"claude" matching MCP servers:

Self-improving learning engine for Claude Code. Extracts signals from sessions (corrections, successes,confusion), runs periodic reflections, and evolves behavioral frameworks through evidence. 9 MCP tools, automatichooks, local-only.

An MCP server that provides Claude with adjustable 0-10 sliders for behavior dimensions like rigor, verification, and autonomy, allowing external tuning without modifying prompts.

A Model Context Protocol (MCP) server that connects Claude to local Ollama models, enabling offloading of simpler tasks to save Claude tokens.

Persistent memory and session intelligence for AI coding assistants. Auto-tracks mistakes, decisions, and context via hooks. Mines your full session history for patterns, predictions, and cross-session search.

MCP server that enables calling Anthropic Claude models from OpenAI Codex Desktop/GUI, supporting API key or OAuth authentication and providing chat, model listing, and diagnostic tools.

Enables persistent cross-session memory, correction-pattern tracking, and self-evolving behavioral frameworks, so past facts and decisions stay searchable by meaning and recurring mistakes fade over time. Runs entirely locally through 15 MCP tools plus hooks, with optional semantic search via Ollama embeddings and no cloud or API key required.

Enables Claude Code to retain cross-session memory of facts, decisions, and lessons with semantic search, while tracking user corrections as behavioral patterns and evolving self-improving frameworks over time. All processing runs locally through an MCP server and hooks, requiring no cloud service or API key.

Gives Claude Code persistent cross-session memory with semantic search, automatically detecting and classifying user corrections to track behavioral patterns over time. It also extracts signals from each session to evolve, promote, or retire behavioral frameworks, letting the assistant develop judgment that improves across sessions.

Gives Claude Code persistent memory across sessions, detecting and classifying user corrections, and evolving behavioral frameworks from accumulated evidence. Exposes 15 MCP tools for semantic memory search, signal recording, self-evaluation, and reflection cycles that run locally alongside automatic hooks.

Local MCP servers that give Claude Code access to other tools mid-session.

Enables users to create notebooks, upload documents and court rulings, query their contents, and generate audio, video, presentation, or flashcard outputs.

A lightweight MCP server that gives Claude Code Channels on Telegram persistent memory by storing facts, conversation logs, and session summaries in Supabase.

An MCP server that enables Claude Code to generate context-aware images using local GPU-powered diffusion models, either automatically during coding or on-demand via slash commands.

An MCP server that gives Claude Desktop persistent memory, self-awareness, epistemic hygiene, and genuine agency across conversations with a typed memory system, embedding-based semantic search, a 3-judge memory jury, and a real-time dashboard.

Enables retrieving real Claude subscription usage statistics, including the 5-hour session window, weekly limit, and per-model limits, from the same endpoint Claude Code uses.

Enables OpenAI Codex to consult Claude Code for co-analysis, adversarial second opinions, and read-only file review over the Model Context Protocol, with Claude remaining advisory and unable to modify files.

Allows Claude Code to request an independent code review from Google Antigravity (Gemini, Claude, or GPT-OSS) via the Antigravity CLI, providing a second opinion on plans or diffs.

Enables users to strip statistical AI text watermarks by rewriting wording while preserving meaning, structure and formatting, running locally with the user's own OpenRouter key including free models. Works in Claude Desktop, Claude Code, Codex, Cursor and any other MCP client, returning the rewritten text with a novelty percentage.

Provides free, unlimited access to Claude AI models via Puter.js for AI coding agents and IDEs through the MCP protocol.

Enables Claude Code to offload bulk tasks to cheap OpenRouter worker models via tiered model selection, parallel batch execution, daily budget caps, and cost logging.