RVTDocs MCP
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rvtdocs_fetchC | Fetch RVTDocs in single-fetch mode with trust-gate output shaping. mode:
|
| rvtdocs_scanC | Resolve and trust-check a query with minimal output for low token cost. |
| rvtdocs_debugC | Run diagnostic fetch with snippet and resolver/semantic trace metadata. |
| rvtdocs_batchB | Batch-fetch multiple RVTDocs queries in a single tool call. Reduces tool-call overhead when looking up related APIs. Returns a list of results, one per query, plus aggregate stats. mode:
|
| rvtdocs_statsB | Query usage statistics for the rvtdocs MCP server. Returns tool call counts, success rates, cache hit rates, and top queries/failures for the specified time period. |
| rvtdocs_version_infoA | Returns supported Revit API documentation versions and recommendations. |
| rvtdocs_schemaA | Return JSON schemas for all rvtdocs tools for external validation. |
| rvtdocs_session_setA | Store a key-value pair in the session store. Useful for caching resolved API info between tool calls. Data is ephemeral (lost on server restart). |
| rvtdocs_session_getC | Retrieve a value from the session store. |
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 9 tools
Multiple tools (rvtdocs_fetch, rvtdocs_scan, rvtdocs_debug, rvtdocs_batch) serve similar fetching purposes with only subtle differences in output mode and verbosity. While descriptions clarify some distinctions, an agent may easily misselect among them.
All tools share the 'rvtdocs_' prefix, but the second part mixes verbs (fetch, scan, debug) with nouns (schema, stats, version_info) and verb_noun pairs (session_get, session_set). This inconsistency, though not chaotic, reduces predictability.
With 9 tools, the server is well-scoped. Each tool serves a distinct purpose (fetching, session management, schema, stats, version info) without bloat or triviality.
The tool surface covers core needs: fetching docs (multiple modes), session caching, schema validation, statistics, and version info. Minor gaps like a dedicated search or listing tool are absent, but the domain is narrow and the set feels functional.