92 results for “MCP servers”

Hotseat is a free, open-source macOS menu bar app that moves Claude Code and Claude Desktop to another of the user's Claude accounts in one click and returns to the same session. Sessions, settings, skills and MCP servers are shared, so `claude --resume` works under either account. When a session hits a usage limit, it offers to continue under another account. It never reads tokens or cookies. Install with Homebrew.

x.comtoolAdded 1 Nov 2026, published 31 Oct 2026🧠 AI

The SAIL Framework from Pillar Security is a seven-phase, lifecycle-oriented method for securing AI systems. The phases are AI policy and safe experimentation, AI asset discovery, AI security posture management, AI red teaming, runtime guardrails, sandboxed execution for agents and MCP servers, and AI activity tracing. It argues for a "Shift Up" approach that protects the business logic AI controls, and it is meant to sit on top of existing standards.

pillar.securityarticleAdded 29 Oct 2026🛡️ Security

An AIBOM is a machine-readable inventory of models, datasets, dependencies, AI services, agents and MCP servers, with evidence of origin, license, integrity and evaluation. The Endor Labs explainer walks through a worked CycloneDX example for a fine-tuned support assistant. It compares CycloneDX ML-BOM, SPDX 3.x, the OWASP AIBOM project and the May 2026 CISA/G7 guidance, and lists what an AIBOM cannot show: runtime behavior and agent actions.

endorlabs.comarticlePublished and added 29 Oct 2026🧠 AI

AIBOM explainer from Endor Labs: an AI bill of materials is a machine-readable inventory of models, datasets, dependencies, AI services, agents and MCP servers, with origin, license and integrity evidence. It walks through a CycloneDX entry for a fine-tuned model, compares CycloneDX ML-BOM, SPDX 3.x, the OWASP AIBOM Generator and the May 2026 CISA/G7 minimum-elements guidance, and lists a six-step build process. It also states what an AIBOM cannot show: model safety, runtime behavior and coding-agent actions.

endorlabs.comarticlePublished and added 29 Oct 2026🛡️ Security

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.

x.comthreadAdded 29 Oct 2026, published 27 Oct 2026🧠 AI

The tweet relays Pillar Security research that opencode on Windows and WSL could run attacker-controlled code during remote MCP server OAuth sign-in. The fix shipped in opencode 1.18.33 on 28 September, with no advisory or CVE published. It advises users of remote MCP servers to update and review which servers they connect to. Technical details are not in the post.

x.comthreadAdded 29 Oct 2026, published 27 Oct 2026🛡️ Security

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.

arxiv.orgpaperAdded 28 Oct 2026, published 26 Oct 2026🛡️ Security

Post explaining Claude's new support for MCP Tasks and Elicitations. A server returns a durable task handle instead of blocking. The client polls tasks/get every 250 ms to 30 s, and states are working, input_required, completed, failed or cancelled. Elicitations pause a task at input_required for human approval. It also notes Cloudflare's stateless MCP servers and Code Mode, and Sentry and Linear adoption.

x.comthreadAdded 25 Oct 2026, published 24 Oct 2026🧠 AI

ADLC Security Best Practices is an Endor Labs guide to controlling what AI coding agents can access, run, install and ship. It covers inventorying agents and MCP servers, sandboxing, pre-execution hooks instead of AGENTS.md rules, install-time package checks against slopsquatting and malware, reachability-based triage of agent PRs, and CI/CODEOWNERS protections. A five-step worked example and coverage metrics are included.

endorlabs.comarticlePublished and added 23 Oct 2026🛡️ Security

Post summarising Pillar Security's finding of a remote code execution flaw in OpenCode, the open-source AI coding agent. Versions 1.0.137 through 1.18.32 could run code from a remote MCP server during OAuth sign-in on Windows and WSL, with no prompt injection needed. The fix is in 1.18.33 (released 28 September). No advisory or CVE was issued, so scanners will not flag old installs. Interim advice is to remove unvetted remote MCP servers.

x.comthreadAdded 22 Oct 2026, published 21 Oct 2026🛡️ Security

Paulo Pierrondi's X post, part 9 of a series on installing MCP servers, lists a monthly review of installed servers. The checks are which tools the agent used, servers not called in weeks, overlapping tools that confuse the model, and whether each server still has an owner. A reply adds a decommissioning check: after removal, confirm the server's old credentials can no longer call the backend.

