompt injection via GitHub issues, Jira and Google Docs, rug-pull tool mutation, and cross-server tool-name collisions. It functions as the de facto vulnerability registry for the MCP ecosystem, useful for tracking disclosed issues before patching or adopting third-party MCP servers.

Model Context ProtocolCursorKubernetes+3

CVE-2025-68143CVE-2025-68144CVE-2025-68145+3

AI Security, AppSec· Added 6 Oct 2026

github.comother🧠 AI

Model Context Protocol releases (2026-07-28 stable spec)

The GitHub releases page for the modelcontextprotocol/modelcontextprotocol repository, listing the version history of the Model Context Protocol (MCP) specification from its initial 2024-10-07 draft through the 2025-03-26, 2025-06-18, and 2025-11-25 revisions to the newly stabilized 2026-07-28 revision. Each entry links to its changelog and distinguishes release candidates from final/stable releases, and the page points to the version-negotiation documentation that lets clients and servers agree on which protocol revision to use.

Model Context Protocol

mcp· Added 5 Oct 2026

arxiv.orgpaper🛡️ Security

COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers

COPEX (COntext Provider EXploitation) is a benchmark that isolates the tool-selecting LLM as the unit of evaluation in Model Context Protocol systems, fixing the surrounding agent stack and varying only the model to measure its intrinsic susceptibility to adversarial context. It covers 25 attack types across 125 scenarios spanning four entry surfaces — model/agent, client, server/tool, and transport — and tests nine models across 3,375 trials, finding a mean attack success rate of 64.4% (58.3%–71.4% by surface); combined input and context scanning cut mean attack success by 49.6% on an eight-attack defense subset. The work separates "system exposure" (attacks succeeding outside the model's observation/control) from "model susceptibility," and the benchmark itself is released publicly.

Model Context ProtocolLLM

COPEX

AI Security· Added 6 Oct 2026, published 3 Oct 2026

arxiv.orgpaper🛡️ Security

CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks

CyTReX is a proposed explainable-AI framework for Distributed Energy Resource (DER) network security that converts edge anomaly-detector alerts into ranked, evidence-traceable threat hypotheses for SOC analysts. It builds a structured "evidence packet" combining edge anomaly detection outputs, cloud-layer attack interpretation, SHAP feature attributions, surrogate decision rules, and Model Context Protocol-enabled cyber threat intelligence enrichment, constraining LLM reasoning so every ranked hypothesis and attack-tree branch is traceable to explicit evidence rather than free-form inference. The authors evaluate five pipeline configurations and show that adding reasoning components improves hypothesis specificity and evidence traceability for SOC triage/investigation.

Model Context ProtocolLLMSHAP

AI Security, Blue Team & Detection· Added 6 Oct 2026, published 3 Oct 2026

github.comrepo🧠 AI

Bifrost (Maxim AI) — open-source LLM gateway

Bifrost is an open-source, high-performance LLM gateway (by Maxim AI) that exposes a single OpenAI-compatible API across 23+ providers including OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Cohere, Mistral, and Ollama. It provides automatic failover, load balancing, semantic caching, Model Context Protocol (MCP) tool integration, budget and governance controls, OIDC user provisioning, and Prometheus-based observability, deployable via npx or Docker with claimed sub-15 microsecond overhead at 5,000 RPS. It is positioned as a drop-in replacement requiring only a base-URL change for existing OpenAI, Anthropic, or GenAI SDK code.

DockerGoModel Context Protocol+4

Maxim AI

ai-infra, mcp· Added 2 Oct 2026

github.comadvisory🧠 AI

MCP TypeScript SDK v2.2.0

Release notes for v2.2.0 of the official Model Context Protocol TypeScript SDK. Upgrade notes: machine-to-machine OAuth providers (ClientCredentialsProvider, PrivateKeyJwtProvider, StaticPrivateKeyJwtProvider, CrossAppAccessProvider) should now be given expectedIssuer, and fetchToken() throws AuthorizationServerMismatchError when client information is bound to a different authorization server. listTools/listPrompts/listResources/listResourceTemplates now follow nextCursor automatically, capped by listMaxPages. Fixes include CommonJS type-checking of the DPoP jose types, unhandled rejections in Client.listen(), createMcpHandler stack overflow and subscriptions/listen handling, .localhost loopback for OAuth token endpoints, and v1-to-v2 codemod comment preservation.

