Discover MCP Servers

@templates

Mandatory human approval gate for autonomous AI agents. Intercepts critical, irreversible, or financially significant actions and routes them to a human via Telegram for real-time approve/reject. Raises workflow success probability from 81.5% to 99.6%.

@featured

MCP security trust layer. Continuously monitors 800+ MCP packages on npm for install scripts, command injection, hardcoded secrets, capability drift, and publisher posture. Ships a GitHub Action policy gate for PR-level allow/warn/block decisions with OIDC auto-provisioning. 5 MCP tools, no API key required.

@featured

Third-party certifying proxy — sign any HTTP call (AI agents, webhooks, microservices) with an independent Ed25519 signature, RFC 3161 timestamp, and Sigstore Rekor anchor. Works with Claude, GPT-4, Mistral, LangChain, AutoGen, or any HTTP client.

@featured

Query the AgentForge Trust Score (0-100 across five dimensions: security, code health, behavioral audit, community trust, EU compliance) for any MCP server before connecting. Exposes `check_trust`, `evaluate_policy`, `list_trusted`, and `recommend` tools. 3,600+ servers audited, free public API.

@featured

Cryptographic provenance, bilateral blind reputation scoring, and tamper-evident logging for AI agent interactions. 7 interlocking trust protocols (CoC, ARP, ASA, AJP, ALP, AMP, CWEP) available in Python (pip) and TypeScript (npm). 663 tests. Bitcoin-anchored provenance chains, anti-Goodhart reputation scoring, machine-readable contracts, dispute resolution, lifecycle management, trust-weighted matchmaking, and context-window cost allocation. Also on [Smithery](https://smithery.ai/server/@alexfl

@templates

[Mobb Vibe Shield](https://vibe.mobb.ai/) identifies and remediates vulnerabilities in both human and AI-written code, ensuring your applications remain secure without slowing development.