x.comthreadPublished and added 20 Oct 2026🧠 AI

ToFu is a tool-aware fuzzing framework for LLM tools, including MCP servers. It maps each tool argument, using its metadata, to one of 74 CWE-guided semantics-aware sanitizers (path, URL, SQL and similar). It then generates schema-valid Atheris harnesses and semantic oracles, using runtime tracers for in-process tools and outcome oracles for opaque ones. The LLM (gpt-4.1) only maps sanitizers and writes seeds; it is never the security judge. The paper also shows a "Repeat-After-Me" trick, where an LLM told to repeat attacker-crafted text emits a tool call the orchestrator executes, reproduced on LangGraph, MAF, ADK 2.0, AutoGen, Strands and CrewAI. Across 273 runnable MCP servers (3,405 tools) it reports 253 verified bugs in 343 tools across 118 servers, such as path traversal, log injection and exfiltration. These are failures a crash-based fuzzer would miss. The result matters because it shows LLM-generated tool arguments cannot be treated as trusted.

arxiv.orgpaperAdded 18 Oct 2026🧠 AI

ToFu is a tool-aware fuzzing framework that derives semantic security checks for LLM tools (mainly MCP servers) from their metadata and a corpus of 74 CWE-guided sanitizers. It generates schema-valid Atheris harnesses, uses runtime tracers and outcome oracles to catch bugs that don't crash, and uses an LLM only to map sanitizers and seed inputs, never as the judge. It also describes a "Repeat-After-Me" attack, in which the LLM is told to repeat attacker-written text that the orchestrator then dispatches as a tool call. It was reproduced on LangGraph, MAF, ADK, AutoGen, Strands and CrewAI. On 273 MCP servers it reports 253 verified bugs across 343 tools in 118 repositories, including path traversal, log injection, exfiltration and command bypass.

arxiv.orgpaperAdded 18 Oct 2026🛡️ Security

Post warning that FastMCP had a critical flaw where a malicious MCP server could execute code on the connecting client through a crafted tool schema. Fixed in FastMCP 3.4.8 and 4.0.11, and there is no patch for the 2.x line. It matters to anyone whose agents connect to MCP servers they don't control. The post gives no CVE ID or technical root cause.

x.comthreadAdded 18 Oct 2026, published 17 Oct 2026🛡️ Security

An X post advises auditing every MCP write tool against the database role it actually runs under. A shared service key lets prompt injection trigger unapproved writes, so each agent session should get a read-only role, with a test that writes are denied. Replies note that MCP servers often inherit ambient host credentials or can escalate through a second connection pool, and suggest also testing that another tenant's rows are unreadable with the same role.

x.comthreadAdded 18 Oct 2026, published 16 Oct 2026🛡️ Security

Studies "filesystem capability laundering" in MCP servers: client approval of a tool call grants the server process broad host filesystem access, so attacker-steered arguments can reach sensitive files outside the tool's declared contract. The authors build MCP-FSD, which infers per-tool least-privilege boundaries, plants credential fixtures outside them, and tests exploitability and sandbox containment by paired dynamic execution. Of 21,097 servers from nine registries, 16.4% of 4,806 triaged servers have filesystem capabilities despite non-filesystem classifications. Dynamic validation confirmed 150 vulnerable instances, and disclosure produced 13 advisories, including two CVEs in Anthropic's Git MCP Server.

arxiv.orgpaperAdded 17 Oct 2026, published 15 Oct 2026🛡️ Security

An Ethereum Magicians proposal for ERC-8444, which adds an onchain value and settlement layer under Google's Agentic Resource Discovery (ARD) spec for finding MCP servers, A2A agents, skills and APIs. A thin kernel records kind (skill, task, agent, registry), a CAIP-19/CAIP-10 anchor, a JCS+SHA-256 descriptor hash, a canonical URN and a status. Authority belongs to the paid address, and domains act as collected endorsements through /.well-known/ard.json. The reference implementation has Foundry-tested Solidity adapters and a Node.js gateway that passes the official ARD conformance CLI. It introduces a "task" kind (application/ai-task+json) for tenders aimed at suppliers, and the author asks for feedback on the trust root, the hash scope, same-chain anchors and the task payload.

