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
LangChain
First-party BaseCallbackHandler. Every tool call, LLM call, and chain step is attested.
OpenAI Agents SDK
Native MCP server via MCPServerStdio. All 47 Attestix tools discovered automatically.
CrewAI
MCPServerAdapter per agent. Crew-wide compliance profile and UCAN hand-offs.
Example integrations via MCP
Any MCP client can consume Attestix. The following ship with reference configs as example integrations, not production-certified:
- Dify /
mcp_serversin the workflow config - Google ADK /
McpClienttool 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 8501Then connect any MCP client to http://localhost:8501/mcp.
Next
- MCP tool reference / full 47-tool catalogue
- Offline verify walkthrough / how regulators verify a VC
- Base L2 testnet anchor walkthrough / put artefact hashes on chain
Reputation Scoring Guide
Build trust between AI agents using Attestix's recency-weighted reputation system with interaction tracking, category breakdowns, and threshold-based queries.
LangChain Integration
Drop Attestix into a LangChain agent with the BaseCallbackHandler. Production-ready in v0.3.0. Every tool call, LLM call, and chain step gets hash-chained and signed.