Skip to main content
Glama
JPeetz

Hermes Docs MCP Server

by JPeetz

Hermes Docs MCP Server

Search, navigate, and read the complete Hermes Agent documentation — from within any MCP client, including Hermes itself.

License: MIT

No more switching tabs. No more stale knowledge. Add one line to your ~/.hermes/config.yaml and your agent can search its own docs in two tool calls.

Quick Start

# Install
pip install -e .

# Build the doc index
python -m server.hermes_docs_server rebuild

# Add to Hermes config (~/.hermes/config.yaml)
mcp_servers:
  hermes-docs:
    command: "python"
    args: ["-m", "server.hermes_docs_server"]
    tools: true
    prompts: false
    resources: false

Restart Hermes and ask: "Search the docs for how MCP auth works."

Related MCP server: docs-mcp

Why?

Hermes Agent's documentation lives at hermes-agent.nousresearch.com/docs — a well-structured Docusaurus site. But the agent can't natively search it. You either:

  1. Open a browser tab and search manually

  2. Ask the agent (which uses its training data — may be stale or imprecise)

Hermes Docs MCP Server fixes this. It indexes the docs into a local SQLite FTS5 database and exposes structured tools. The agent fetches current documentation, with snippets and full page content, every time.

Tools

Tool

Description

search_docs(query, limit=10)

FTS5 full-text search across all documentation

read_page(slug)

Read a full doc page by URL slug

list_sections()

Browse documentation structure

list_pages(section)

List pages within a section

doc_stats()

Index statistics

Requirements

  • Python 3.10+

  • MCP SDK (pip install mcp)

  • httpx (for index building — pip install httpx)

Architecture

hermes-docs-mcp-server/
├── server/
│   └── hermes_docs_server.py    # MCP server (FastMCP-compatible) + SQLite FTS5 index
├── scripts/
│   └── fetch_hermes_docs.py     # Doc indexer: scrapes live site OR reads local repo
├── SKILL.md                      # Hermes optional-skill definition
├── README.md
└── pyproject.toml

Index Management

  • Live index: python -m server.hermes_docs_server rebuild — scrapes the Hermes docs site

  • From repo: python -m scripts.fetch_hermes_docs --repo /path/to/hermes-agent — builds from a local checkout

  • Custom path: set HERMES_DOCS_INDEX_PATH env var

The index uses sqlite3 FTS5 (stdlib) — zero external search infrastructure.

License

MIT — same as Hermes Agent. The indexed documentation is from the Hermes Agent repo (MIT).

Author

Joerg Peetz — part of the Hermes Agent growth and contribution initiative.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

  • F
    license
    A
    quality
    D
    maintenance
    Provides AI assistants with real-time access to the AGNO framework documentation by enabling them to browse, search, and fetch documentation pages. This server allows users to query information about AGNO's Agents, Teams, and Workflows directly through MCP-compatible clients.
    16
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Indexes documentation sites by base URL and serves keyword search, optional semantic search, and Markdown page retrieval as MCP tools, all from a single SQLite file.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to search, read, and traverse documentation bundles in Open Knowledge Format via MCP tools.
    561
    68
    MIT

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/JPeetz/hermes-docs-mcp-server'

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