ethereum-magicians.orgthreadAdded 14 Oct 2026, published 13 Oct 2026🧠 AI

A guided tour of a GitHub repository of resources and examples for building AI agents, published on the Becoming a Hacker blog. Per the routing note, it covers LangChain 1.x, LCEL, RAG, LangGraph, CrewAI, DeepAgents, MCP servers and token-cost control such as caching, routing and budget guards. The fetched page held only a LinkedIn redirect notice, so the article text was not read.

linkedin.comarticleAdded 13 Oct 2026🧠 AI

Guided tour of Omar Santos's eight-part AI-agents-for-cybersecurity repository. It moves from LLM building blocks (LangChain, RAG) to security agents built with LangGraph, CrewAI, DeepAgents and MCP servers (nmap, CISA KEV, Shodan). It also covers a hardening guide for six agentic frameworks, token-cost control, and a spec for a supervisor-led, human-gated assessment harness. Design lessons include least-privilege subagents, single-use approvals and kill switches.

becomingahacker.orgarticleAdded 13 Oct 2026🧠 AI

Companion repository for Omar Santos's Pearson and O'Reilly trainings and books. It has eight parts of runnable Python labs: chat models, embeddings, prompt templates, LCEL prompt chaining, Chroma-based RAG, ReAct/LangGraph/CrewAI/DeepAgents agents, and FastMCP servers (nmap, CISA KEV, Shodan). It also includes guides to six agentic frameworks (OpenClaw, Hermes, Agent Zero, OpenHands, Paperclip, Buzz), a tokenomics module on agent cost (context compounding, prompt caching, model routing, token budget guards, batch API, cost per accepted outcome), and a vendor-neutral design spec for a human-gated multi-agent assessment harness. It is a current, practical curriculum for building and operating agents. Some examples act on real systems and should only be run in an authorized lab.

github.comrepoAdded 13 Oct 2026🧠 AI

Omar Santos walks through his eight-part AI-agents-for-cybersecurity repository: LLM building blocks (LangChain, RAG), then security agents with LangGraph, CrewAI, DeepAgents and MCP servers (nmap, CISA KEV, Shodan), a hardening guide for six agentic frameworks, token-cost control for agents, and a spec for a supervisor-led, human-gated security-assessment harness. It covers concrete design lessons such as least-privilege subagents, staged response actions, single-use approvals bound to exact actions, kill switches, and mapping controls to the OWASP Top 10 for Agentic Applications. Also notes Project CodeGuard rules shipped for AI coding assistants.

becomingahacker.orgarticleAdded 13 Oct 2026🛡️ Security

Omar Santos walks through his AI-agents-for-cybersecurity GitHub repo, which has eight parts. Parts 1–4 cover LLM basics (LangChain, prompting, LCEL, RAG). Parts 5–8 cover building security agents with LangGraph, CrewAI, DeepAgents and MCP servers (nmap, CISA KEV, Shodan), and a hardening baseline for six ready-made agentic frameworks. They also cover token-cost control (caching, routing, budget guards, cost per accepted outcome) and a supervisor-led, human-gated security-assessment harness spec with single-use approvals, a kill switch and an append-only audit log. The post also covers Project CodeGuard rules for AI coding assistants. It is a practical learning path and a reference for governing and securing agents.

linkedin.comarticleAdded 13 Oct 2026🛡️ Security

Beginner-oriented GitHub blog guide to giving GitHub Copilot project context through four mechanisms: repository custom instructions (.github/copilot-instructions.md and path-specific .github/instructions files with applyTo), agent skills (SKILL.md folders under .github/skills), custom agents (.github/agents profiles), and MCP servers such as Playwright. It explains when to use each and how they combine, using examples like a quality-checks skill and an accessibility-review agent. Useful as a concrete reference for the repo layout Copilot reads, with a pointer to the community Awesome Copilot collection.

github.blogarticlePublished and added 12 Oct 2026🧠 AI

Endor Labs whitepaper on using context engineering to make AI coding assistants produce secure code. It covers secure prompting (priming, decomposition, refinement with design-spec and test-first patterns), reusable system rules such as Cursor rules and the CSA R.A.I.L.G.U.A.R.D. framework, and external SAST/SCA tools wired in through MCP servers with a rule that triggers scans. It also covers the costs and risks: extra token use, models ignoring rules, untrusted community rules, and MCP server supply-chain threats. It cites figures such as 62% of AI-generated solutions containing flaws and a 77.5% reduction in weaknesses from recursive prompting.

