gknowledge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROJECT_PATH | Yes | Path to the gknowledge project folder, passed as the single positional argument to `gknowledge-mcp`, e.g. `gknowledge-mcp ~/Knowledge/my-project` or `"args": ["/home/you/Knowledge/my-project"]` in the MCP client configuration. This is the wiki folder the agent reads and writes. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Wiki 'gknowledge-demo'. Search before reading; cite page slugs in your answers.
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 |
|---|---|
| search_wikiA | Search the gknowledge wiki. Returns matching pages with slug, type and a one-line summary. Use read_page for details. |
| read_pageA | Read one wiki page as Markdown, including its sources and the pages that link to it. |
| list_pagesB | List wiki pages, optionally filtered by type (source, entity, concept, topic, answer). |
| askB | Answer a question from the wiki with numbered citations, using the provider configured in the project. |
| add_sourceB | Import a local file (Markdown, text, PDF, HTML) into the project and ingest it into the wiki. |
| stale_sourcesA | Lint the wiki for drift: sources whose original file changed after ingestion, with the pages that still reflect the old version. Re-import or refresh them in the app. |
| recent_activityC | Recent operations from the wiki log (ingests, saved answers). |
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 7 tools
Each tool targets a fairly distinct capability: browsing (list_pages), querying (search_wiki), reading (read_page), question answering (ask), ingestion (add_source), activity log, and drift detection. The only mild overlap is list_pages vs search_wiki, but the descriptions clarify that one enumerates by type while the other matches a query.
Most tools follow verb_noun (list_pages, search_wiki, read_page, add_source), but recent_activity and stale_sources are noun phrases and ask is a bare verb. The convention is readable but clearly mixed.
Seven tools is well-scoped for a wiki/knowledge-base server: each covers a distinct part of the browse-search-read-ingest-lint lifecycle with no filler.
The surface covers discovery, reading, Q&A, ingestion, and drift linting, which is solid lifecycle coverage. Minor gaps: stale_sources only detects drift (refreshing is pushed to the app), and there is no update/delete or page-authoring operation for existing content.