knowledge-basesearchresearchcitationsdeveloper-tools
Search cited, structured knowledge units with confidence scores, provenance, freshness data, and related-unit links.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent ā or use 1-click editor setup below.
Not yet automatically verified
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag ā we're steadily working through the catalog.
Manual Client & Custom JSON ConfigExpand JSON ā¾
Client Config & Setup
Choose your client or environment
Target File:
š” Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Overview
Use cases
Search for answers across indexed knowledge domains
Retrieve full knowledge units by identifier
Batch-search up to 10 topics in one request
Check source provenance and content freshness
Submit requests or report incorrect knowledge
Key features
Query knowledge units with filters
Batch queries for up to 10 topics
Full markdown unit retrieval
Confidence scores and inline source citations
Freshness and quality-status metadata
Related-unit knowledge graph links
Capabilities & Tool Schemas (6)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Knowledgelib IO.
query_knowledgeSearch across all knowledge units with filters
batch_querySearch multiple topics in one call (max 10)
get_unitRetrieve full markdown content by ID
list_domainsList all domains with unit counts
suggest_questionSubmit a topic request for new unit creation
report_issueFlag incorrect, outdated, or broken content
Documentation Overview
knowledgelib.io
AI Knowledge Library ā structured, cited knowledge units for AI agents. Pre-verified answers that save tokens, reduce hallucinations, and cite every source.
What is this?
1,800+ knowledge units across 18 domains (consumer electronics, software, business strategy, ERP integration, compliance, energy, finance, and more). Each unit answers one canonical question with:
- Confidence scores (0.0-1.0) per published methodology
- Inline source citations from 5-8 authoritative sources
- Freshness tracking with verified dates and temporal validity
- Quality status ā verified, needs_review, or unreliable
- Knowledge graph ā related units with typed edges
One API call replaces 5 web searches and 8,000 tokens of parsing.
Quick Start
MCP Server (Claude, Cursor, Windsurf)
Or add to claude_desktop_config.json:
MCP over HTTP (no install needed)
Streamable HTTP transport, JSON-RPC 2.0, MCP spec 2025-03-26.
REST API
LangChain (Python)
n8n
MCP Tools
| Tool | Description | Read-only |
|---|---|---|
query_knowledge | Search across all knowledge units with filters | Yes |
batch_query | Search multiple topics in one call (max 10) | Yes |
get_unit | Retrieve full markdown content by ID | Yes |
list_domains | List all domains with unit counts | Yes |
suggest_question | Submit a topic request for new unit creation | No |
report_issue | Flag incorrect, outdated, or broken content | No |
All read-only tools are marked with readOnlyHint: true and idempotentHint: true per MCP spec 2025-03-26, enabling parallel execution by agents.
API Features
- Structured error codes with retryable flag and retry_after_ms
- ETag / If-None-Match caching (304 Not Modified)
- Correlation IDs (X-Request-Id header on all responses)
- Quality status (verified / needs_review / unreliable) on all results
- Related units for knowledge graph traversal
- Content previews (150-char summaries without fetching full unit)
- Token budgeting (total_tokens across results)
- Rate limiting on write endpoints (10 suggestions/hr, 20 feedback/hr)
- Zod validation with per-field error messages
Entity Types
| Type | Count | Description |
|---|---|---|
| product_comparison | 418 | Best-of roundups with decision logic and buy links |
| concept | 336 | Definitions of terms agents often get wrong |
| software_reference | 239 | Code examples, anti-patterns, decision trees |
| execution_recipe | 202 | Step-by-step implementation plans |
| erp_integration | 166 | API capabilities, rate limits, data mapping |
| agent_prompt | 55 | System prompts for pipeline sub-agents |
| assessment | 54 | Structured scoring frameworks |
| decision_framework | 35 | Decision trees with trade-offs |
| benchmark | 28 | Industry benchmarks by segment |
| rule | 28 | Actionable directives with evidence |
Discovery
- /llms.txt ā Plain-text guide for LLMs
- /llms-full.txt ā Complete index of all questions
- /.well-known/ai-knowledge.json ā Machine-readable manifest
- /catalog.json ā Full catalog with metadata
- /for-agents ā Integration guide
Links
- Website: https://knowledgelib.io
- npm: https://www.npmjs.com/package/knowledgelib-mcp
- PyPI: https://pypi.org/project/langchain-knowledgelib/
- HTTP MCP: https://knowledgelib.io/mcp
- OpenAPI: https://knowledgelib.io/api/v1/openapi.json
- GPT Actions: https://knowledgelib.io/.well-known/openapi-gpt.json
License
CC BY-SA 4.0
Related MCP Servers
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks ā not a rating.
GitHub stars
1
Stargazers on the source repository.
npm downloads
54
Package downloads in the last 30 days.
Last commit
2mo ago
Most recent push to the default branch.
Tools exposed
6
Callable tools this server registers over MCP.
Directory activity
2 views
Config copies, upvotes, and views on AllMCPs.
Reviews
No reviews yet ā be the first to share how this listing worked for you.
Frequently Asked Questions about Knowledgelib IO
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/peterbeck111-knowledgelib-io)HTML Embed
<a href="https://allmcps.com/mcp/peterbeck111-knowledgelib-io"><img src="https://allmcps.com/api/badge/peterbeck111-knowledgelib-io?style=directory" alt="Knowledgelib IO on AllMCPs" /></a>