endorlabs.comarticlePublished and added 12 Oct 2026🧠 AI

Endor Labs' 2025 State of Dependency Management report examines how AI coding agents and MCP servers add supply chain risk. Researchers analysed 10,663 GitHub MCP server repositories and tested AI-generated dependency recommendations across PyPI, npm, Maven and NuGet, finding agents import vulnerable or non-existent packages. MCP servers are immature: 75% are built by individuals, 41% lack license info, and 82% use sensitive APIs. The report advises treating AI-generated code as untrusted third-party input subject to code review, SAST/SCA and dependency governance.

endorlabs.compaperPublished and added 12 Oct 2026🛡️ Security

iran-mcp is an open-source catalog of 39 MCP servers (488 tools) that let AI agents query Iranian websites such as Digikala, Torob, Divar, Snappfood, Jabama, Paziresh24, TSETMC and qavanin.ir, with prices normalised to Toman. Most servers are unofficial, read-only Python packages run with uvx; three are official hosted servers. It ships Claude Code plugins, Agent Skills, bundles, proxy lists and a machine-readable servers.json.

github.comrepoAdded 24 Oct 2026, published 11 Oct 2026🧠 AI

Adversa AI's October 2026 MCP security roundup, aggregating and synthesizing 15 resources: authentication-bypass vulnerabilities in LiteLLM's MCP endpoint (CVE-2026-59822, now CISA KEV), Grafana's MCP server session spoofing/SSRF (CVE-2026-19516), an MCP Python SDK OAuth-fallback flaw exploited by a malicious server returning a 404, and an Obot gateway route-matching bypass reopening GHSA-vw82. It also covers detection failures (two malicious MCP servers passing five scanners including Cisco mcp-scanner and Snyk agent-scan, 12% of 82,000 public MCP configs hardcoding secrets), a malicious npm wallet-signing package (gadgethumans-mcp), the A2M agent-hijacking attack technique, and CoSAI's MCP Security v2.0 governance model.

adversa.aiarticlePublished and added 8 Oct 2026🛡️ Security

Latent Space interviews Stacklok founders Craig McLuckie and Joe Beda (Kubernetes co-creators) about Mecatl, an open-source "cloud-native harness" for coding agents that separates the agent loop from local tool execution, session state and model provider so enterprises can run and govern agents centrally rather than on individual desktops. The piece also covers Stacklok's earlier pivot from supply-chain security to ToolHive, an open-source platform/Kubernetes operator for running and governing MCP servers, and a not-yet-open-sourced "AI Gateway" focused on access control, budgets and provider routing for regulated enterprises (banks, telcos, semiconductor firms). The framing draws an explicit analogy to how Kubernetes decoupled enterprises from cloud providers, arguing agent harnesses need the same "cattle not pets" treatment to scale beyond desktop tools like Claude Code, Codex and GitHub Copilot.

latent.spacearticlePublished and added 7 Oct 2026🧠 AI

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.

vulnerablemcp.inforepoAdded 6 Oct 2026🛡️ Security

A Twitter/X thread reacting to OpenAI's announcement that ChatGPT Sites can now host MCP servers, including turning plugin extensions into deployable MCP servers (e.g. "@sites create a todo list that I can use in ChatGPT"). User Dave Gilbert (@docgotham) flags a concrete operational bug: with a ChatGPT Pro account, custom MCP servers can't be refreshed — disconnecting/reconnecting or even deleting and re-adding a server still serves the old cached plugin version after an update.

x.comthreadPublished and added 2 Oct 2026🧠 AI

Claude Code added a `claude --desktop` command that opens the Desktop app on the current directory or a resumed/continued session, plus `claude plugin configure` to view a plugin's options. Bundled .mcpb MCP servers can now have their settings set at `plugin install --config` time so they start immediately without a manual Configure step. The post also notes CLAUDE_CODE_DISABLE_WEB_FETCH to disable WebFetch and an allowedProviders setting to restrict which API providers a managed machine can use.

x.comthreadPublished and added 30 Sep 2026🧠 AI

Researchers at Island identified nearly 7,600 malicious GitHub repositories (from ~6,600 fake profiles) making up the "FakeGit" campaign, with over 800 posing as AI Skills or MCP servers (for Gmail, WhatsApp, Databricks, Jenkins, Docker, etc.) to distribute SmartLoader via malicious ZIP files that trigger a LuaJIT loader chain, ultimately deploying the StealC infostealer. The campaign has racked up over 14 million downloads across ~200 repos and 600+ listings on registries like LobeHub, Glama, MCP.so, and MCP Market. The report also introduces "AgentBaiting," a technique where AI agents (Claude Code, Gemini, ChatGPT were shown to be susceptible) autonomously discover and surface these malicious repos while searching for skills/MCP servers on a user's behalf, without ever being given a link.

