Hrevn MCP server

HREVN MCP Server

<!-- mcp-name: io.github.ai-human-andalusia/hrevn-mcp-server -->

Minimal stdio MCP server for HREVN, backed by the live managed runtime at https://api.hrevn.com.

Why this exists

This repo exposes HREVN as real MCP tools instead of ad hoc helper scripts. It stays intentionally thin:

riskflags, remedypayload, and check_id

• canonical semantics remain in the HREVN managed runtime
• the MCP layer only exposes stable tool contracts
• consequential results come back as structured output, including

Included tools

• baseline_check
• profile_validate
• generate_bundle
• verify_bundle

Environment

export HREVN_API_BASE_URL="https://api.hrevn.com"
export HREVN_API_KEY="replace-with-issued-alpha-key"

Optional environment variables:

• HREVNMCPTIMEOUT_SECONDS
• HREVNMCPSERVER_NAME
• HREVNMCPSERVER_VERSION

Install

Editable install

cd hrevn-mcp-server
python3 -m pip install -e .

From PyPI

python3 -m pip install hrevn-mcp-server

The console entry point is:

hrevn-mcp-server

Run

hrevn-mcp-server

The server uses MCP stdio transport.

Verify before using a client

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.

Tool contracts

baseline_check

Minimal 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_validate

Minimal payload:

{
  "profile": "eu_readiness_profile",
  "record": {},
  "metadata": {}
}

generate_bundle

Minimal payload:

{
  "record": {},
  "traces": [],
  "options": {
    "include_report_pdf": false
  }
}

verify_bundle

Minimal payload:

{
  "source": "/path/to/bundle-or-artifact"
}

Example MCP config

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:

• Antigravity setup guide
• Conservative experiment guide
• Antigravity MCP config example
• Antigravity baseline payload

Antigravity status

HREVN can already be explored experimentally in Google Antigravity through custom MCP configuration.

What is already validated:

• the HREVN MCP server runs locally
• the server exposes real tools backed by https://api.hrevn.com
• baseline_check returns real structured results
• Antigravity preview builds expose MCP configuration surfaces in the UI

What is not claimed yet:

• official native Antigravity integration
• guaranteed MCP tool injection into every Antigravity agent instance
• Antigravity-specific guardrail hooks beyond what has been directly observed

Registry metadata

This repo includes:

• server.json

as a machine-readable manifest describing the MCP server, package, transport, and repository metadata.

Design rule

This server must not reimplement HREVN truth locally. It should expose stable MCP tools that call the managed API.