#model-context-protocol

PubNub MCP Model Context Protocol Server for use in Cursor, Windsurf, Claude Desktop, Claude Code and OpenAI Codex and more!

Model Context Protocol for Actual Budget API

Local credential control for AI coding agents.

A Vitest reporter that keeps results of test runs focused for LLMs

No repository description published.

Run Claude Code, Codex, Copilot, Gemini, OpenCode and Amp side by side in isolated Git worktrees, with shared issue ownership, reservations and explicit handoffs.

Public protocol source of truth for AgenC: Anchor program, zkVM guest, migrations, and generated protocol artifacts

Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.

Search history local agents for prompts and conversations (Codex, Claude, Cursor, agy, grok, pi, opencode)

Send and receive webhooks with retries, ordering and replay. Self-hosted, MIT.

Identity, memory & collaboration platform for AI agents — facts, memories, secrets, and inter-agent messaging via a CLI, MCP, and a Go server.

One .NET command graph. CLI, REPL, remote sessions, MCP.

An MCP client library for building conversational AI applications with enhanced control and dynamic tool discovery for context-efficient agents.

Seedance by Ace Data Cloud: text-to-video, image-to-video and task results via MCP.

Tooling for AI coding agents. Vercel AI SDK adapters, sandbox providers, skill and MCP managers, ACP-protocol utilities.

Undetectable browser automation for AI agents via MCP. Stealth Chrome DevTools with smart profile management, anti-detection arg filtering, and CDP access.

Anti-hallucination AI agent kit for Cursor, Windsurf & Antigravity. 27 specialist agents, 17 slash commands, 8 Tribunal reviewers. Install: npx tribunal-kit init

The live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via MCP.

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

MCP server with reviewed OilPriceAPI facts, keyless diagnostics, source-timestamped data, and read-only defaults

Typed, reproducible high-content microscopy workflows across GUI, Python, CellProfiler, Napari/Fiji, GPU, and local MCP agents.

a11y-computer-use: accessibility-first computer use for AI agents. Pruned a11y-tree snapshots, element refs instead of pixel coordinates, a safety layer, an MCP server and CLI. macOS, Windows, Linux, and Chromium over CDP.

MCP server for using the REMnux malware analysis toolkit via AI assistants

MCP stdio bridge for AI clients that only speak stdio — query financial statements, explore graph structures, resolve XBRL elements, and build fact grids over RoboSystems. In maintenance mode: every graph now serves a hosted remote MCP endpoint needing no install, and this package proxies to it by default.

Python SDK for astrology, Vedic kundli, BaZi four pillars, feng shui, tarot, numerology, horoscope, I Ching, biorhythm and more. One multi domain API key, sync and async. AI agent and MCP ready.

A Rust CLI and MCP server for X.509 certificate analysis, format conversion, and key verification. Reads certificates from PEM files or HTTPS endpoints. Validates TLS connections, checks revocation status, converts between PFX and PEM formats and integrates with AI-powered IDEs via the Model Context Protocol (MCP) and Vault.

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

Trusty Squire signs up / in to websites for you so you don’t have to.

No repository description published.

Pre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.