thehackernews.comarticleAdded 26 Sep 2026🛡️ Security

Cato AI Labs disclosed DuneSlide, two critical (CVSS 9.8) Cursor flaws — CVE-2026-50548 and CVE-2026-50549 — that let a zero-click prompt injection (via MCP servers or web search results read by the agent) escape Cursor's terminal sandbox and achieve arbitrary command execution. Both abuse the file-write allowlist logic: one via the run_terminal_cmd tool's working_directory parameter, the other via a symlink-resolution fallback that trusts an in-project path when the real-path check fails; both let an attacker overwrite Cursor's sandbox helper binary or startup files like ~/.zshrc to disable the sandbox entirely. Fixed in Cursor 3.0 (April 2), affecting all prior 2.x versions; the piece also situates this alongside earlier Cursor agent-exploitation chains (CurXecute/CVE-2025-54135, MCPoison/CVE-2025-54136, CVE-2026-26268).

thehackernews.comarticleAdded 26 Sep 2026🛡️ Security

CVE-2026-57860 describes an arbitrary code execution flaw in ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI that automatically loads and executes MCP servers defined in a repository's .mcp.json on startup without user confirmation. A malicious repo can define mcpServers entries with arbitrary command/args (e.g. bash -c) that spawn under the invoking user's privileges the moment forge is run inside the cloned repo, giving attackers a reliable initial-access and persistence primitive against developers evaluating untrusted code. CVSS 4.0 8.4 HIGH, CWE-829 (inclusion of functionality from untrusted control sphere); a fix commit and VulnCheck advisory are linked.

nvd.nist.govadvisoryAdded 26 Sep 2026🛡️ Security

Belgian CCB advisory on CVE-2026-48710 ("BadHost", CVSS 6.5), an authentication bypass in Starlette versions before 1.0.1. The Host header was not validated when request.url was rebuilt, so request.url.path could differ from the routed path. Middleware and endpoints that enforce access control on request.url could therefore be bypassed. The flaw affects FastAPI, LiteLLM, vLLM, MCP servers and other Python LLM infrastructure, and may expose stored third-party credentials. The advisory recommends upgrading to 1.0.1 or later and increasing monitoring, and links to the badhost.org scanner and to the GitHub, OSTIF, X41 D-Sec and Ars Technica write-ups.

ccb.belgium.beadvisoryAdded 26 Sep 2026🛡️ Security

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.

arxiv.orgpaperAdded 26 Sep 2026🛡️ Security

The first large-scale measurement study of authentication security across real-world remote MCP servers, scanning 7,973 live deployments and finding 40.55% expose tools with no authentication at all. For the 119 testable OAuth-enabled servers, the authors built a semi-automated (passive traffic inspection + active dynamic probing) detection framework and derived a taxonomy of nine flaw types across four categories — three MCP-specific (open client environments, dynamic client registration, delegated authorization) and conventional OAuth misconfigurations — finding every tested server had at least one flaw, with dynamic client registration flaws hitting 96.6% of servers and leading to information leakage or account takeover; the work resulted in 9 CVEs via responsible disclosure.

arxiv.orgpaperAdded 26 Sep 2026🛡️ Security

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.

arxiv.orgpaperAdded 26 Sep 2026🛡️ Security

AWS Security Blog's August 2026 ICYMI roundup covering 20 blog posts, 23 security bulletins, and 17 code samples. The dominant theme is securing agentic AI workloads on Amazon Bedrock AgentCore, alongside IAM/Cognito updates, S3 over-permission remediation, and a bulletin wave featuring prompt-injection consent bypasses in Strands Agents Tools, an IDOR exposing cross-tenant agent memory, credential-disclosure flaws in MCP servers, and RCE issues such as path-traversal-to-root in amazon-ssm-agent and Zip Slip in awsdac.

aws.amazon.comarticleAdded 7 Oct 2026, published 23 Sep 2026🛡️ Security

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.

arxiv.orgpaperAdded 2 Oct 2026, published 22 Sep 2026🛡️ Security

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.

arxiv.orgpaperAdded 22 Sep 2026, published 17 Sep 2026🛡️ Security

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.

