AI & Agent Tools MCP Servers

Self-hosted MCP server: pi-coding-agent tools (run_prompt, file ops) over streamable HTTP.

Full-text search, browse, and resume across your coding agent sessions (Claude Code, Codex, Amp)

Self-hosted MCP server exposing Claude Code as an agentic AI tool over streamable HTTP.

Self-hosted MCP server: run OpenAI Codex CLI prompts and manage workspace files.

Local-first MCP server for task tracking and coordination of autonomous AI coding agents.

Deterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.

MCP server enabling AI clients to interact with any MediaWiki wiki through standard tools

MCP stdio server for Attestify OS — governed agent execution with on-chain receipts.

Non-custodial cross-chain OTC for AI agents: sealed RFQ, negotiation, HTLC atomic swaps. Testnet.

MCP Server that turns your AI agent into a localization expert with token-efficient i18n translation

Read-only IBM MQ diagnostics for AI agents. Cited root cause, never destructive.

Read-only context and complete checks against patterns learned from git history. Local; no LLM.

Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.

Brazilian company registry (CNPJ), sanctions, funds & market data for AI agents, paid via x402.

Give your coding agent the dependency graph it is about to change: scan, diff, explain, audit

Manage Authentik through AI assistants

Manage Komodo through AI assistants

Manage Proxmox VE through AI assistants

Manage AdGuard Home through AI assistants

Protect your AI agents and IDEs from malicious open-source packages.

Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.

Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.

Local-first, contract-governed data explorer with read-only, PII-masked query tools for AI agents.

Screen AI-work venues for inventory, funding, payouts, withdrawal, economics, and security risk.