opencode-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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| docs_listA | List all available documentation sources stored locally. Shows source names, page counts, and descriptions. |
| docs_searchB | Search across all local documentation. Returns matching pages with snippets. Use this to find relevant documentation. |
| docs_readA | Read a specific documentation page. Provide sourceId and pagePath to read the full content. If pagePath is omitted, lists all pages in the source. |
| docs_add_urlB | Add documentation from a URL. Features: recursive crawling (follows links), Playwright support for JS-rendered sites (React, Vue, etc.), smart content detection. Use recursive=true to crawl multiple pages. |
| docs_add_sitemapA | Crawl an entire documentation site from its sitemap.xml. Scrapes all pages (up to maxPages), converts to Markdown, and stores locally. Use for adding complete doc sites. |
| docs_add_openapiB | Import an OpenAPI/Swagger specification from a direct JSON URL. Converts all API endpoints to searchable documentation. Automatically uses saved credentials for the host. |
| docs_add_swaggerB | Import documentation from a Swagger UI page. Automatically detects the OpenAPI spec URL by trying common patterns. Use this when you have a Swagger UI URL like /swagger or /api-docs. |
| docs_updateA | Update/refresh existing documentation by re-scraping. Can update an entire source or a single page. Detects changes and shows diff summary. |
| docs_previewA | Preview scraped content without saving. Use this to test scraping before adding docs. Shows extracted content, metadata, and discovered links. |
| docs_authB | Manage authentication credentials for documentation sources. Actions: add (save credentials), list (show all), remove (delete), get (show one). Credentials are automatically used when fetching APIs. |
| docs_removeA | Remove a documentation source and all its pages. Requires confirmation. |
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 11 tools
The four add tools (url, sitemap, swagger, openapi) target distinct source types, but overlap exists between generic URL crawling and sitemap crawling, and between Swagger UI and OpenAPI JSON imports. Descriptions clarify the intended use, but an agent may still hesitate when both could work.
All tools share the 'docs_' prefix and use consistent snake_case, with predictable forms like docs_add_*, docs_list, docs_search, docs_read, docs_update, docs_remove. No mixing of conventions (e.g., camelCase) occurs.
11 tools is well within the ideal 3-15 range. Each tool covers a distinct operation in documentation ingestion, management, or retrieval, with no obvious redundancy.
Core lifecycle operations are present: add from multiple sources, list, search, read, update, remove, preview, and auth management. Minor gaps include no page-level deletion (only source removal) and no credential editing, but these are workaroundable.