search_docs
Search indexed documentation files to find relevant information by querying the FastMCP documentation index and returning top matching filenames.
Instructions
Search the documentation index and return top filenames for query.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- main.py:94-98 (handler)The handler function for the 'search_docs' tool. It is registered with the @mcp.tool decorator, calls the core implementation, and returns a list of top filenames matching the query.
@mcp.tool def search_docs(query: str) -> list: """Search the documentation index and return top filenames for `query`.""" results = search_docs_impl(query, top_k=5) return [r.get('filename') for r in results] - main.py:88-92 (helper)Core implementation of the search logic. Retrieves the pre-built index and performs similarity search using minsearch, returning the top results.
def search_docs_impl(query: str, top_k: int = 5): idx = get_index() results = idx.search(query, num_results=top_k) return results - main.py:81-86 (helper)Lazy-loading helper for the documentation index. Builds it on first use if not cached and returns the index instance.
def get_index(): global _INDEX_CACHE if _INDEX_CACHE is None: _INDEX_CACHE = build_index_from_zip() return _INDEX_CACHE - main.py:69-79 (helper)Builds the minsearch index by downloading the FastMCP repo zip (if needed), extracting .md/.mdx files, and indexing their content and filenames.
def build_index_from_zip(): docs = [] ensure_zip() for fname in os.listdir('.'): if fname.lower().endswith('.zip'): for filename, text in iter_md_files_from_zip(fname): docs.append({'content': text, 'filename': filename}) idx = Index(text_fields=["content"], keyword_fields=["filename"]) idx.fit(docs) return idx - main.py:44-53 (helper)Downloads the FastMCP GitHub repo zip archive if it doesn't exist locally.
def ensure_zip(): if os.path.exists(ZIP_NAME): return resp = requests.get(ZIP_URL, stream=True, timeout=60) resp.raise_for_status() with open(ZIP_NAME, "wb") as f: for chunk in resp.iter_content(1024 * 64): if chunk: f.write(chunk)