Skip to main content
Glama
deenesjakoruzh
veer-mehta

fathom-mcp

by veer-mehta
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

fathom-mcp

文档 RAG 系统：爬取文档站点 → 本地分块 + 嵌入（HuggingFace）→ 存储到 Postgres+pgvector → 通过 MCP 服务器、REST API 和 Web UI 进行语义搜索。

架构

flowchart LR
    A[Browser] --> B[API Server]
    B --> D[Web UI]
    B --> C[(Postgres + pgvector)]
    B --> G[Ingestion Pipeline]
    G --> H[Scraper Subprocess]
    G --> C
    I[AI Client<br/>Claude, Cursor] -->|MCP over stdio| F[MCP Server]
    F --> C

Related MCP server: MCPDocSearch

快速开始

git clone ... fathom-mcp && cd fathom-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e ".[local]"
docker compose up -d
cp .env.example .env              # set LLM_API_KEY
.venv/bin/docs-mcp-api            # http://127.0.0.1:8000

npm（无需克隆）

npx @fathom-mcp/server            # first run installs ~5GB deps, then instant
npx @fathom-mcp/server --api      # REST API + web UI

MCP 工具

add_documentation · search_documentation · list_sources · get_ingest_status · add_local_docs

REST API

端点

说明

GET /search?q=...

语义搜索

GET /sources

已索引来源

POST /upload

上传文件

POST /upload-folder

索引本地文件夹

GET /llm-chat?q=...

与文档对话

GET /about

系统信息

OpenCode

添加到 ~/.config/opencode/opencode.jsonc：

{
  "mcp": {
    "fathom-mcp": {
      "type": "local",
      "command": ["npx", "-y", "@fathom-mcp/server"]
    }
  }
}

配置

~/.fathom-mcp/.env — 设置 EMBEDDING_PROVIDER=api 和 EMBEDDING_API_KEY 以使用远程嵌入（Jina、OpenAI 等），或保持 local 以使用 HuggingFace。

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd
A
license - permissive license
Not graded
quality - not tested
B
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • AgentBase

    Shared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.

  • agentbay-mcp

    Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.

  • writespace-mcp

    Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/veer-mehta/fathom-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server