StitchAPI Docs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsA | Search the StitchAPI documentation semantically (hybrid BM25 + vector), entirely locally. Returns the most relevant doc sections as excerpts with deep links — never full pages. Follow up with get_doc to read a full page. |
| get_docA | Fetch a full StitchAPI documentation page as Markdown — the "read the whole thing" escape hatch for a search_docs hit. Pass a |
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 2 tools
The two tools have clearly distinct purposes: search_docs for finding relevant excerpts and get_doc for retrieving full pages. No overlap in functionality.
Both tools use consistent snake_case naming with verb_noun pattern: search_docs and get_doc. Simple and predictable.
With only 2 tools, the set is minimal but covers the core documentation workflow (search + full retrieval). For a dedicated documentation server, this is slightly thin but complete for its stated purpose.
The tools cover search and full-page retrieval. There is no explicit listing of all pages or navigation support, but for a documentation API that emphasizes search-first workflow, this is a reasonable surface with no major dead ends.