Security

A Python SDK for MCP tool integration with LLM providers

Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.

Security scanner for Model Context Protocol (MCP) servers

JWE authentication middleware for MCP/Starlette applications

Conformance scanner for MCP server authorization (OAuth 2.1, RFC 9728, RFC 8414, RFC 8707). Logs in, scans a live server, grades it, fails CI.

Intuitive authorization middleware for MCP tools with type-safe policies

OAuth 2.0 Authorization Server framework for MCP (Model Context Protocol) servers

Actively test whether an MCP server you own validates bearer-token audience (aud), issuer (iss) and expiry (exp).

Privacy-first security scanner for MCP server configurations

Scan, enumerate, and risk-score every MCP server configured on your machine.

Automated security scanner and grading CLI for MCP servers.

Open-source security CLI and runtime for MCP-style agent tool calls: deny-by-default policy, adaptive campaign watch, hash-chained receipts.

A comprehensive MCP configuration scanner with client-aware security analysis.

MCP server for autonomous API logic penetration testing — OWASP API Top 10 / BOLA-IDOR detection via LLM-driven analysis

Protocol- & auth-agnostic API connector: SOAP/REST behind any auth, config-driven. Lib/API/MCP.

Security scanner for MCP (Model Context Protocol) server configurations and AI agent tool permissions.

Static preflight scanner for MCP servers and agent skills

AgentLock authorization middleware for MCP (Model Context Protocol) servers.

Adversarial input harness for MCP servers. Replay injection / oversize / traversal fixtures against any MCP server and assert it stays sane.

A Matrix MCP server for connecting coding agents to Matrix and MindRoom conversations.