Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genpark-enterprise-knowledge-graph-provenance-tracer-skill trace claim 'Q3 revenue grew 12%' to sources and validate clearance boundaries"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🌐 GenPark MCP Hub • 📦 GenPark Official • 📖 Documentation
genpark-enterprise-knowledge-graph-provenance-tracer-skill provides industrial-grade capabilities engineered for next-generation Personal Multimodal Agents and Enterprise Workplace Execution. Built exclusively on the Python standard library with zero external runtime dependencies, it integrates seamlessly as a native Model Context Protocol (MCP) server or an importable Python module.
Enterprise Knowledge Graph Provenance & Anti-Hallucination Tracer (inspired by Tencent Docs, Meeting & Enterprise Knowledge Bases). Provides cryptographic chunk hashing, reverse claim-to-source attribution, clearance boundary validation, and provenance audit trails.
Zero-Dependency Architecture: Runs anywhere Python 3.9+ is installed without pip install overhead or supply-chain vulnerabilities.
Model Context Protocol (MCP) First: Fully compatible with Claude Desktop, Cursor, GenPark Engine, Meta Muse, Ray-Ban smart glasses, and enterprise agent runtimes.
Deterministic & Safe: Structured JSON schemas, cryptographic verification, rigorous boundary validation, and real-time telemetry.
High Concurrency & Low Latency: In-memory caching, vectorized math approximations, and robust fault-tolerant state handling.
Related MCP server: Mcp-Omega-Brain
from client import KnowledgeGraphProvenanceTracer
client = KnowledgeGraphProvenanceTracer()
result = client.trace_claim_provenance()
print(result)Run the MCP server via standard JSON-RPC 2.0 stdio:
python mcp_server.pyVerify standard compliance and self-tests:
python mcp_server.py --testAdd this tool to your claude_desktop_config.json or Cursor MCP settings:
{
"mcpServers": {
"genpark-enterprise-knowledge-graph-provenance-tracer-skill": {
"command": "python",
"args": ["/absolute/path/to/genpark-enterprise-knowledge-graph-provenance-tracer-skill/mcp_server.py"]
}
}
}Run the included verification suite:
python example_usage.pyThis project is licensed under the MIT License - see the LICENSE file for details.
Developed with ❤️ by the GenPark Autonomous Agent Ecosystem Team.
This server cannot be deployed
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
Machine-readable entity discovery with provenance, trust and verified source evidence.
Encrypted memory, knowledge graph and provable history for AI agents. ENYAL is the trust infrastructure for autonomous AI: identity, encrypted memory, and BSV-anchored proofs. Archived records are Merkle-batched and anchored to a permanent cryptographic ledger, and any record's inclusion proof can be checked by anyone, with no account.
Attestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts.
