fathom-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_API_KEY | Yes | API key for the LLM provider, used for chat functionality. | |
| EMBEDDING_API_KEY | No | API key for the embedding provider, required when EMBEDDING_PROVIDER is set to 'api'. | |
| EMBEDDING_PROVIDER | No | Embedding provider: 'local' for HuggingFace or 'api' for remote embeddings (Jina, OpenAI, etc.). | local |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_documentationA | Crawl a framework/library documentation site and index it for semantic search. Re-ingesting an existing source is incremental: pages whose extracted markdown is unchanged are skipped (no re-embedding). Args: name: Short identifier for the framework, e.g. "react". version: Version string, e.g. "18.3" or "latest". base_url: Entry point URL of the documentation site. max_depth: How many link hops to follow from base_url. max_pages: Hard cap on the number of pages crawled. background: If true, start the crawl and return a job id immediately; track it with get_ingest_status. Large sites should use this to avoid tool timeouts. prune_missing: If true, delete indexed pages that this crawl did not visit. Only enable when depth/page caps cover the whole site, otherwise capped crawls would delete valid pages. lang: ISO 639-1 language code to filter pages (e.g. "en"). Only pages matching this language are crawled. sitemap: If true, discover pages from sitemap.xml instead of following links. Gives better coverage for docs sites that expose a sitemap. |
| get_ingest_statusA | Check progress of a background add_documentation job. Args: job_id: The id returned when the job was submitted with background=true. |
| search_documentationA | Semantic search over indexed documentation. Returns the most relevant markdown chunks with their source URL and heading path. Use add_documentation first if nothing is indexed yet. Args: query: What to look for, e.g. "how to define a loader". name: Optional framework name filter, e.g. "react". version: Optional version filter, e.g. "18.3". k: Number of chunks to return (1-20). mode: "hybrid" (default) fuses vector + keyword ranking; "vector" or "keyword" force a single strategy. |
| list_sourcesA | List all indexed documentation sources with page and chunk counts. |
| add_local_docsA | Index local documentation files from a folder on disk. Walks the folder, finds supported files (HTML, Markdown, PDF, TXT), extracts text, chunks, embeds, and stores them for semantic search. Args: name: Short identifier for this collection, e.g. "internal-api". path: Absolute or relative path to the folder on the server. recursive: If true, descend into subdirectories (default true). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct operation: web ingestion (add_documentation), local ingestion (add_local_docs), job tracking (get_ingest_status), search (search_documentation), and enumeration (list_sources). The two ingest tools could superficially be confused, but their descriptions clearly separate web-crawl vs local-folder scopes.
All tools use consistent snake_case verb_noun naming: add_documentation, add_local_docs, get_ingest_status, search_documentation, list_sources. The verb set (add/get/search/list) is predictable and readable throughout.
Five tools is well-scoped for a documentation indexing/search server, covering ingestion, async job tracking, retrieval, and listing. No tool feels redundant or gratuitous.
The surface covers ingest (web + local), status, search, and list, which handles the core RAG lifecycle. However, there is no tool to delete or remove an indexed source, and no way to inspect job history or cancel a running job, leaving minor gaps.