Connects Claude to the HREVN trust layer at api.hrevn.com for running compliance and integrity checks on AI workflows. Exposes four tools: baseline_check for pre-flight diagnostics, profile_validate for testing compliance profiles, generate_bundle for packaging audit trails, and verify_bundle for cryptographic verification. Every result includes risk_flags and remedy_payload fields. Runs over stdio and requires an HREVN API key. Useful when you need structured proof that an agent's behavior meets EU AI Act readiness profiles or other verifiable compliance baselines before committing to production workflows.
Minimal stdio MCP server for HREVN, backed by the live managed runtime at
https://api.hrevn.com.
This repo exposes HREVN as real MCP tools instead of ad hoc helper scripts. It stays intentionally thin:
risk_flags, remedy_payload, and check_idbaseline_checkprofile_validategenerate_bundleverify_bundleexport HREVN_API_BASE_URL="https://api.hrevn.com"
export HREVN_API_KEY="replace-with-issued-alpha-key"
Optional environment variables:
HREVN_MCP_TIMEOUT_SECONDSHREVN_MCP_SERVER_NAMEHREVN_MCP_SERVER_VERSIONcd hrevn-mcp-server
python3 -m pip install -e .
python3 -m pip install hrevn-mcp-server
The console entry point is:
hrevn-mcp-server
hrevn-mcp-server
The server uses MCP stdio transport.
hrevn-mcp-server --version
hrevn-mcp-server --list-tools
hrevn-mcp-server --self-test
If you are running directly from source without an installed entry point:
PYTHONPATH=src python3 -m hrevn_mcp_server.server --list-tools
PYTHONPATH=src python3 -m hrevn_mcp_server.server --self-test
The self-test runs a live baseline_check against the configured HREVN
managed API.
baseline_checkMinimal payload:
{
"task_type": "ai_workflow",
"profile": "eu_readiness_profile",
"record": {
"agent_name": "example_agent",
"summary": "baseline smoke test"
},
"metadata": {
"surface": "mcp",
"stage": "pre_completion"
}
}
profile_validateMinimal payload:
{
"profile": "eu_readiness_profile",
"record": {},
"metadata": {}
}
generate_bundleMinimal payload:
{
"record": {},
"traces": [],
"options": {
"include_report_pdf": false
}
}
verify_bundleMinimal payload:
{
"source": "/path/to/bundle-or-artifact"
}
Use a local stdio configuration like this:
{
"mcpServers": {
"hrevn": {
"command": "python3",
"args": [
"-m",
"hrevn_mcp_server.server"
],
"env": {
"PYTHONPATH": "/ABSOLUTE/PATH/TO/hrevn-mcp-server/src",
"HREVN_API_BASE_URL": "https://api.hrevn.com",
"HREVN_API_KEY": "YOUR_HREVN_API_KEY"
}
}
}
}
See also:
HREVN can already be explored experimentally in Google Antigravity through custom MCP configuration.
What is already validated:
https://api.hrevn.combaseline_check returns real structured resultsWhat is not claimed yet:
This repo includes:
as a machine-readable manifest describing the MCP server, package, transport, and repository metadata.
This server must not reimplement HREVN truth locally. It should expose stable MCP tools that call the managed API.
makafeli/n8n-workflow-builder
danishashko/make-mcp
lukisch/n8n-manager-mcp
io.github.us-all/airflow
io.github.infoinlet-marketplace/mcp-workflow