AI & Agents MCP Servers

Deployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.

Delegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.

A MCP server for interactive user questions with native UI

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

Verification and memory layer for coding-agent workflows.

Offline spell checker + BYOK grammar for AI assistants. Works with Claude Desktop, ChatGPT, Cursor.

MCP server for LightningProx — pay for AI inference with Bitcoin Lightning. No API keys. Pay per request in sats. 19 models across 5

Three-layer firewall for MCP: content, egress and action policy. Proxy or server.

Python SDK + MCP server for NexusToken — an agent-to-agent capability network

Pre-execution governance for AI agents. Validates tool calls before they execute.

Verification infrastructure for the agentic economy: submit a claim, get an Ed25519-signed verdict resolved against real external ground

Agent coordination MCP server and Claude Code plugin — shared blackboard, decision tracking, and context assembly

Claude Code plugin — 51 tools for video analysis, deep research, content extraction, media production, and explainer video creation

P2P runtime for A2A protocol. Encrypted agent communication with zero-config NAT traversal.

Governed MCP server: YAML-declared tools, typed effects, policy-gated and audited calls.

Windows control server for the Model Context Protocol

Universal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter

MCP server bridge for LiteLLM

Mirror MCP: Introspection for LLMs

Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.

Decision system for software built with AI