wisdomforge-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Host for the HTTP dev server (npm run dev:http). Defaults to 127.0.0.1. | 127.0.0.1 |
| PORT | No | Port for the HTTP dev server (npm run dev:http). Defaults to 3000. | 3000 |
| WF_SRC | No | Path to the wisdomforge source checkout, used during ingest to import curriculum TypeScript. Defaults to ../wisdomforge-src. | ../wisdomforge-src |
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
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_contentA | Rank WisdomForge items for a query. Uses the site's BM25 search index for corpus documents and the same tokenizer over catalog titles and excerpts. Optional filters: band, subject, type, figure. Default limit 10. |
| get_itemA | Fetch one catalog item. include=summary returns metadata, a short excerpt, media, and the Hermes prompt. include=chapters adds chapter text. include=full adds the stored body text. |
| list_age_bandsA | The four WisdomForge age bands with age ranges, promises, and the booklet level mapping (elementary, middle, high, adult). |
| list_subjectsA | The ten subjects with item counts. Pass band to count only items in that age band. Index documents are not counted. |
| list_by_age_bandA | Page lessons, books, booklets, audio, and demos for one age band. Optional subject and type filters. cursor is opaque; pass nextCursor back for the next page. Default limit 20. |
| list_coursesC | Books and lesson tracks in title order. A course is a book or a subject unit's sittings for one band. Each row includes ordered item ids. |
| get_course_outlineB | Ordered chapters or sittings for a course_id from list_courses. Each entry has an item_id. |
| get_media_urlsA | Public media URLs for an item (pdf, epub, mp3, image, markdown), with MIME type and size when known. The server does not proxy bytes. kinds filters the list; omit it for every kind on the item. |
| get_lesson_plan_seedB | Objectives, Hermes pairing line and prompt, discussion questions, activities, cautions, and printable links for an item. learner_profile is optional and is not stored. |
| recommend_for_learnerB | Deterministic ranking for one request. Age maps to a band (through 10 little, 11–14 young, 15–18 emerging, 19+ adult). Other bands are excluded. Auditory learners are boosted toward audio, reading learners toward books and printables, visual learners toward images and art, kinesthetic learners toward lessons with a Try This. No model is called and nothing is stored. |
| get_catalog_infoB | Counts by item type, content version (source git SHA and search-index build time), level mapping, and the license and child-safety notes. |
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
Most tools have distinct purposes, but a few boundaries blur: get_item can return media while get_media_urls exists specifically for media URLs, and list_courses already includes ordered item IDs that get_course_outline also provides. Descriptions largely clarify intended use.
All names use snake_case with clear verb prefixes (get_, list_, search_, recommend_). The pattern is predictable throughout, with only minor prepositional variants like list_by_age_band.
Eleven tools is well within a healthy range for a read-only content catalog. Each tool covers a distinct facet: discovery, detail, media, lesson plans, recommendation, and catalog metadata.
The surface covers the full read lifecycle for this domain: browse by age band/subject, search, course outlines, item details, media URLs, lesson plan seeds, recommendations, and catalog metadata. No obvious gaps for content discovery or lesson preparation.