github.comrepoAdded 26 Sep 2026, published 14 Sep 2026🧠 AI

Adversa AI argues that AI agent security lives in the harness, the loop, tool executors, context/memory management, approval gates and sandbox wrapped around an LLM, not in the model itself, and catalogs nine recurring harness failure classes. It details the firm's own research: SymJack (a symlink-based approval-prompt bypass that let six tested coding agents write attacker-controlled MCP config), GuardFall (shell-matcher bypass exploitable in 10 of 11 open-source agents tested), and TrustFall (MCP servers auto-executing on folder-trust acceptance in Claude Code, Gemini CLI, Cursor CLI and GitHub Copilot CLI), plus references to IDEsaster's 30+ AI-IDE vulnerabilities, a Hugging Face download-counter side channel (CVE-2026-54316), and Novee Security's Black Hat findings on credential leakage across Gemini CLI/Codex trust boundaries. It closes with concrete mitigations: Meta's Agents Rule of Two, allowlisting over blocklisting, treating agent config as executable code, and chain-of-event monitoring mapped to the OWASP Top 10 for Agentic Applications.

adversa.aiarticleAdded 7 Oct 2026, published 14 Sep 2026🛡️ Security

Plamen is an open-source Python orchestrator that drives 18-100 Claude Code or OpenAI Codex CLI agents across 40+ phases to autonomously audit smart contracts (EVM/Solidity, Solana/Anchor, Aptos Move, Sui Move, Soroban, DAML/Canton) and L1 node-client infrastructure (Go/Rust consensus, p2p, mempool code), producing a severity-tiered AUDIT_REPORT.md with verified proof-of-concept exploits for each finding. It integrates MCP servers for Slither, ChromaDB and Solodit, ingests vulnerability corpora from Solodit, DeFiHackLabs and Immunefi to ground findings, and runs a PTY-supervised worker-pool architecture with checkpoint/resume, artifact-based completion gating, and a dedicated L1 mode with consensus-invariant and network-surface depth agents.

github.comrepoPublished and added 7 Sep 2026🛡️ Security

Adversa.ai's August 2026 MCP security roundup leads with Deadbugz, an active supply-chain campaign that filed 23 GitHub pull requests in 74 minutes to plant a malicious MCP server that only reveals its credential-harvesting instructions after three tool calls, defeating one-time review. It also covers three fresh MCP-server CVEs (Atlassian path traversal, ArcadeDB cleartext cluster-token disclosure, facebook-ads-mcp-server SSRF), a large-scale audit finding 68 vulnerabilities across 414 internet-facing MCP servers with 91.8% lacking authentication, and defense writeups on Keycloak-backed MCP authorization and Cloudflare's MCP traffic fingerprinting.

adversa.aiarticleAdded 26 Sep 2026, published 7 Sep 2026🛡️ Security

Grafana patched CVE-2026-19516 (CVSS 9.1), a critical SSRF in the Grafana MCP server's grafana_api_request tool where a caller-supplied X-Grafana-URL header could control the method, path and body of outbound requests, letting an attacker reach internal-only services from the server's network position. Pillar Security researchers chained this with a second flaw — the MCP server accepting unauthenticated "session-shaped IDs" it never issued — and demonstrated using it to hit the AWS IMDSv2 endpoint and retrieve cloud credentials via a two-step PUT/TTL token request. Grafana MCP v1.1.0 adds optional bearer-token auth to close the session-forgery gap; Pillar frames MCP servers broadly as "identity brokers" that need explicit outbound destination policies and mandatory auth for remote deployments.

scworld.comadvisoryAdded 26 Sep 2026, published 3 Sep 2026🛡️ Security

Endor Labs breaks down how indirect prompt injection compromises AI coding agents (Cursor, GitHub Copilot) via poisoned READMEs/rules files, malicious MCP servers, and web/issue content the agent reads with elevated trust and auto-approve permissions. Cites a study testing 314 payloads across 70 MITRE ATT&CK techniques showing up to 84% attack success, OWASP's MCP tool poisoning definition, Unit 42's real-world IDPI telemetry, and CVE-2025-52573 as a concrete command-injection-via-prompt-injection case in an MCP server.

