AI & LLM Tools MCP servers

Coding agent with basic tools for listing, reading, editing and writing files, running commands and web search, supporting multiple projects at once.

Self-hosted MCP gateway fronting upstream servers with per-tool access control, guardrails, rate limits and usage logs; also proxies LLM and A2A agent traffic.

an MCP server for Claude Code conversation history

Bridge to multiple OpenAI-compatible LLMs for rubber duck debugging: explain a problem to several AI ducks and get different perspectives.

Command-line execution with customizable security policies.

AI image generation and editing with prompt optimization and quality presets

Integrate real-time Scrapeless Google SERP(Google Search, Google Flight, Google Map, Google Jobs....) results into your LLM applications. This server enables dynamic context retrieval for AI workflows, chatbots, and research tools.

Chat with any other OpenAI SDK Compatible Chat Completions API, like Perplexity, Groq, xAI and more

Remote MCP Server that securely connects Glean Enterprise Knowledge with your IDE, LLM, or agents.

AI orchestration: Claude Code, Codex, Gemini on shared repos. 11 MCP tools, stdio (stage: internal)

LLM-driven context and memory management: short- and long-term memory with vector, timeline and knowledge graph retrieval plus reranking.

Access LeetCode problems, solutions, submissions and public data, with optional login for user features such as notes; supports the global and China sites.

MCP server for Apple Notes - read, search, create, edit, organize, and export notes on macOS via Claude and other AI assistants

Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer

AI council: query CLI agents (Claude Code, Codex, Gemini and OpenCode) in parallel with deliberation rounds.

Turn any website or API into structured JSON with LLM-authored declarative scraping configs.

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

MCP server for MindBase — query and write to your wiki from Claude Desktop, Cursor, Windsurf, Cline, or any MCP-compatible AI client.

Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents

Meta-MCP server that unifies AI coding assistants (Codex, Claude Code, Cursor, Gemini) behind one interface with automatic discovery and zero configuration.

Control plane for long-running Codex Desktop tasks: submit asynchronously, poll state, approve Plan Mode, recover retries and search SQLite-backed history.

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

Automatic project memory for Claude Code. Also works with Cursor and Codex.

A Go implementation of a Model Context Protocol (MCP) server for Trino, enabling LLM models to query distributed SQL databases through standardized tools.

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

Query Langfuse traces, debug exceptions, analyze sessions and manage prompts for LLM applications.

MCP server for the OpenAffiliate registry. Search affiliate programs from Claude, Cursor, or any MCP client.

Deep research via the OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.

Capture website screenshots, tiling full pages into 1072x1072 chunks for Claude Vision, with configurable viewports and wait strategies for dynamic content.

Self-hosted mem0 for Claude Code: Qdrant vector search, Neo4j knowledge graph, Ollama embeddings and session hooks for automatic cross-session memory.

Run shell commands securely, auditably and on demand in isolated environments such as Docker.

Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.

Improve agent reasoning with the think tool described by Anthropic.

Browser automation where an LLM plans and Jev (Typesafe System One) makes every per-step decision. Library, CLI and MCP server.

MCP server for delegating tasks to specialized AI assistants in Cursor, Claude Code, Codex, Command Code, Google Antigravity, Gemini, GLM, Kimi, Grok, and OpenCode

Persistent memory + git snapshots for Claude Code. Never lose context or code.

Subscription-aware LLM router for Claude Code: routes tasks to providers like OpenAI, Gemini, Groq and Ollama by complexity, subscription usage and cost.

Expose OpenAI's built-in web search tool.

Learning engine for Claude Code: extracts signals from sessions, runs periodic reflections and promotes or retires behavioral frameworks based on evidence.

Convert source code into an AST, regardless of language.

Query multiple Ollama models and combine their responses for diverse perspectives on a single question.

Use Claude with local workspace access from Telegram on your phone: read, write and code on the go.

Structured, model-driven interaction with network devices via Cisco pyATS.

Control the Unitree Go2 robot with natural language commands interpreted by an LLM.

Investment runtime for AI agents — LLM investment committee, portfolio ledger, decision accounting

Build iOS Xcode workspaces or projects and feed errors back to the LLM.

Query OpenAI models directly from Claude using MCP protocol