Model Context ProtocolTypeScriptOAuth+1

mcp· Added 1 Oct 2026

openid.netpaper🧠 AI

Identity Management for Agentic AI [pdf] (2025)

A whitepaper from the OpenID Foundation, led by Tobin South with contributors from WorkOS, Stanford's Loyal Agents Initiative, and the Artificial Intelligence Identity Management Community Group, mapping how authentication and authorization standards apply to AI agents. It surveys current fixes (OAuth 2.1, Model Context Protocol authorization, enterprise SSO/SCIM provisioning, IPSIE profiles) and lays out unsolved problems for autonomous agents: delegated "on-behalf-of" identity versus user impersonation, consent fatigue at scale, recursive sub-agent delegation, multi-user shared agents, and browser/computer-use agents that bypass API-based authorization entirely.

Model Context ProtocolOAuthSCIM

OpenID FoundationTobin SouthWorkOS+7

mcp, agents, ai-policy· Added 2 Oct 2026, published 1 Oct 2026

thedefiant.ioarticle🧠 AI

Blockworks Opens Its Full Dataset To AI Agents

Blockworks, a crypto research and data provider, launched a hosted Model Context Protocol server that gives AI agents like ChatGPT, Claude and Cursor read access to the datasets underlying its research and its Intel app. The MCP server is included free with every existing API plan and uses the same API key and permission scope as the regular API, rather than requiring separate onboarding.

Model Context Protocol

BlockworksChatGPTClaude+2

mcp· Published and added 1 Oct 2026

blog.modelcontextprotocol.ioarticle🧠 AI

The Official Ruby SDK for MCP Reaches Tier 1

The official Ruby SDK for the Model Context Protocol (the mcp gem) became the sixth Tier 1 MCP SDK in September 2026, after TypeScript, Python, C#, Go and Rust. Version 1.2.0 supports the 2026-07-28 spec revision, including the stateless lifecycle, multi round-trip requests and cache hints. The SDK passes 67/67 server and 50/50 client conformance runs, and the post gives install and upgrade steps.

Model Context ProtocolRubymcp gem+6

Topher BullockKoichi ItoAteş Göral+4

mcp· Added 30 Oct 2026, published 29 Sep 2026

arxiv.orgpaper🧠 AI

Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using MCP

This paper proposes an architectural mediation approach, implemented as the "Eunomia Agent," that uses the Model Context Protocol to let LLM agents discover and invoke Data Space services as structured, schema-driven tools without modifying existing data space components. A prototype validates end-to-end interaction — catalog discovery, metadata retrieval, and data service invocation — while preserving governance, policy, and access-control constraints native to Data Spaces. It offers practical architectural guidance for organizations wanting to introduce AI-driven automation into governed, sovereign data-sharing ecosystems while maintaining compliance and interoperability.

Model Context Protocol

Eunomia Agent

research, mcp· Added 28 Sep 2026

github.comrepo🧠 AI

awslabs/mcp release 2026.09.20260922000649

This is a release changelog for awslabs/mcp, AWS Labs' collection of Model Context Protocol servers covering services like HealthOmics, Aurora DSQL, Bedrock Knowledge Base retrieval, ECS, CloudWatch, billing/cost management, and dataprocessing. This release adds vended metrics tools, SQL parser-based policy guards for Aurora DSQL, agentic retrieval support for Bedrock KB, and fixes several security issues including region validation to prevent SSRF credential disclosure in the CloudWatch server and read-only mode bypass in the MySQL server. It reflects an actively maintained, high-velocity multi-server MCP monorepo used for AWS tool integration with LLM agents.

Model Context ProtocolPythonFastMCP

AWSAWS HealthOmicsAurora DSQL+4

mcp· Added 26 Sep 2026

github.comrepo🧠 AI

MCP Python SDK v2.2.0

Release notes for MCP Python SDK v2.2.0, the reference Python implementation of the Model Context Protocol. Key changes: HTTP client redirects are now restricted to the same origin as the endpoint, idle Streamable HTTP sessions expire after 30 minutes (with a 10,000-session cap), OAuth authorization server metadata issuer checks are now enforced on the legacy discovery path, and new deprecation warnings push toward requiring explicit `issuer=` and `validate_token_resource` settings ahead of a 3.0 release.

