Server data from the Official MCP Registry
Structured domain knowledge for AI agents. 42x more accurate than RAG, 11x fewer tokens.
Structured domain knowledge for AI agents. 42x more accurate than RAG, 11x fewer tokens.
ckg-mcp is a well-structured MCP server for querying pre-compiled knowledge graphs with appropriate security design. The server operates entirely on read-only bundled CSV data with no external network calls, authentication, or credential handling. Minor code quality improvements around error handling and input validation are recommended, but no security vulnerabilities were identified. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
5 files analyzed · 9 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-yarmoluk-ckg-mcp": {
"args": [
"ckg-mcp"
],
"command": "uvx"
}
}
}From the project's GitHub README.
mcp-name: io.github.Yarmoluk/ckg-mcp
Compact Knowledge Graph MCP server. Pre-structured domain knowledge as a routing layer for agent stacks — 42× more efficient than RAG on structural queries.
Built on the CKG Benchmark — 45 domains, 7,928 queries, fully reproducible results.
Drop CKG into your agent stack as an MCP tool. Instead of retrieving text chunks and hoping the LLM infers structure, CKG gives agents pre-compiled dependency paths, prerequisite chains, and concept relationships — directly from a structured graph.
| System | Macro F1 | Tokens/query | Hallucination Rate |
|---|---|---|---|
| CKG | 0.471 | 269 | 0% |
| RAG | 0.123 | 2,982 | Variable |
| GraphRAG | 0.120 | 3,450 | Variable |
pip install ckg-mcp
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ckg": {
"command": "ckg-mcp"
}
}
}
| Tool | Description |
|---|---|
list_domains() | List all available CKG domains |
query_ckg(domain, concept, depth) | Extract subgraph — prerequisites + dependents |
get_prerequisites(domain, concept) | Full prerequisite chain to root |
search_concepts(domain, query) | Find concepts by name |
| Domain | Concepts |
|---|---|
| calculus | 105 |
| algebra-1 | 80 |
| chemistry | 95 |
| biology | 88 |
| linear-algebra | 72 |
| data-science-course | 91 |
| economics-course | 78 |
| glp1-obesity | 90 |
More domains available via Graphify.md — weekly-updated commercial CKGs for clinical, regulatory, legal, and financial domains.
# In your agent — via MCP tool call
query_ckg(domain="calculus", concept="Taylor Series", depth=3)
# Returns:
## CKG: Taylor Series (calculus)
### Prerequisites (what you need to know first)
- Power Series
- Sequences and Series
- Limits
- Derivatives
- Infinite Series
### Builds toward
- Maclaurin Series
- Error Estimation
RAG retrieves text chunks and forces the LLM to infer structure. On multi-hop structural queries (prerequisites, dependency chains, category aggregation), that inference fails — F1 = 0.123 vs CKG's 0.471.
CKG is a pre-compiled routing layer: the dependency paths are already in the graph. BFS/DFS traversal, not similarity search. No hallucinations by construction.
Full benchmark: github.com/Yarmoluk/ckg-benchmark
MIT — Yarmoluk & McCreary, 2026. Commercial deployment → graphifymd.com
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.