Back to search
30
MCP

ckg-mcp

pypi/ckg-mcp

Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.

Uptime
0.0%
48 probes
Response
0ms
last probe
Tools
0
callable
Primary URL
—

Similar MCP servers embedding-nearest

CKG-MCP — Compressed Knowledge Graphs
Compressed Knowledge Graphs over MCP — 97 domains, 4× F1 vs RAG at 11× fewer tokens.
0 tools
io.github.Yarmoluk/ckg-mcp
Structured domain knowledge for AI agents. 42x more accurate than RAG, 11x fewer tokens.
0 tools
io.github.pmgarg/cgraphy
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
0 tools
io.github.arrayo/smart-context-mcp
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
0 tools
io.github.nitishgourishetty/contextual-mcp-server
RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.
0 tools
io.github.Arrayo/smart-context-mcp
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
0 tools

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "ckg-mcp": {
      "url": "None",
      "transport": "http"
    }
  }
}