MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Smart-Thinking is a Model Context Protocol (MCP) server that delivers graph-based, multi-step reasoning without relying on external AI APIs. Everything happens locally: similarity search, heuristic-ba
Hosted by authorMIT★ 33No key
A structured, persistent reasoning workspace for AI. 20 tools for thought chains, branching, revision, search, and session persistence across context resets.
Node.jsMIT★ 3Few starsNo key
cotlib is a secure, high-performance Go library for parsing, validating, and generating Cursor-on-Target (CoT) XML messages. It features a comprehensive, embedded type catalog with metadata and XSD ca
GoMIT★ 13No key
Simple RAG implementation from scratch using MCP, focusing on Perception, Memory, Decision and Action
SkillApache-2.0★ 16No key
Does blocking GPTBot remove you from ChatGPT? No — OAI-SearchBot is the token that does. Free robots.txt AI-crawler checker (CLI + MCP server) and open data on 165 AI crawlers: which cost you AI answe
DockerMITFew starsNo key
CLI, MCP server, and API-compatible interface for Perplexity AI
PythonMIT★ 20No key
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
Node.jsMIT★ 645No key
Hybrid search for Obsidian vaults via plugin, CLI, and MCP server
Node.jsMIT★ 111No key
An MCP server that provides web search capabilities powered by DeepSeek API, designed for AI assistants and agents.
Node.jsMIT★ 33No key
Free Perplexity AI MCP server with multi-account pooling, React admin dashboard, zero-cost health monitoring, and Telegram alerts. No API keys needed.
PythonMIT★ 13No key
support cc/codex/grok build/kimicode/pi/antigravity cli/opencode sessions viewer, skills manage, token usage statistics, global search, resume, and export to html
SkillMIT★ 399No key
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
PythonAGPL-3.0★ 381No key
Free SEO Audit MCP server for Claude - captures and stores all the raw data you need for a complete technical SEO audit. Google Search Console + a first-party crawl + DataForSEO + Majestic SEO merged
Node.jsApache-2.0★ 57No key
Python terminal AI agent CLI with ReAct tools, MCP, Runtime API, memory, snapshots, web search, and image input
PythonMIT★ 107No key
A TypeScript-based MCP server implementing a memory system inspired by neurodivergent cognitive styles. It organizes thoughts into five districts (knowledge domains), ranks search results using BM25 s
Node.jsMIT★ 22No key
Structural RAG (Retrieval-Augmented Generation) system for large codebases
SkillMIT★ 19No key
Agentic RAG for any scenario. Customize sources, depth, and width
SkillApache-2.0★ 290No key
Find AI/LLM security vulnerabilities in your code before attackers do — covers prompt injection, MCP tool poisoning, RAG data poisoning, and more
Node.jsMIT★ 23No key
Secure AI Memory with Dynamic Project Detection, Automatic Session Briefing, Personal+Team Session Summary Prompts, Triple Search, Knowledge Graphs, GitHub Integration (Issues, PRs, Actions, Kanban, M
Hosted by authorMIT★ 20No key
Enhanced fork of claude-context with stability fixes, improved sync, and better reliability for semantic code search
SkillMIT★ 4Few starsNo key
Build a second brain every AI can share: your content in Oracle AI Database 26ai — semantic search with in-database embeddings, a self-compiling wiki, four kinds of agent memory, and an MCP server tha
SkillMIT★ 13No key
Ultimate Gemini 3.1 Flash Image MCP server with 4K generation, Google Search grounding, reference images (up to 14), and thinking mode. Professional image generation made simple.
MCPLink only★ 14
Local-first second brain with semantic search. Stores notes as Markdown files and indexes them with a local ML model — no cloud, no API keys.
Node.jsMIT★ 3Few starsNo key
Self-hosted knowledge service for AI agents: an LLM-maintained wiki and a business graph, searched in milliseconds, far faster than RAG, with no LLM or database on the read path. HTTP and MCP.
SkillApache-2.0★ 4Few starsNo key
Who stands behind it
