tool-poisoning

Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。

Offensive MCP server auditor: detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.

Multi-engine security scanner for AI agents, MCP servers & plugins — 13 engines, one report.

Open-source security firewall for MCP servers. Scan for OWASP MCP Top 10 vulnerabilities, enforce runtime policies on AI agent tool calls, and generate compliance audit logs.

Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shadowing defense, and NIST AI RMF + OWASP LLM Top-10 audit trails for any MCP server. Works with Claude, Cursor, Cline, Windsurf.

55-tool MCP server for security scanning of MCP servers. Runtime inspection, AST-based SAST, config audit, dependency analysis, OWASP MCP Top 10 compliance. OAuth, TLS, fuzz testing, prompt injection, tool mutation detection. 100% local, zero external API calls.

Security scanner for MCP servers. Detects tool poisoning, prompt injection hidden in tool descriptions, leaked API keys, and supply-chain risk across Claude, Cursor, VS Code, Windsurf and Zed configs. One command, no API key.

Zero-trust governance middleware for Model Context Protocol deployments

MCPCustoms is the customs checkpoint for MCP tool calls: a zero-dependency TypeScript runtime semantic firewall that inspects every Massive Intelligence (IM) agent tool call before execution. Detects tool poisoning, command/SQL/prompt injection, path traversal, and capability overreach; verifies signed Ed25519 publishers; fail-closed by default.

Security scanner for MCP servers — flags tool poisoning, prompt injection, tool drift, over-broad scope, and context-cost runaway across 12 checks. Run as npx toolfence <url>, CI-ready exit codes.

Security scanner for MCP server configurations. Detects tool poisoning, prompt injection, shadowing attacks, and known threats.

Ed25519-signed tool manifests for MCP. Stop tool-poisoning and rug-pull attacks with cryptographic verification.

Local static scanner for MCP setup, config, prompts, and workflow trust.

Scan any MCP server for prompt injection, tool poisoning, and leaked secrets. One command, no key. SARIF + GitHub Action.

Security scanner for AI agent tools — detect tool poisoning, data exfiltration, and supply chain attacks in MCP servers and agent skills

Pins the hash of every approved MCP tool definition and blocks the instant one drifts - catching rug-pull attacks. Free, local, zero-infra.

Scan and identify security issues in MCP servers to help strengthen defenses against potential attacks on AI agent connections.

Local-first firewall and black-box run reporter for MCP tool calls: block poisoned tools, detect drift, rate-limit agents, and audit runs.

Runtime + semantic trust registry for MCP servers - catches tool poisoning and scope creep, $0 infra (local LLM via Ollama)

Static security scanner for MCP servers: tool poisoning, prompt injection, secrets, command injection. CLI + GitHub Action, SARIF output.