Search

Capability auditor for AI agents. Scans tool definitions from LangChain, OpenAI, MCP and more — detects dangerous capability combinations before they reach production.

PyRASP is a Runtime Application Self Protection package for Python-based Web Servers (Flask, FastAPI and Django), Serverless Functions (AWS Lambda, Azure and Google Cloud Functions) and MCP Servers (FastMCP)

Local encrypted execution base for multi-agent, cross-node, privacy-preserving task execution.

Static preflight scanner for MCP servers and agent skills

Open-source database, API access & deployment governance platform A SQL, NoSQL, and API proxy that puts review, approval, and audit between your team and production data and services.

Free, in-process scanner for MCP (Model Context Protocol) servers — detects tool poisoning, typosquats, hidden unicode, base64 payloads, and exposed transports. Same regex / scoring engine that ships with the VyriAI control plane.

MCP server for AgentScore — trust scoring for AI agents. Check agent reputation before transacting. No API key, zero config.

Prebuilt vex-mcp binary for win32-x64.

MCP middleware for Signet cryptographic action receipts

Aggregate multiple Model Context Protocol (MCP) servers into a single unified interface with a powerful monitoring UI. Prov deep visibility into every request and response.

MCP server for Workforce AI — policy management, asset visibility, and apps catalog via LLM tool calls

MCP server for ShieldPi Watchtower — query 27,000+ LLM attack techniques, run scans, fetch breach forensics from any MCP-compatible client (Claude Desktop, Claude Code, Cursor).

[](https://glama.ai/mcp/servers/swnotmetal/Project-Koma) 🎖️ 📇 🏠 🍎 🪟 🐧 - MCP server exposing Koma Gate's LLM-based classification of prompt injection and out-of-scope input through the `classify_input` tool.

AgentGuard — runtime governance for production AI agents. APRA CPS 230, EU AI Act and ISO 42001 evidence built-in. Native OpenClaw, LangChain, CrewAI, OpenAI Assistants, AutoGen, and MCP integrations.

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

Scan MCP servers before installing them

C2 server fingerprinter — Cobalt Strike, Sliver, Mythic, Havoc, Brute Ratel

A Roslyn analyzer that catches prompt-injection and tool-poisoning in C# Model Context Protocol (MCP) server tool descriptions at build time. MCPGxxx diagnostics, code fixes, and a CI gate.

Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate all HTTP requests and responses between your IDE and MCP servers

Eko multi-agent connector for BonkLM — validates planner output + BrowserAgent + FileAgent + MCP-tool dispatch.