Skip to main content
Glama
123,596 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

"Hosting Supabase on Your Own Server" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    B
    quality
    B
    maintenance
    On Board is a local MCP server that gives multiple AI agents and IDEs a shared project memory, ticket queue, and handoff history, so agents can seamlessly continue each other's work. It supports agent-to-agent wake events, enabling autonomous workflows like reject-fix-resubmit cycles without human relay.
    30
    4
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Experimental read-only MCP for Supabase application data: memory_search, memory_get and memory_list_recent under user-bound PostgreSQL RLS. Setup and demo: https://github.com/jryski/Supabase_user_MCP/blob/main/docs/GETTING_STARTED.md . Public preview is POSIX-only and synthetic-only; native Windows, hosted OAuth, one-click installation and writes are not available.
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    A local catalogue of the AI tools people share in group chats: search it, save links, vote out junk, and file items into your own folders. Works with any model or none.
    2
    15
    486 npm
    27
    MIT
  • F
    license
    A
    quality
    C
    maintenance
    Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.
    10
    10
    -
  • F
    license
    A
    quality
    D
    maintenance
    Enables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.
    4
    -
  • A
    license
    A
    quality
    B
    maintenance
    Provides AI coding tools with one local SQLite memory and rules store they can read over MCP, REST or the CLI, so facts, sessions and goals persist across sessions and shared rules are written into each tool's own instruction file. Runs entirely on your machine with no account, telemetry or network calls by default.
    4
    14
    444 npm
    10
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Chronicle is a secure, local-first MCP server designed to transform your historical AI chat logs into a persistent memory vault. It seamlessly parses and indexes raw conversation exports from ChatGPT, Claude, and various IDE transcripts directly on your machine. By utilizing dynamic token-stripping, the engine automatically cleans redundant syntax wrappers to save up to 40%
    8
    74 PyPI
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables users to search locally across imported Claude, ChatGPT, and Claude Code conversations and retrieve surrounding turns with citations, while keeping indexing and storage on their own computer.
    2
    143 PyPI
    Apache 2.0
  • A
    license
    A
    quality
    A
    maintenance
    Self-hosted long-term memory gateway for AI clients, deployed to your own Cloudflare account (Workers + D1 + Vectorize). It captures conversations, consolidates them overnight, and exposes MCP tools to search, recall and write memories from any MCP client.
    10
    150
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    Turnbook records every conversation you have with your AI agents, word for word, in a store on your own PC. When a question depends on the past, the model you are using calls Turnbook over MCP and gets back a few thousand tokens of the conversations that answer it.
    7
    262 PyPI
    15
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, updating, and scheduling these memories.
    4
    7
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    A local MCP server that gives saved bookmarks a lifecycle with time-based layers (pending, watching, kept, lapsed), so they get decided on instead of accumulating. It aggregates bookmarks from your browsers, drips them into a daily queue, and supports keep/watch/drop decisions, restore, and undo.
    7
    40 npm
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    An MCP server that stores notes as Markdown files on your machine, enabling you to save, search, and manage notes through natural language with Claude Code or Claude Desktop.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Search past OpenCode conversation history before starting new work on a module or file, via a local read-only FTS5 index built from OpenCode's own SQLite database. No network calls, fully local. 7 tools for keyword search, file lookup, and session browsing.
    7
    61 PyPI
    4
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Privacy-first local document search using semantic search. Runs entirely on your machine with no cloud services, supporting PDF, DOCX, TXT, and Markdown files.
    9
    5,381 npm
    430
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Self-hosted memory for your AI, kept in your own git repo: Markdown and HTML it reads and writes, beside PDFs, office files, images and JSON it reads as they are. 30 tools to search, read, write and file notes. Every change is attributed to a person or an AI, an agent's work undoes in one step, any note reads as it was on any date. Flags contradictions. Runs over stdio or as a server with OAuth.
    30
    1,578 PyPI
    6
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    Sends a folder of documents to a grid of idle laptops and office PCs, each running its own small Ollama model, and returns a knowledge graph your AI IDE can query with chunk-cited answers. Tools: ingest_directory_to_graph, query_local_graph, dispatch_mapreduce_text and grid_status; data never leaves your machines.
    4
    1
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    An MCP server that reads all your Claude Code project memory files and exposes them as tools. Lets any Claude instance — in any project, or via Claude.ai — query your full project history and preferences.
    5
    50 npm
    1
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Provides LLMs with access to molt-md, an encrypted markdown document hosting service, for managing and reading secure knowledge bases. It enables users to create, update, and organize encrypted documents into workspaces with full version control and end-to-end encryption.
    11
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Gives an AI agent a durable, private long-term memory hosted on the user's own Keephaven box, letting it write, read, list, search and delete notes and append to an immutable journal. Each agent is isolated to its own token-protected folder with quotas, read-only mode and instant revocation.