Model Context ProtocolPython

mcp· Added 26 Sep 2026

osv.devadvisory🛡️ Security

Vulnerability Database - OSV

CVE-2026-91931 is a critical remote code execution vulnerability in Flowise versions before 3.1.4, triggered through the platform's Custom MCP feature which invokes npx to run Model Context Protocol servers. A fix is available in 3.1.4; the flaw scores 9.0 (Critical) on CVSS, indicating an attacker can achieve arbitrary code execution likely via unsanitized input to the npx invocation path.

FlowiseModel Context Protocolnpm

CVE-2026-91931

AI Security, AppSec· Added 26 Sep 2026

nvd.nist.govadvisory🛡️ Security

CVE-2026-52869: The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP)

CVE-2026-52869 describes a session-hijacking flaw in the MCP Python SDK (PyPI package mcp) prior to version 1.27.2: the SSE and stateful Streamable HTTP transports (mcp.server.sse.SseServerTransport and mcp.server.streamable_http_manager.StreamableHTTPSessionManager) route requests to existing sessions using only the session_id query parameter or Mcp-Session-Id header, without checking that the requesting principal matches the session's original authenticated bearer-token client. This lets a different authenticated client that learns or guesses a valid session ID inject JSON-RPC messages into another user's MCP session. CVSS 3.1 base score 7.1 (High); fixed in mcp 1.27.2.

Model Context ProtocolPython

CVE-2026-52869

AppSec· Added 26 Sep 2026

arxiv.orgpaper🛡️ Security

No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

This paper proposes no-box vulnerability analysis, a new paradigm for auditing systems using only functionality metadata when neither system access nor runtime interaction is available. The authors build MCPSEC, a prototype that audits Model Context Protocol servers for indirect prompt injection vulnerabilities purely from tool metadata exposed at server registration, evaluating it against 20 widely-deployed MCP servers with 177 tools where human evaluators confirmed 95 vulnerable tools; MCPSEC achieved 98.9% recall versus 84.2% for an LLM baseline, also producing hypothesized exploitation techniques per finding.

Model Context ProtocolLLM

MCPSEC

AI Security· Added 26 Sep 2026

arxiv.orgpaper🛡️ Security

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

ShareLock is a novel Tool Poisoning Attack against the Model Context Protocol that uses Shamir's secret-sharing scheme to split a malicious instruction into benign-looking fragments distributed across multiple tool descriptions, evading detectors that look for monolithic malicious text in a single tool. A covert trigger planted during a server update reconstructs the hidden instruction, and the authors report over 90% attack success across mainstream LLMs and two MCP clients while evading tool-description-based detection far better than prior single-tool poisoning approaches.

Model Context ProtocolLLM

Tool Poisoning AttackShamir's Secret SharingShareLock

AI Security· Added 26 Sep 2026

arxiv.orgpaper🛡️ Security

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers

MCPTox is a benchmark for evaluating Tool Poisoning Attacks against LLM agents using the Model Context Protocol, where malicious instructions are hidden in a tool's metadata rather than its output. Built on 45 live real-world MCP servers and 353 authentic tools, it generates 1312 malicious test cases across 10 risk categories via three attack templates, and finds widespread vulnerability across 20 LLM agents: o1-mini has a 72.8% attack success rate, more capable models are often more susceptible due to stronger instruction-following, and even the best model (Claude-3.7-Sonnet) refuses less than 3% of attacks.

Model Context Protocolo1-miniClaude-3.7-Sonnet

Tool Poisoning AttackMCPTox

AI Security· Added 26 Sep 2026

bex.coarticle🛡️ Security

30+ MCP CVEs in Two Months: What the Early-2026 Vulnerability Wave Means for Your MCP Supply Chain

Analysis of 30+ CVEs filed against Model Context Protocol servers, clients, SDKs, and proxies in the first two months of 2026, showing the flaws concentrated in plumbing (proxies, registries, transports) rather than tool implementations. It walks through CVE-2025-6514 (CVSS 9.6 RCE in mcp-remote via unsanitized OAuth authorization_endpoint URLs shelled out to launch a browser), the chained Atlassian MCP server CVEs (CVE-2026-27825/CVE-2026-27826), unauthenticated public registries, and a systemic stdio-transport advisory, then ties the findings to the NSA's May 2026 MCP security CSI and the OWASP MCP Top 10.

