Practitioner Knowledge MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNOWLEDGE_MCP_DB | No | Path to the SQLite database file that stores ideas (defaults to ~/.knowledge-mcp/ideas.db) |
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 |
|---|---|
| store_ideaB | Save a new idea to the knowledge base. Returns its id and the stored record. |
| get_ideaC | Return the full record for one idea. |
| update_ideaB | Change one or more fields of an existing idea. Omitted fields stay as they are. Returns the updated record. |
| search_ideasA | Full-text search across titles, domains, problems, insights, assumptions, and tags.
Results are ranked best match first and include a snippet with matched words in
[brackets]. If no idea contains every word, ideas containing any word are returned
instead, and each result's |
| list_ideasA | List ideas, newest first, optionally filtered by domain, tag, or status. |
| idea_statsA | Return the total number of ideas, counts by domain and by status, and the most-used tags. |
| list_frameworksA | List the analytical frameworks available, with each one's name, title, category, and when to use it. |
| get_frameworkA | Return one framework's details and its full Markdown text. |
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 8 tools
Each tool has a clearly distinct purpose: idea-level CRUD/stats/search/list versus framework-level retrieval/list. The only possible overlap between list_ideas and search_ideas is resolved by descriptions emphasizing filtered listing versus full-text ranked search. Agents should not confuse these tools.
Most names follow a predictable verb_noun snake_case pattern (get_idea, store_idea, update_idea, search_ideas, list_ideas, get_framework, list_frameworks). The only deviation is idea_stats, which uses noun_stats instead of a verb-first pattern, but it remains readable and consistent with snake_case.
Eight tools is well-scoped for a practitioner knowledge base covering ideas and frameworks. Each tool earns its place by handling a distinct operation without excessive fragmentation.
The idea lifecycle covers create, read, update, list, search, and stats, which supports core workflows. A delete_idea operation is missing, and frameworks are read-only, but these are minor gaps given the likely reference-data nature of frameworks.