endorlabs.comarticleAdded 3 Sep 2026, published 2 Sep 2026🛡️ Security

JFrog vendor post arguing that agentic development (ADLC) introduces new unvetted supply chains — models, MCP servers, skills/plugins, hooks, and APM packages — that bypass traditional signature-based scanning. It cites real incidents: a malicious MCP server impersonating Postmark's email MCP that BCC'd all agent-sent emails to an attacker, and the 'omnicogg' malicious Claude/agent skill that hid a 22MB encoded payload and evaded all 65 VirusTotal engines for 5,000+ installs, plus references to 2026 supply-chain attacks on LiteLLM, TanStack, and Mistral AI. It then pitches JFrog AI Catalog's expanded MCP/skill/model registries as the fix.

jfrog.comarticleAdded 3 Sep 2026, published 2 Sep 2026🛡️ Security

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.

github.comrepoAdded 3 Sep 2026, published 31 Aug 2026🛡️ Security

LiteLLM is an open-source (MIT) AI gateway that puts 140+ LLM providers, agents and MCP servers behind one OpenAI-compatible API. It adds virtual keys, per-team budgets and rate limits, SSO/JWT/RBAC with SCIM, audit logs, leaked-key protection, and guardrails for PII masking and prompt injection (Presidio, Lakera). It self-hosts via Helm, Terraform or Docker, including air-gapped, with Cosign-signed non-root images, Grype and CodeQL scanning, and secrets pulled from Vault or cloud secret managers. A new Rust gateway is benchmarked at 0.66 ms p99 overhead.

litellm.aitoolAdded 3 Sep 2026, published 31 Aug 2026🛡️ Security

LiteLLM is an open-source (MIT) AI gateway that puts 140+ providers and 1,800+ models, plus agents and MCP servers, behind one OpenAI-compatible API with SSO and virtual keys. It adds per-key/team/org spend tracking, hard budgets, rate limits, guardrails, audit logs, load balancing, lowest-cost and auto routing, and response/semantic caching (Redis, S3, GCS). It self-hosts via Helm, Terraform or Docker, including air-gapped, and the page cites a new Rust gateway with 0.66 ms p99 overhead measured with the public AI Gateway Bench.

litellm.aitoolAdded 10 Oct 2026, published 31 Aug 2026🧠 AI

ADR (Agentic AI Detection and Response) is Uber's open-source enterprise security system for AI agents, covering discovery of unsanctioned AI tools on endpoints, telemetry capture of agent intent/tool-use/execution traces, a benchmark (ADR-Bench: 300+ tasks, 134 MCP servers, 17 agent attack techniques), and a dual-agent detector for risky agent behavior. It is deployed in production at Uber to secure employee-facing coding agents (Cursor, Claude Code, Codex, GitHub Copilot CLI, DeepSeek) and customer-facing support agents; the accompanying paper was accepted to MLSys 2026. The prevention component and offline red-teaming engine (ADR Explorer) are not included in the open-source release.

github.comrepoPublished and added 21 Aug 2026🛡️ Security

N4D Mesh Controller is a Linux malware campaign that abuses exposed MCP servers (tools/list, then tools/call on execute_command) and many other services. Datadog executed a UPX-packed, garble-obfuscated Go agent (33.8-go-titan) fetched from 209.99.186.235 in isolated microVMs and an offline replay lab. The post lists persistence paths, controller API paths, an SSH key, YARA and VirusTotal Livehunt rules, and response guidance.

securitylabs.datadoghq.comwriteupAdded 29 Oct 2026, published 20 Aug 2026🛡️ Security

Reporting on ASSET Research Group's GhostSplice disclosure, which shows a malicious MCP server can bypass single-shot prompt-injection refusals by splitting a data-exfiltration request across multiple channels (tool descriptions, tool results, server-initiated sampling) so no single message looks malicious, letting the coding agent stitch the fragments together and exfiltrate SSH keys, .env secrets, and source code. Testing across 15 models and clients (Cursor, Codex CLI, Claude Code) found splitting a request into two pieces raised average compliance from 42% to 82%, with GPT-4o, Gemini 2.0 Flash, and Llama 3.3 70B going from 0% to 100%, and results varying sharply by client even for the same model (e.g., Claude Haiku 4.5 at 0% in API tests but 100% in a three-piece Cursor test). It follows the same lab's earlier Ghostcommit disclosure and recommends clients treat MCP server output as untrusted data rather than instructions.

