colyseus-docs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COLYSEUS_DOCS_PATH | No | Override the docs directory. | <package_root>/docs |
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_docsA | List every Colyseus documentation page available to this MCP server. Returns each page's slug (use as the |
| read_docA | Read a single Colyseus documentation page by its slug (e.g. 'room', 'room/messages', 'state', 'getting-started/typescript'). Use |
| search_docsA | Full-text search across all Colyseus documentation pages. Results are ranked by relevance (title hits weighted highest, then headings, then body) and each hit includes a snippet around the first match. Use this to find pages about a specific API, concept, or recipe (e.g. 'reconnection', 'schema @type', 'rate limit', 'matchmaker'). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| colyseus_overview | Returns a system-style message describing what Colyseus is and listing every documentation page (slug + title). Useful to prime a chat before the user asks their first question. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a completely distinct purpose: listing all pages, reading a specific page, and searching across pages. There is no ambiguity or overlap.
All three tool names follow a consistent verb_noun pattern using snake_case (list_docs, read_doc, search_docs), making them predictable and easy to understand.
Three tools is minimal but appropriate for a documentation server, covering the essential operations of discovering, reading, and searching content. It is slightly on the thin side but well-scoped.
The tool surface covers the core documentation tasks (listing, reading, searching). Minor gaps exist, such as no way to get a table of contents or hierarchical navigation, but list_docs already provides category information, so the gaps are not critical.