jmp-docs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JMPDOCS_PATHS__DATA_DIR | No | Directory where the corpus, index, and other data are stored. If your project is inside a synced folder (OneDrive, Dropbox), set this to an unsynced location to avoid issues. | |
| JMPDOCS_SOURCE__VERSION | No | Version of JMP documentation to index. Default is likely '19.1'. Change this if indexing a different JMP release. | 19.1 |
| JMPDOCS_LLM__NUM_PREDICT | No | Maximum number of tokens to generate for answers. Default is '420'. | 420 |
| JMPDOCS_SOURCE__BASE_URL | No | Base URL of the JMP documentation. Used by the crawler to download pages. Default is likely the official JMP documentation URL. | http://localhost:8080 |
| JMPDOCS_LLM__ANSWER_MODEL | No | The LLM model used for answering questions. Default is 'qwen3:8b'. Override with e.g. 'qwen3:14b' for higher quality (requires more resources). | qwen3:8b |
| JMPDOCS_RETRIEVAL__RERANK | No | Whether to use cross-encoder reranking. Default is 'false'. Set to 'true' to enable (may improve ranking but adds ~10x latency). | false |
| JMPDOCS_INDEX__EMBED_MODEL | No | Embedding model used to build the index. Default is 'BAAI/bge-base-en-v1.5'. Use 'BAAI/bge-small-en-v1.5' for a ~3x faster build. | BAAI/bge-base-en-v1.5 |
| JMPDOCS_RETRIEVAL__K_FINAL | No | Number of final retrieved documents to pass to the LLM. Default is '8'. | 8 |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_jmp_docsA | Search the JMP 19.1 documentation and return the most relevant excerpts. Handles JMP's own naming: asking for a "random forest" finds "Bootstrap Forest", "pivot table" finds "Tabulate", and so on. |
| whats_thisA | Explain an on-screen JMP element using JMP's own context-help map. JMP ships a mapping from UI element names to the exact documentation section that describes them; this looks the user's words up in it. |
| find_menu_pathA | Find where a feature lives in JMP's menus. Backed by JMP's own menu reference (every menu item and its description), so the paths are authoritative rather than scraped from prose. |
| get_jmp_pageA | Return the full text of one documentation page, with its figures. |
| find_exampleA | Find worked examples, optionally restricted to a sample data table. JMP users learn from the built-in sample data, so this searches the ~630 'Example of...' pages specifically. |
| find_jmp_figuresA | Find documentation figures (JMP dialog and report screenshots) by caption. |
| list_jmp_booksA | List the JMP documentation books, with page counts. |
| browse_jmp_tocA | Browse the table of contents for one book. |
| jmp_fetch_liveA | Fetch a documentation page live from jmp.com, bypassing the local index. Use when a page may be newer than the index, or is not indexed. |
| index_statsA | Report what the local index contains and when it was built. |
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 10 tools
Each tool targets a distinct resource: docs search, menu lookup, examples, figures, TOC, books, context help, and page retrieval. The closest pair, get_jmp_page and jmp_fetch_live, is clearly differentiated by local index vs. live bypass.
Most tools follow a snake_case verb_noun pattern (search_jmp_docs, find_menu_path, get_jmp_page, browse_jmp_toc). A few deviations like whats_this, jmp_fetch_live, and index_stats are noticeable but do not seriously undermine the overall pattern.
Ten tools is well-scoped for a documentation server: it covers search, navigation, retrieval, examples, figures, menu paths, and index introspection without redundancy. Each tool has a clear role and none feels like filler.
The surface covers the full documentation workflow: discovering features, finding menu paths, browsing TOCs, retrieving pages, locating examples and figures, and checking index freshness. The live fetch fallback also handles newer or unindexed content, leaving no obvious dead ends.