thehackernews.comarticlePublished and added 19 Aug 2026🛡️ Security

Socket founder Feross Aboukhadijeh's AI Council 2026 talk examines how coding agents that autonomously select dependencies, connect to MCP servers, install skills, and execute code with developer credentials are reshaping the software supply chain threat model. He walks through 2026 attacks against Axios, TanStack, and Trivy involving compromised maintainers, malicious transitive dependencies, and prompt injection, arguing existing security tooling assumes human trust decisions that no longer hold at machine speed.

socket.devtalkPublished and added 17 Aug 2026🛡️ Security

Endor Labs explainer arguing that an AI agent's "harness" (orchestration loop, tool calling/MCP, memory, sandboxes, permission guardrails) - not the underlying LLM - is what determines both capability and attack surface. It walks through concrete harness-level risks (prompt injection as OWASP's LLM01, MCP servers as unvetted dependencies, permission sprawl) and pitches deterministic lifecycle hooks (as used in Claude Code/Cursor via Endor's AURI) as a jailbreak-proof control layer, citing Endor's Agent Security League benchmark where Cursor+Fable 5 beat Claude Code and Codex on both functional and security correctness.

endorlabs.comarticleAdded 3 Sep 2026, published 15 Aug 2026🛡️ Security

AuditSentry is a GitHub project that pairs Claude Code with 13 specialized MCP servers and 23 parallel AI agents to audit Solidity and Vyper smart contracts, generating vulnerability findings, working exploit PoCs, mainnet-fork simulations, and CVSS-scored audit reports. It targets DeFi-specific bug classes (reentrancy, oracle manipulation, flash loan attacks, ERC-4626 inflation, cross-chain messaging replay, L2 sequencer issues, ERC-4337 account abstraction) and claims results benchmarked against 150+ historical Code4rena/Sherlock contest findings.

github.comrepoAdded 3 Sep 2026, published 10 Aug 2026🛡️ Security

HarnessRouter is a self-hostable (Docker) infrastructure layer that wraps existing agent harnesses such as Codex and Claude Code behind one OpenAI Responses-compatible API, letting a product run tasks, stream progress, manage files/artifacts, and switch harnesses without writing harness-specific integration code. It implements the Unified Harness Protocol (UHP), a versioned, OpenAI Responses-compatible contract with a reference implementation, schemas, and conformance suite, plus features like per-session workspaces, custom harness configuration with tools/skills/MCP servers, and secret redaction via vault references or header-scoped env vars so long-lived tokens never leak through agent output.

github.comrepoAdded 2 Oct 2026, published 9 Aug 2026🧠 AI

Wiz's H1 2026 cloud threat report documents a 60% jump in significant incidents driven by a doubling of supply-chain attacks (TeamPCP's npm/PyPI/GitHub Actions credential-harvesting spree, its open-sourced Shai-Hulud worm spawning Miasma/Hades/Megalodon/IronWorm follow-ons, North Korea's axios and @mastra trojanizations) and by growing attacks on AI infrastructure, including exposed unauthenticated MCP servers, LiteLLM/Dify/Langflow/n8n/Ollama vulnerabilities, and cryptominers deployed via a Langflow RCE. It also profiles JINX-0163, a cloud-native extortion group targeting non-human identities (service accounts/IAM roles) across AWS/Azure/GCP/Okta/Snowflake linked to the "FulcrumSec" extortion brand, and closes with concrete detection techniques for stolen access keys, Kubernetes VM Run Command abuse, GCP org-policy tampering, and CloudTrail user-agent/boto3 credential-provenance mismatches.

wiz.iowriteupAdded 3 Sep 2026, published 6 Aug 2026🛡️ Security

Cloudflare explains the MCP 2026-07-28 specification, which removes the mandatory stateful session handshake (Mcp-Session-Id) from the core protocol so MCP servers can run as ordinary stateless HTTP workloads (e.g. a single Cloudflare Worker) instead of requiring sticky sessions or Durable Objects. It covers the new Multi Round-Trip Requests (MRTR) model replacing stream-based elicitation, new Mcp-Method/Mcp-Name HTTP headers for gateway-level routing and caching, tightened authorization (CIMD preferred over DCR, RFC 9207 issuer checks, RFC 8707 audience binding), a formal Active/Deprecated/Removed feature lifecycle, and the createMcpHandler API graduating into the official TypeScript SDK, with testimonials from Sentry, Linear, and Anthropic's MCP lead.

blog.cloudflare.comarticleAdded 2 Oct 2026, published 6 Aug 2026🧠 AI