"An official Figma MCP server" matching MCP servers:

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Design contract layer for AI agents. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth so every agent gets the same authoritative design rules before it builds. Local-first.

Provides a compressed knowledge graph of the NVIDIA AI developer stack for deterministic traversal, enabling agents to answer questions about dependencies and prerequisites with minimal tokens.

Enables personal knowledge management through Claude Desktop, allowing users to capture thoughts, connect ideas, and reflect on thinking changes via natural conversation.

A personal digital twin MCP server that manages professional context, including skills, experience, and project learnings. It allows AI assistants to retrieve and update user preferences and career interests across different development environments.

Local MCP server that automates an open Obsidian vault through Obsidian's official CLI, offering tools for note creation/update, search, tasks, daily notes, and organization. It uses MCP over STDIO, requires no cloud services, and provides safety/audit features for autonomous writes.

An MCP server for managing work logs, research results, and task checkpoints to enable seamless collaboration and state recovery between AI agents. It provides a persistent memory layer for tracking project history and resuming workflows across different sessions or tools.

Turn any data source into an MCP server in 5 minutes. Build knowledge bases that AI assistants like Claude and Cursor can query directly.

An enhanced fork of the official MCP memory server that enables persistent knowledge graph storage with automatic timestamps, tags, importance levels, date range search, comprehensive statistics, and multi-format export (JSON, CSV, GraphML).

AI development assistant with 36 specialized tools for memory management, code analysis, project planning, and problem-solving through natural language interactions in Korean and English.

Enables AI agents to persist, search, and evolve knowledge through a Markdown vault with a typed knowledge graph and MCP interface.

An open-source bitemporal knowledge graph that provides long-term memory for AI agents via a native MCP endpoint, enabling conflict-aware ingest and hybrid retrieval.

Persistent semantic memory-as-a-service for legal AI agents. Store and recall case notes, client context, and matter history via MCP. Namespace-isolated, audit-logged, and GDPR-compliant.

Enables AI assistants to turn conversations into a searchable personal wiki, read and organize pages, and propose edits such as merges, translations, and fact-checks as reviewable changesets.

Enables AI assistants to search, create, and manage knowledge graphs in Aiqbee brains for architecture, portfolio, and digital strategy.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

Provides LLM clients with persistent memory tools for searching, reading, creating, and updating notes, retrieving backlinks, listing recent notes, and managing tasks using self-hosted MySQL storage.

A Git-backed MCP relay that lets multiple AI assistants share one local Markdown notes vault, recording which app, model and reasoning setting made each edit. It versions every change in Git and holds suspicious prompt-injection attempts or large deletions in a quarantine for human review.

Open-source AI memory layer for LLM agents. Importance scoring, temporal decay, hierarchical memory (facts, summaries, themes), YMYL prioritization, and active retrieval with contradiction detection. Supports OpenAI, Anthropic, Ollama. Local-first with SQLite + FAISS.

An MCP server that tracks AI prompts in Claude Code and automatically annotates git commits with the history of what was asked. It provides tools to query session summaries, retrieve uncommitted work, and manage AI provenance directly within Claude.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.

Enables MCP clients such as Claude Desktop, Claude Code and Cursor to hand tasks and questions to a self-hosted agent that answers using its own local model, memory, document library and tools. It also lets those clients search long-term memory, save facts, and search, list or add documents, while shell commands and file writes are refused.

Enables searching imported AI conversations locally across different providers from an MCP client, with read-only access to the archive.

Enables AI coding agents to persist and retrieve project knowledge using three MCP tools with local vector and full-text search.

Provides durable project context for coding agents, including project maps, session history, and explicit memories, all stored locally.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Identity infrastructure for AI agents. Gives agents an evolving persona, session continuity, and self-correcting retrieval so they stop being strangers. Local-first, model-agnostic.

Turn editor chat history (Cursor/Claude Code/Windsurf/Copilot/Codex CLI) into typed Markdown memories + AGENTS.md + Cursor Rules via MCP. Local-first, git-trackable.

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

Enables local MCP clients to list, read, write, and search notes in an Obsidian vault via an HTTP server running inside Obsidian.