    8
    48 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Agent-agnostic persistent memory backend. 13 MCP tools, Supabase + Jina embeddings, multi-profile isolation, semantic recall across sessions.
    16
    7
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Memory vaults on your own machine, one per life domain, retrieved with a local BM25 index fused with vector search, where the human decides which vaults a model may answer from. Requires the Mnemosyne OS desktop app running locally; it also reports what other coding agents on the same machine are doing.
    31
    509 npm
    23
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Read-only recall over your past Claude Code, Codex, pi and Hermes sessions: semantic search for past decisions, rationale and findings, plus tools to list sessions, get the gist of one, find exact strings in it and read its turns. Works on your local memory or on any memory published as a Hugging Face dataset.
    5
    6
    597
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Basic Memory is a knowledge management system that allows you to build a persistent semantic graph from conversations with AI assistants. All knowledge is stored in standard Markdown files on your computer, giving you full control and ownership of your data. Integrates directly with Obsidan.md
    2
    12
    10,764 PyPI
    4,603
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    Connects AI assistants to IT Glue, the MSP documentation platform. Browse organizations, read and write documents and flexible assets, and answer natural-language questions via semantic vector search (OpenAI/Azure embeddings). Viewer/editor/admin roles gate tool access; bring-your-own-key applies IT Glue's native permissions. Runs over stdio or HTTP; Docker image available.
    27
    92 npm
    6
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables agents to query an organization's own documents and receive cited answers, while also maintaining persistent memory across conversations.
    4
    52 npm
    2
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables Claude Code to search, save, and relate local Markdown notes—lessons, do/don't rules, and task history—by project, ticket, epic, tags, or text, keeping everything on the user's own computer.
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Keeps your notes, decisions and projects in one folder on your own server, so your AI assistant picks up where the last chat ended. Reads and searches PDF, Word, Excel and mail as text; write policies per folder, a trash instead of delete.
    20
    61 npm
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    MCP server that gives Claude Code and other MCP clients persistent memory using plain Markdown notes stored on your disk and optionally synced to cloud storage (iCloud, OneDrive, Google Drive, Dropbox).
    36
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Shared, local memory for AI coding tools that stays true to your code. Claude Code, Cursor, and Codex share one memory per project; memories are linked to the files they depend on and retired automatically when those files change. Includes a local dashboard, import from CLAUDE.md/AGENTS.md, and export. Runs entirely on your machine.
    10
    242 PyPI
    4
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Local, private memory for coding agents: facts tied to files, reusable skills and a task board that persist across sessions. One SQLite file on your machine.
    16
    410 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    One local memory shared by Claude Code, Codex and Cursor on your Mac. Tell one app a decision and the others can recall it. Tools: recall, remember, forget, access_status; per-app access levels.
    4
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    This MCP server lets any compatible AI assistant read, extend and connect the matters in a person's life — plans, trips, people and places — from a repository that belongs to the user, so a new assistant picks up where another left off. It keeps the user's words verbatim, records every change, and stores the repository as a plain file on the user's own computer.
    14
    213 npm
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    Connects AI assistants like Cursor and Claude to your local Daylens timeline so they can answer questions about your past work sessions, no cloud or API keys needed.
    5
    9 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Builds interactive, filterable timelines from your own materials through an interview process, generating self-contained offline files with optional web publishing and cross-device sync.
    19
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    Enables AI assistants to search, create, and organize content in your Capacities.io knowledge base, with limitations on reading object content due to API restrictions.
    9
    15 npm
    1
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Connects Claude Code to a local EverOS instance for searching and storing long-term memory, keeping data entirely on your machine.
    4
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Local index and hybrid search (SQLite FTS5 + on-device vector KNN) over your AI coding-agent conversation history across 11 tools (Claude Code, Codex, Cursor, and more). Exposes search_threads, search_current_project, recent_threads, get_thread, list_tags, and list_open_todos so any agent can recall its own past work.
    23
    49
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    A personal work twin for any AI agent. It briefs agents on the guidance you have confirmed, checks consequential actions against explicit, expiring grants and asks otherwise, and turns your corrections into lessons only you can confirm.
    12
    2
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables Claude to save, retrieve, update, search, and organize personal ideas and reusable analytical frameworks in a private SQLite-backed knowledge base. Supports local desktop use or always-on access across a user's own devices over a private network.
    8
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Geniuz stores everything in a local database locally on Mac, Windows, Linux, Raspberry Pi. No cloud. No account. No API keys. Nothing leaves your machine. It's open source; you can read every line of code.
    14
    3
    36
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables AI agents like Claude and Cursor to directly query Google's NotebookLM for zero-hallucination answers based on your uploaded documents, eliminating the need for manual copy-pasting and providing expert-level synthesized responses with source citations.
    16
    38 npm
    8
    MIT