Model Context Protocolmcp-remoteClaude Desktop+3

CVE-2025-6514CVE-2026-27825CVE-2026-27826+5

AI Security, Supply Chain, AppSec· Added 26 Sep 2026, published 23 Sep 2026

arxiv.orgpaper🛡️ Security

A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

A2M (Attraction-to-Manipulation) is a two-stage black-box framework for hijacking agents that use the Model Context Protocol to select tools from third-party MCP servers. The Attraction phase optimizes attacker-controlled tool metadata to raise invocation probability, while the Manipulation phase uses execution traces to craft adversarial tool outputs that steer agent behavior; on LiveMCPBench it achieves a 93.6% malicious tool invocation rate against GLM-4.6, inflates token cost 32.4x under a cognitive denial-of-service variant, and reaches a 74.4% mean attack success rate across information exfiltration, environment integrity compromise, and reasoning derailment, with partial transfer (63.6%/2.7x/24.5%) to four other models without re-optimization. The authors argue this exposes a semantic supply-chain risk in MCP tool ecosystems and call for stronger tool vetting and runtime isolation.

Model Context ProtocolGLM

LiveMCPBenchA2MCognitive Denial of Service

AI Security· Added 2 Oct 2026, published 22 Sep 2026

arxiv.orgpaper🛡️ Security

Zero-Trust Authorization and Discovery for Enterprise MCP

This paper analyzes authentication/authorization gaps in the six official Model Context Protocol SDKs (Python, TypeScript, Go, Rust, C#, Swift), identifying structural shortcomings for enterprise zero-trust deployments: single-header credential binding that breaks dual-persona (human SSO vs. service-account) setups, no pre-authentication tool discovery, and no fine-grained per-tool authorization. The authors propose composable FastMCP extensions — cross-header credential normalization, cached cross-IdP token verification, an unauthenticated metadata/discovery endpoint, and permission-filtered tool visibility enforced consistently at invocation — and test them against four frontier LLMs over 2160 attempts, showing an in-body-check-only server leaks forbidden tools 21.1% of the time versus 0% with permission-aware visibility, while also showing visibility-only filtering is still bypassable by scripted clients and models can infer hidden tool names up to 94% of the time from prompt context.

Model Context ProtocolFastMCPPython+3

AI Security, Identity & Access· Added 2 Oct 2026, published 18 Sep 2026

arxiv.orgpaper🛡️ Security

VIPER-MCP: Detecting Vulnerabilities in MCP Servers

VIPER-MCP is an end-to-end automated auditing framework that combines two-pass static taint analysis (anchor queries mapping alerts to specific MCP tool handlers) with feedback-driven LLM prompt evolution to both detect and dynamically confirm taint-style vulnerabilities (command injection, SSRF, path traversal) in Model Context Protocol servers. Run against 39,884 real-world open-source MCP server repositories, it discovered 106 0-day vulnerabilities — all confirmed via end-to-end exploit traces with concrete proof-of-concept natural-language prompts — resulting in 67 assigned CVEs, including a root-privilege RCE in the bytebot computer-use agent. It reports 0% false positive rate and 7.7% false negative rate, substantially outperforming existing static and dynamic MCP security baselines.

Model Context ProtocolLLMDocker+3

bytebotCWE-78CWE-918+1

AI Security, AppSec· Added 22 Sep 2026, published 17 Sep 2026

arxiv.orgpaper🛡️ Security

Closed-World Resolution Against Tool Hallucination in LLM Agents

This arXiv paper identifies tool hallucination — LLM agents calling nonexistent tools or passing undeclared arguments — as a structural blind spot that existing tool-selection and tool-gating defenses cannot catch, since a hallucinated call was never a real gating decision. The authors propose a five-class taxonomy (H1-H5) of tool hallucination and a training-free closed-world resolver (the Resolution Rung, based on registry membership plus signature checking) that must run before any causal gate, then extend the analysis to the Model Context Protocol where merging multiple servers into one namespace creates a second hallucination class (M1-M5) from tool collisions and shadowing. Across ten hosted models they measure 322 hallucinations on single-registry tool calls and 154 on a live MCP surface, and release the versioned Hallucinated-Tools Benchmark (HTB) for comparing resolvers.

