#mcp

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.

Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon

Lightweight file-based CLI API client with age-encrypted secrets and first-class GraphQL support built for humans and AI agents

Like Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.

Full Portkey Admin API MCP server

Spec-driven development framework — AI agents that think before they type

ThumbGate Pre-Action Checks derive rules from repeated failures, flag risky tool calls, hard-block detected secret leaks, and block matches in strict mode.

Donmai is an open-source workflow runtime that runs, retries, and audits multi-step agent tasks on your machine. The same binary powers Rensei in production. MIT-licensed.

TypeScript SDK for astrology, Vedic kundli, tarot, numerology, horoscope, I Ching, biorhythm and more. One multi domain API key, fully typed. AI agent and MCP ready.

Build distribution MCPs: multi-step conversational funnels (lead gen, booking, quotes) that run as a single MCP tool in ChatGPT, Claude, and Cursor. A typed state graph compiles to one MCP tool.

Talk to your self-hosted Actual Budget from any MCP client: a remote HTTP server for LibreChat/LobeChat or a local stdio process for Claude Desktop, with 71 tools for transactions, budgets, rules, and bank sync. No Docker needed for local use.

Standalone MCP server for Obsidian vaults — hybrid search, structured memory, tasks, and full vault access for any AI agent

A memory of the codebase your AI agent can't get from grep: a persistent call graph, semantic search, and per-symbol review learnings over any repo. Self-hosted MCP server — Go, tree-sitter, Apache AGE.

MCP server for Atlassian Confluence — search, read, create and update pages via Claude / Windsurf / any MCP-compatible AI client. Supports Cloud and on-premise (Server/Data Center).

Active security scanner for A2A and MCP servers

Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.

Open-source AI governance gateway for EU teams: enforce PII, cost, model, data residency, and tool policies for LLMs and AI agents with signed evidence.

Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.

Add Angie Chat Anywhere

Receipt Required for AI agents — no receipt, no irreversible action. An open, offline-verifiable authorization-receipt protocol: a named human signs the exact high-risk action (payment, deploy, delete, permissions) before it runs, and anyone can verify it later, trusting no one. Apache-2.0 · formally verified · IETF Internet-Drafts.

The semantic system of record for AI-written software: a graph of entities and relations, not file diffs.

MCP package manager with built-in trust scoring. Search, install, and audit MCP servers across Claude Desktop, Cursor, VS Code, and Windsurf.

Start a run in your terminal and walk away. Get pinged when it finishes, or needs you. Every step is a readable trace you check before anything ships.

Self-hostable AI agents you can actually leave running — durable crash-resume, governed autonomy, seccomp sandbox, offline-replayable workflows, CI-native eval. Async-Python, YAML-config, multi-provider (OpenAI/Anthropic/Cloudflare), MIT.

A compiler and runtime for multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok Build — verify before model spend, isolate context, resume, replay, and recompute.

an MCP server that interacts with SAP via the Desktop and/or Web GUI

No repository description published.

Persistent semantic memory for AI agents — 100% local on Apple Silicon (MLX) or Linux/Ubuntu (CPU). Markdown source of truth, sqlite-vec + BM25 hybrid search, a codegraph-backed knowledge graph, MCP server + CLI. No cloud, no keys.

m0lz.03 — Security proxy daemon for MCP servers. Auth, rate limiting, PII detection, permissions, audit logging.

Maya-specific implementation of Model Context Protocol (MCP) for Autodesk Maya, enabling remote control and integration with MCP ecosystem.