Skip to main content
Attestix
Guides

Integration Guide

How to use Attestix with LangChain, OpenAI Agents SDK, CrewAI, plain Python, and other MCP clients.

Attestix integrates with three agent frameworks as production-ready shipments in v0.3.0, and with any MCP-compatible client through the generic MCP server.

Production integrations

Example integrations via MCP

Any MCP client can consume Attestix. The following ship with reference configs as example integrations, not production-certified:

  • Dify / mcp_servers in the workflow config
  • Google ADK / McpClient tool registration
  • Microsoft Semantic Kernel / MCP plugin layer
  • Strands / MCP runtime binding
  • Claude Desktop, Cursor, Continue, Windsurf, VS Code

As a plain Python library

You can import Attestix services directly without running the MCP server.

from services.identity_service import IdentityService
from services.credential_service import CredentialService
from services.compliance_service import ComplianceService
from services.provenance_service import ProvenanceService

identity_svc = IdentityService()
credential_svc = CredentialService()
compliance_svc = ComplianceService()
provenance_svc = ProvenanceService()

agent = identity_svc.create_identity(
    display_name="quarterly-analyst-v2",
    source_protocol="manual",
    capabilities=["data_analysis", "reporting"],
    issuer_name="VibeTensor",
    expiry_days=365,
)

All services share the same Ed25519 signing key (auto-generated on first use) and the same JSON storage files.

As an MCP server (stdio)

{
  "mcpServers": {
    "attestix": {
      "command": "attestix",
      "args": ["mcp"]
    }
  }
}

As an MCP server (HTTP)

attestix mcp --transport http --port 8501

Then connect any MCP client to http://localhost:8501/mcp.

Next