Model Context ProtocolLLM

Hallucinated-Tools Benchmark

AI Security· Added 2 Oct 2026, published 16 Sep 2026

arxiv.orgpaper🧠 AI

Closed-World Resolution Against Tool Hallucination in LLM Agents

This arXiv paper studies tool hallucination in tool-augmented LLM agents, where agents call tools that do not exist or pass arguments no schema declares, arguing existing tool-selection and tool-gating defenses structurally cannot catch it since a hallucinated call was never a decision a gate made. The authors give a five-class taxonomy (H1 to H5), propose the Resolution Rung, a training-free closed-world resolver based on registry membership plus a signature check that must run before any causal gate, and extend the analysis to the Model Context Protocol with a second taxonomy (M1 to M5) covering collisions and shadowing when multiple servers are merged into one namespace. Across ten hosted models they measure 322 hallucinations on two invocation surfaces and 154 on a live MCP surface, and release the versioned Hallucinated-Tools Benchmark for comparing resolvers.

Model Context Protocol

Laxmipriya Ganesh Iyer

mcp, evals· Added 2 Oct 2026, published 16 Sep 2026

github.comrepo🧠 AI

bsab/sweden-mcp-servers

A community-maintained catalog of Model Context Protocol servers connecting AI assistants to Swedish data, laws and services (e.g. Fortnox, Bokio, BolagsAPI, ICA), forked/adapted from the France and Italia MCP Servers projects. Each entry is checked against canonical documentation, tracks license/credential requirements, and includes a runtime smoke-test report (protocol/tool call attempts, credential blockers, failures) plus a six-criterion documentation-readiness rubric, published as a static JSON/HTML site.

Model Context ProtocolPython

FortnoxBokioBolagsAPI+3

mcp· Added 26 Sep 2026, published 14 Sep 2026

arxiv.orgpaper🛡️ Security

VIPER-MCP paper

VIPER-MCP is an automated auditing framework for Model Context Protocol servers that detects taint-style vulnerabilities in tool handlers and dynamically confirms exploitability via generated proof-of-concept prompts. It uses two-pass static analysis plus feedback-driven prompt evolution, and scanning 39,884 real-world MCP server repos found 106 0-day vulnerabilities with 67 CVE IDs assigned.

Model Context Protocol

VIPER-MCP

AI Security, AppSec, Offensive Security· Added 22 Sep 2026, published 13 Sep 2026

github.comrepo🛡️ Security

shinthink/blitzstrike

Blitz Strike is an open-source Model Context Protocol server (TypeScript/Bun) that packages a structured 3-tier pentesting methodology — BLITZ (attack-surface recon), EAGLE-EYE (source-to-sink reachability tracing), and STRIKE (live validation before reporting) — into callable tools any MCP client (Claude Code, Cursor, Gemini, etc.) can drive with a single run_engagement call. It ships 130 self-written security tools, 317 indexed tool manuals, 58 data-driven escalation chains with negative-control checks, a Web3/Solidity audit module with Foundry proofs, and a regression/benchmark suite (453 checks, reported 1.0 detection / 0 false-positive rate) to make every finding verified rather than pattern-matched.

Model Context ProtocolBunTypeScript+3

IDORSSRFPayloadsAllTheThings+3

Offensive Security, AI Security, AppSec· Added 2 Oct 2026, published 12 Sep 2026

x.comthread🛡️ Security

0xor0ne (@0xor0ne) on X

A tweet from @0xor0ne surfacing two blog posts by researcher ZephrFish on using LLMs for vulnerability research: one describing an MCP (Model Context Protocol) server for the workflow, and a second on 'harnessing' LLMs for this purpose. The posts (hosted at blog.zsec.uk) cover applying LLM agents to vulnerability discovery/analysis tasks.

Model Context ProtocolLLM

ZephrFish

AI Security, Offensive Security· Published and added 9 Sep 2026

github.comrepo🛡️ Security

mukul975/cve-mcp-server

cve-mcp-server is a Model Context Protocol server that gives Claude direct access to 28 security tools spanning 24 APIs (NVD, EPSS, CISA KEV, OSV.dev, GitHub GHSA, MITRE ATT&CK, AbuseIPDB, GreyNoise, Shodan, VirusTotal, MalwareBazaar, ThreatFox, Ransomwhere, and more), fronted by a one-call triage_cve orchestrator. It computes a composite 0-100 risk score from CVSS, EPSS, KEV status, and PoC availability (with a hard CISA KEV override forcing CRITICAL/≥76), supports dependency scanning via OSV, IP/domain reputation lookups with private-IP blocking, and ships an SSVC v2 gated decision mode plus audit logging and XML-bomb protections via defusedxml.

