Is io.github.Yarmoluk/ckg-mcp safe to use?

io.github.Yarmoluk/ckg-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.Yarmoluk/ckg-mcp?

io.github.Yarmoluk/ckg-mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.Yarmoluk/ckg-mcp do?

io.github.Yarmoluk/ckg-mcp provides 4 tools: list_domains, query_ckg, get_prerequisites, search_concepts. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.Yarmoluk/ckg-mcp?

io.github.Yarmoluk/ckg-mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.

Is io.github.Yarmoluk/ckg-mcp actively maintained?

io.github.Yarmoluk/ckg-mcp is actively maintained — last commit was 7 days ago. It has 3 GitHub stars.

io.github.Yarmoluk/ckg-mcp

ckg-mcp

Structured domain knowledge for AI agents. 42x more accurate than RAG, 11x fewer tokens.

3 4 tools GitHub PyPI

No known CVEs

No license

Actively maintained

Last commit 7d ago

Works with most clients

Transport: stdio, http

4 tools · ~321 tok

Grade A · 0.2% of 200K ctx

Edit this pageView history

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ckg": {
      "command": "ckg-mcp"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-yarmoluk-ckg-mcp)](https://mcppedia.org/s/io-github-yarmoluk-ckg-mcp)

Read me

What io.github.Yarmoluk/ckg-mcp does

Compact Knowledge Graph MCP server. Pre-structured domain knowledge as a routing layer for agent stacks — 42× more efficient than RAG on structural queries.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

uvx 'ckg-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

87/100across 5 weighted dimensions

How we score →

0255075100

−13

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked ckg-mcp against OSV.dev.

Inventory

Tools (4)

Click any tool to inspect its schema.

~321 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.Yarmoluk/ckg-mcp safe to use?: io.github.Yarmoluk/ckg-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.Yarmoluk/ckg-mcp?: io.github.Yarmoluk/ckg-mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.Yarmoluk/ckg-mcp do?: io.github.Yarmoluk/ckg-mcp provides 4 tools: list_domains, query_ckg, get_prerequisites, search_concepts. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.Yarmoluk/ckg-mcp?: io.github.Yarmoluk/ckg-mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is io.github.Yarmoluk/ckg-mcp actively maintained?: io.github.Yarmoluk/ckg-mcp is actively maintained — last commit was 7 days ago. It has 3 GitHub stars.

Similar servers

Others in ai-ml

View all →

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

87.8k 1

Memory MCP Server96

Persistent memory using a knowledge graph

87.8k 5

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

18.3k 6

Gemini Cli95

An open-source AI agent that brings the power of Gemini directly into your terminal.

105.6k 8

MCP Security Weekly

Get CVE alerts and security updates for io.github.Yarmoluk/ckg-mcp and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ckg": {
      "command": "ckg-mcp"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-yarmoluk-ckg-mcp)](https://mcppedia.org/s/io-github-yarmoluk-ckg-mcp)

Read me

What io.github.Yarmoluk/ckg-mcp does

Compact Knowledge Graph MCP server. Pre-structured domain knowledge as a routing layer for agent stacks — 42× more efficient than RAG on structural queries.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

uvx 'ckg-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

README

ckg-mcp

Give your agent the structure, not the search.

ckg-mcp serves Compressed Knowledge Graphs to any LLM via MCP — pre-structured, typed dependency graphs your agent traverses instead of text chunks it guesses from.

4× the F1 of RAG · 11× fewer tokens · works with Claude, GPT-4o, Gemini, Llama, Mistral, and any MCP client

Measured on the open CKG Benchmark — 45 domains, 7,928 queries. Re-run it yourself.

Quickstart — 30 seconds

pip install ckg-mcp        # Python ≥ 3.10
# or zero-install:  uvx ckg-mcp

Pick your client:

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "ckg": { "command": "ckg-mcp" }
  }
}

Claude Code (CLI)

claude mcp add ckg -- ckg-mcp

Cursor · Cline · Windsurf · any MCP client

{
  "mcpServers": {
    "ckg": { "command": "ckg-mcp" }
  }
}

Or with uvx (no global install):

{
  "mcpServers": {
    "ckg": { "command": "uvx", "args": ["ckg-mcp"] }
  }
}

LangChain / LangGraph / smolagents (Python)

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "ckg": {"command": "ckg-mcp", "transport": "stdio"}
})
tools = await client.get_tools()

OpenAI SDK

import subprocess, json
proc = subprocess.Popen(["ckg-mcp"], stdin=subprocess.PIPE, stdout=subprocess.PIPE)
# Use any MCP-over-stdio adapter — e.g. mcp-client-python or openai-agents-mcp

Restart your client, then try:

list_domains()
get_prerequisites(domain="calculus", concept="Taylor Series")
query_ckg(domain="nvidia-gpu-inference", concept="FlashAttention-3", depth=3)

What you get

6 tools. No database. No embeddings. No API key.

Tool	What it does
`list_domains()`	List all available domains. Call this first.
`query_ckg(domain, concept, depth=3)`	Dependency subgraph around a concept — prerequisites + dependents up to N hops
`get_prerequisites(domain, concept)`	Full prerequisite chain — every concept to understand first, in order
`search_concepts(domain, query)`	Find concepts by name (partial match, case-insensitive)
`list_agent_blueprints()`	List pre-built agent configs for specific use cases
`get_agent_blueprint(use_case)`	Full blueprint: domains, constraints, workflow, prompt template, LangGraph hint

Example session

list_domains()
→ Available domains (62 free / 85 total): algebra-1, agent-reliability, calculus,
  context-as-a-service, databricks-unity, glp1-obesity, hipaa-compliance,
  nvidia-gpu-inference, payer-formulary, snowflake-horizon, ...

get_prerequisites(domain="calculus", concept="Taylor Series")
→ Prerequisite chain for 'Taylor Series' in calculus (20 concepts):
  Function → Limit → Derivative → ... → Power Series → Taylor Series

query_ckg(domain="nvidia-gpu-inference", concept="KV Cache", depth=3)
→ ## CKG: KV Cache (nvidia-gpu-inference)
  ### Prer

... [View full README on GitHub](https://github.com/Yarmoluk/ckg-mcp#readme)

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

87/100across 5 weighted dimensions

How we score →

0255075100

−13

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked ckg-mcp against OSV.dev.

Inventory

Tools (4)

Click any tool to inspect its schema.

~321 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.Yarmoluk/ckg-mcp safe to use?: io.github.Yarmoluk/ckg-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.Yarmoluk/ckg-mcp?: io.github.Yarmoluk/ckg-mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.Yarmoluk/ckg-mcp do?: io.github.Yarmoluk/ckg-mcp provides 4 tools: list_domains, query_ckg, get_prerequisites, search_concepts. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.Yarmoluk/ckg-mcp?: io.github.Yarmoluk/ckg-mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is io.github.Yarmoluk/ckg-mcp actively maintained?: io.github.Yarmoluk/ckg-mcp is actively maintained — last commit was 7 days ago. It has 3 GitHub stars.