smartipedia-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SMARTIPEDIA_URL | No | Point at your own instance. Default is https://smartipedia.com. | https://smartipedia.com |
| SMARTIPEDIA_EDITOR | No | Attribution name on edits. Default is agent. | agent |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_topicsA | Keyword search over Smartipedia article titles and text. Returns slugs and summaries; call read_topic with a slug for the full article. |
| discover_topicsA | Semantic/vector search with optional filters. Use when keyword search misses, or to browse a category by meaning rather than exact wording. |
| read_topicA | Fetch the full Markdown article for a topic slug, with infobox, related topics and citations. |
| create_topicA | Generate a new sourced encyclopedia article from a title (web search + LLM, ~15s). Returns the existing article instead if the topic is already covered. Daily rate limit applies — search first. |
| preview_phraseA | Get a short AI explanation of any phrase without generating a full article. Cheap and fast — use it to decide whether a topic is worth creating. |
| edit_sectionA | Replace one section of an article with corrected Markdown. Preferred over creating a duplicate topic when you find an error. Pass expected_revision (from read_topic) to avoid clobbering a concurrent edit. |
| list_missing_topicsA | Topics people searched for that don't exist yet, ranked by demand. The highest-leverage queue for deciding what to write next. |
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
Most tools have distinct purposes: search_topics and discover_topics are the only pair that could be confused, but their keyword-vs-semantic distinction is explicitly described. read/create/preview/edit/list_missing are clearly separate operations.
Tool names generally follow a verb_object pattern (search_topics, read_topic, create_topic, edit_section, list_missing_topics). Minor inconsistency between singular and plural objects and preview_phrase/edit_section not matching topic naming, but the pattern is recognizable.
Seven tools is a well-scoped size for a knowledge-base server: search, discovery, read, create, preview, edit, and missing-topic queue each cover a distinct workflow without redundancy.
The core encyclopedia workflow is covered: discover/search, read, create, preview, edit, and prioritize missing content. Minor gaps exist (no delete/rename/revert or full-topic replacement), but edit_section handles corrections and the stated use cases are covered.