Model Context ProtocolClaude DesktopClaude Code+9

CVE-2021-44228CVE-2024-3400CVE-2023-44487+3

AI Security, Threat Intel· Published and added 7 Sep 2026

github.comrepo🛡️ Security

Awesome Cybersecurity Agentic AI

A curated GitHub awesome-list cataloging the emerging agentic-AI security ecosystem: dozens of Model Context Protocol servers that give LLM agents access to security tools (Nuclei, Shodan, VirusTotal, Burp Suite, Ghidra, BloodHound, x64dbg), autonomous penetration-testing and CTF-solving agent frameworks (CAI, pentagi, BreachSeek, Dark-Moon, D-CIPHER), scanners/guardrails that audit agent skills, MCP servers, and multi-agent chains for prompt injection and other risks (Aguara, Inkog, MCP Doctor, AI-Infra-Guard, ATR), agentic SOC/detection platforms (Vigil), threat-modeling frameworks for agentic systems (MAESTRO, ATFAA/SHIELD), research papers, benchmark datasets, and community/learning resources. It functions as a living index for anyone building or defending AI-agent-driven security tooling.

Model Context ProtocolLangChainCrewAI+3

OWASP Top 10 for LLM ApplicationsEU AI ActOWASP FinBot CTF+1

AI Security, Offensive Security, Blue Team & Detection· Added 3 Sep 2026, published 31 Aug 2026

blog.modelcontextprotocol.ioarticle🧠 AI

The New MCP Roadmap

The Model Context Protocol Core Maintainers publish an updated roadmap covering five priority areas: agentic messaging primitives (server-initiated events, maturing the Tasks extension SEP-2663), HTTP-native transport unification (including local servers over Streamable HTTP/stdio), agent identity and enterprise security (DPoP, Workload Identity Federation, ID-JAG grant, token exchange, engagement with IETF OAuth and WIMSE working groups), improved tool-call result primitives and progressive tool discovery, and SDK developer experience. It also recaps the previous roadmap's shipped work in the 2026-07-28 spec release — removal of protocol-level sessions/handshake for stateless horizontal scaling, server/discover, cacheable list results, Multi Round-Trip Requests (SEP-2322), issuer validation, issuer-bound client credentials, and Client ID Metadata Documents (CIMD).

Model Context ProtocolOAuth

IETFWIMSE

mcp· Added 7 Oct 2026, published 22 Aug 2026

blog.modelcontextprotocol.ioarticle🛡️ Security

The New MCP Roadmap

Official blog post from the Model Context Protocol Core Maintainers laying out the updated project roadmap, with a significant authorization/identity component: it recaps the 2026-07-28 spec release's security work (issuer validation, issuer-bound client credentials, Client ID Metadata Documents as the preferred client registration path, and a now-stable Enterprise-Managed Authorization extension) and names "Agent identity and enterprise-ready security" as a top priority going forward. That upcoming work covers finalizing DPoP, defining agent identity and delegation through Workload Identity Federation, the ID-JAG grant, and standard token exchange, plus deeper engagement with the IETF OAuth and WIMSE standards groups — aimed at moving MCP server authorization away from long-lived API keys toward cryptographically bound, delegated agent identities.

Model Context ProtocolOAuth

DPoPWorkload Identity FederationID-JAG+4

Identity & Access· Added 8 Oct 2026, published 22 Aug 2026

rapid7.comarticle🛡️ Security

Rapid7

Rapid7's release notes for Metasploit Framework 6.5 detail 422 new modules and major new capabilities: Malleable C2 profile support across all Meterpreter payloads, a new Metasploit MCP Server (msfmcpd) exposing 16 tools to let LLM agents like Claude or Cursor drive reconnaissance and (optionally) exploitation via the Model Context Protocol, HTTP-to-SMB/LDAP NTLM relaying with a new NTLMRelay2Self local-privesc technique, fileless/pipe/multi-arch Fetch payload improvements, randomized block API hashes to evade static signatures, and MITRE ATT&CK tagging for module search. This is a landmark release blending traditional exploitation tradecraft with agentic AI integration for automated pentest workflows.

