Skip to main content
Glama
124,386 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

  • A
    license
    Not graded
    quality
    B
    maintenance
    Graph-level operations for Karpathy LLM Wiki knowledge bases, enabling LLM agents via MCP and humans via CLI to perform structured graph surgery including node/edge CRUD, wikilink management, index rebuilding, and graph metrics.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables LLM clients to read, search, create, update, and delete notes in a self-hosted shared memory bank over MCP, using hybrid vector and full-text search with optional summarization.
    4
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    A self-learning knowledge layer for local LLM chat that answers questions from Markdown files, writes new knowledge back every turn, and provides grounding verdicts.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for persistent, compounding markdown wikis maintained by LLMs. Enables incremental knowledge base building with interlinked pages, search, and raw source management.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables Claude to automatically extract entities and relationships from URLs, PDFs, and YouTube videos to build structured knowledge graphs in Neo4j. It supports custom schemas, academic citation extraction, and community detection for advanced research and content analysis.
    Apache 2.0
  • A
    license
    Not graded
    quality
    F
    maintenance
    Enables LLMs to store, search, and manage memories with hybrid semantic and keyword search using ChromaDB and Neo4j for persistent memory and knowledge graph capabilities.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that enables persistent, hybrid, local memory for LLM agents, with vector + BM25 search, knowledge graph, and policy-driven retention, providing token-budgeted context injection for AI assistants.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes a local SQLite entity/fact/alias knowledge graph to MCP clients over stdio, letting a model look up entities with their parents, children and facts, learn or update records and operational notes, and receive a token-budgeted context block for any prompt. This keeps small 4B–9B models grounded in exact structured data without stuffing prompts or losing relationships and aliases.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables creation of persistent, compounding knowledge bases using Karpathy's LLM Wiki pattern with LLM-maintained markdown wikis. Supports automated ingestion, cross-referencing, synthesis, and linting of sources as an alternative to traditional RAG systems.
    63
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Long-term memory that files itself into a Markdown wiki you can read: a small typed classifier, not the LLM, decides where each fact or document goes, using far fewer LLM tokens. Recall answers with cited notes; it files PDFs, Office files and spreadsheets too, and runs with no key on the client's own models or fully local with Ollama.
    16
    18
    492 PyPI
    305
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    An MCP server for a plain-markdown LLM wiki vault with YAML frontmatter and Obsidian-style wiki-links, enabling headless full-text search, note reading, backlink discovery, and safe append/create-only writing with path traversal protection and an immutable raw/ directory.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables an LLM to autonomously maintain a Markdown-based wiki with YAML frontmatter, using hybrid BM25 and local CPU vector search for fully offline retrieval without external APIs or databases.
    18
    31 npm
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Provides a lightweight personal knowledge base MCP server that compiles raw materials into interconnected Wiki pages, with hybrid search (BM25, optional vector, link expansion) and tools for querying, reading, writing, and ingesting content.
    5
    -
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to query a locally recorded personal lifelog, searching verbatim transcripts and temporal knowledge-graph facts, retrieving day or week summaries, gathering everything known about a person, and tracing topics over time. Answers omit timestamp filters, merge overlapping passages, and gracefully fall back to whichever store is reachable.
    4
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    An MCP server that provides AI assistants with long-term semantic memory using a Markdown-based knowledge base with hybrid search (vector + FTS5) and syntax-aware chunking. It supports idempotent ingestion, project isolation, and integrity linting.
    4
    -
  • F
    license
    A
    quality
    B
    maintenance
    A shared memory MCP server for the Senegalese MOHEBS teaching and learning materials pipeline that ensures AI-generated documents remain consistent in characters, terminology, and concept coverage while varying example domains, operating across grade and subject via Firebase storage.
    17
    -
  • A
    license
    A
    quality
    D
    maintenance
    Implements the Recursive Language Model pattern, enabling LLMs to process arbitrarily long contexts through session-based document management, on-demand chunking, BM25 search, and artifact storage.
    12
    1
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables LLMs to read a user-owned, local-first memory store kept in a portable folder (USB, SSD or laptop), with per-profile permissions limiting what each client can see and access cut off when the pocket is locked or unplugged. Also lets models propose new memories for the user to review and approve, keeping provenance and keeping canonical memory free of direct model writes.
    8
    Apache 2.0
  • A
    license
    B
    quality
    C
    maintenance
    An MCP server that provides AI agents with a governed wiki requiring human approval before any formal page update, combining structured knowledge management with safe, auditable writes.
    14
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    MindBase implements Karpathy's "LLM wiki" pattern as an MCP server. Instead of retrieving chunks at query time (RAG), the LLM maintains a persistent wiki between your conversations: it reads every source you feed it, cross-references pages with [[wikilinks]], flags contradictions between sources, and keeps a context.md that reflects your current synthesized thinking.
    50
    138
    MIT
  • A
    license
    C
    quality
    B
    maintenance
    A local-first memory cartridge for MCP-compatible AI clients, providing durable, inspectable, and auditable memory storage with a read-only-by-default MCP server.
    36
    79 PyPI
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables chat with multiple LLM providers (OpenAI and Anthropic) while maintaining persistent conversation memory. Provides extensible tool framework for various operations including echo functionality and conversation storage/retrieval.
    MIT
  • A
    license
    Not graded
    quality
    F
    maintenance
    A local stdio MCP server that exposes a shared brain (read/search/write) over ~/.claude/memory, allowing memories written in any agent to be readable and searchable across all three (Claude Code, Cursor, Codex). It provides tools like memory_search, memory_read, memory_write, etc., with no external services.
    14 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes a local Markdown knowledge base over HTTP MCP with a dedicated endpoint and bearer token, giving other compatible agents read-only tools (kb_info, kb_search, kb_read, kb_list, kb_related) plus MCP resources to search, read, and explore linked pages. Tokens can be rotated or sharing disabled at any time, and access stays local by default.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables LLM applications and agents to persist and recall scoped memories in a local SQLite store, with semantic/hybrid/metadata search, review-first corrections and summaries, and controlled export, backup, and purge operations over stdio.
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables Claude Code, Codex, and local models to share one canonical PostgreSQL conversation history over MCP, preserving append-only facts, decisions, preferences, events, and project state with searchable retrieval.
    GPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Exposes a Markdown vault as long-term memory for MCP-compatible LLM clients, letting agents search, read, create, update, and delete notes, manage core persona and persistent directives, append to daily logs, and inspect backlinks, tags, and the link graph. It runs locally over stdio against a chosen vault directory.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to search and retrieve source-grounded memory records from a local Markdown vault and SQLite index, and to build bounded task contexts through stdio MCP. Supports normal and bounded tool modes while respecting scope, lifecycle status, and response limits.
    Apache 2.0