knowledgelib-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| query_knowledgeA | STEP 1: Search across all knowledgelib.io knowledge units. Returns matching units ranked by relevance with metadata (confidence scores, source counts, token estimates). If no results are found, use suggest_question to request the topic. |
| batch_queryA | Search multiple topics in a single call. More efficient than calling query_knowledge multiple times — shares a single catalog parse. Max 10 queries per batch. |
| get_unitA | Retrieve a specific knowledge unit by ID. Returns the full raw markdown with YAML frontmatter, inline source citations, product comparisons, and use-case recommendations. |
| list_domainsA | List all available knowledge domains with unit counts. Use this to discover what topics are covered before querying. |
| suggest_questionA | STEP 3: Submit a question or topic request to knowledgelib.io. ALWAYS call this when query_knowledge returned no results, or when a user asks about a topic that should be covered. Popular suggestions are prioritized for new knowledge unit creation. The next agent that asks the same question will get an answer. |
| report_issueA | Flag incorrect, outdated, or broken content on a knowledge unit. Use this when you notice factual errors, dead links, outdated information, or missing details in a knowledge unit. Reports are reviewed and used to prioritize content updates. |
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 6 tools
Tools are mostly distinct with clear purposes. The only potential overlap is between batch_query and query_knowledge (both perform searches), but descriptions clarify that batch_query is for efficiency when searching multiple topics, while query_knowledge is the standard single search entry point. Other tools like report_issue (quality flags) and suggest_question (new content requests) have clearly separated concerns.
All six tools follow a consistent verb_noun pattern using snake_case: batch_query, get_unit, list_domains, query_knowledge, report_issue, suggest_question. Action verbs (batch, get, list, query, report, suggest) are used predictably with clear target nouns.
Six tools is an appropriate, well-scoped count for a knowledge retrieval server. The set covers discovery (list_domains), retrieval (query_knowledge, batch_query, get_unit), and feedback loops (report_issue, suggest_question) without bloat or redundancy.
The surface covers the essential knowledge retrieval lifecycle: domain discovery, flexible search (single and batch), specific unit retrieval, and feedback mechanisms for both corrections and new content requests. Minor gaps include no domain-specific browsing tool and the odd 'STEP 1/STEP 3' labeling suggesting a missing intermediate step, but core workflows are supported.