MetasploitModel Context ProtocolMITRE ATT&CK+3

NTLMRelay2SelfT1059.001T1059

Offensive Security, AI Security· Added 7 Aug 2026, published 30 Jul 2026

github.comrepo🛡️ Security

Bug Bounty Directory & MCP API

bug-bounties is a community-maintained directory of over 3,000 active bug bounty programs and vulnerability disclosure policies (VDPs), exposed via a public API and a Model Context Protocol (MCP) server. It lets researchers programmatically query scope, rewards, and program metadata, and lets AI coding agents like Claude Code look up bug bounty targets directly.

Model Context Protocol

Offensive Security· Added 3 Sep 2026, published 29 Jul 2026

owasp.orgadvisory🛡️ Security

OWASP MCP Top 10 | OWASP Foundation

The OWASP MCP Top 10 (2025) is a living-document taxonomy of the ten most critical vulnerability classes affecting Model Context Protocol-based AI systems, covering issues like token mismanagement, privilege escalation via scope creep, tool poisoning, MCP-specific supply chain and dependency tampering, command injection, prompt injection via contextual payloads, weak authN/authZ, missing audit/telemetry, shadow MCP servers, and context injection/over-sharing. It targets AI/ML developers and security practitioners building agentic, model-chaining, and multi-modal MCP deployments, giving them a common vocabulary and checklist for secure design and auditing analogous to the OWASP Top 10 for LLM Applications.

Model Context Protocol

OWASP MCP Top 10

AI Security· Added 3 Jul 2026

blog.modelcontextprotocol.ioarticle🛡️ Security

The 2026-07-28 MCP Specification Release Candidate

The MCP (Model Context Protocol) team announces the 2026-07-28 spec release candidate, the largest revision since launch, which removes the protocol-level session/handshake in favor of a stateless request model and restructures server-to-client interactions. The security-relevant core is a set of authorization SEPs that harden OAuth 2.0/OIDC usage: clients must validate the `iss` parameter per RFC 9207 to mitigate authorization-response mix-up attacks, declare `application_type` during Dynamic Client Registration to avoid redirect-URI misclassification, bind credentials to the issuing authorization server, and clarify scope accumulation during step-up auth. A related change requires that server-initiated requests (e.g. elicitation prompts) only be issued while actively processing a client-originated call, closing a class of out-of-nowhere prompt/consent issue for agentic clients.

Model Context ProtocolOAuthOIDC

RFC 9207mix-up attack

Identity & Access, AI Security· Added 28 Jul 2026, published 21 May 2026

github.comrepo🛡️ Security

paralax/SeldomMonster

SeldomMonster is a collection of Model Context Protocol servers built for Gemini CLI (but MCP-generic) that wrap free/community cyber threat intel APIs — GreyNoise, Malpedia, OpenCTI, AlienVault OTX, ransomware.live, IBM X-Force, YaraHub, blockchain transaction lookups, and r/netsec/r/blueteamsec feeds — plus a separate set of macOS tools (Nmap as the only third-party dependency) for discovering and hacking devices on the local network. It's a practical toolkit for wiring an LLM agent directly into IOC enrichment, ransomware tracking, and local network recon/exploitation workflows.

Model Context ProtocolGemini CLINmap+3

MalpediaOTXIBM X-Force+4

Threat Intel, Offensive Security· Published and added 12 May 2026

github.comrepo🛡️ Security

mcpwn

mcpwn is a CLI security scanner for Model Context Protocol (MCP) servers, described as "nikto or nuclei, but for MCP servers." It runs checks (MCP-001 through MCP-013+) that statically analyze tool descriptions/schemas for hidden-instruction tool poisoning and, in an --aggressive mode, actively probe for prompt injection via tool output, SSRF against internal IPs/cloud metadata endpoints, command injection via shell metacharacters, cross-tool data exfiltration via canary tokens, and hardcoded secrets in resources. It supports stdio/SSE/HTTP transports, JSON/SARIF output for CI gating, and pairs with a companion runtime tool called mcp-firewall.

Model Context ProtocolPythonpip+2

AI Security· Published and added 6 May 2026