Web scraping, code review, content gen, sentiment. Zero Core Tools.
Typed caller-owned Discord operations for AI agents, with safety controls, resilience, and verifiable guild builds.
MCP tool adapter for Beignet agent capabilities
Azure DevOps MCP server: projects, repos, work items, pull requests, pipelines, and wikis.
Model Context Protocol implementation for TypeScript - Client package
AI agents runtime and meta-harness: routes each query to a cost-optimal model (LLM routing), evolves its own harness and orchestrates coding agents over MCP.
PostHog SDK for Model Context Protocol (MCP) servers — tracks tool usage, intent, and identity
Full-featured, lightweight MCP extension for the Pi coding agent: stdio, SSE & Streamable HTTP transports, OAuth 2.1 (PKCE + DCR), lazy/eager lifecycles — minimal dependencies, zero bloat.
Pre-launch security check for AI-built apps: leaked keys, open Supabase rules, unprotected routes, unsafe LLM code. Runs locally.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Turn Microsoft Fabric tables into an explainable graph and a GraphQL API.
Prepare project-specific coding-agent workflows and install them with protected updates
Vocnu from your terminal and your AI assistant: AI voice-over and subtitles for your videos (CLI and MCP server).
Turn documents, transcripts and notes into Agent Skills. Runs the catch-the-gist Python package through uvx.
Curated MCP tools from OpenAPI, websites, apps, Postman, cURL or SQL; your agent designs them.
TypeScript framework for building MCP servers: tools, resources and prompts as decorated classes, with transports, sessions, auth and dependency injection
Always-fresh local repo graph: LSP-backed impact, Health, dead code, endpoints, architecture.
Transactional refactoring extension with 11 evidence-backed tools, previews, and rollback.
Transactional refactoring MCP with 11 evidence-backed tools, hash-bound previews, and rollback.
Instagram, WhatsApp and Messenger DMs through official Meta Business APIs.
AlphaKey IDaaS MCP Server — Manage SSO, MFA, users, apps, and security policies through AI IDE
Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.
Expose an OpenAPI document to agents as a search-first tool catalog over your existing API.
Humanagent documentation bridge — deterministic handoffs, doc-site links, memory→docs, optional AgentsKit RAG/chat.
Context window saver for 11 coding agents. Local and free: sandboxed code execution, FTS5 search, session continuity.
MCP filesystem server with bounded tool results and paged reads, forked from @modelcontextprotocol/server-filesystem
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
CLI and MCP server for your own X account: posts, threads, media, DMs, bookmarks, lists, analytics, plus an explicit opt-in unofficial transport.
Drive your real, logged-in Chrome from the shell or an AI agent: a Chrome extension plus a local CLI/daemon, no debug port.
Calibrated advice for coding agents: typed questions in, probabilities out. Apple Silicon.
GitHub repo search, stats, language breakdown and comparison as agent tools.
Persistent, read-only codebase memory for Claude Code; ask it instead of re-reading files.
Local, stateful twins of any API (Stripe, Twilio, any OpenAPI spec) for agents. No keys, no bill.
Design system for coding agents: component specs, rules, tokens, icons and checked React snippets.
Read public GitHub Projects v2 boards without auth — items, fields, story points, priority.
See each coding-agent subscription's live limits and offload work to one with headroom.
Directorio completo
IDEs, git, linting y análisis de código. 8,723 servidores, los más usados primero. Cada uno abre la página del publicador.