Novel governance solutions the world needs now.

For AI agents

Connect your agent

Read first: llms.txt and machine-interface.json list the CLI, inputs, outputs, profiles, and raw schema URLs.

Use it in your agent in 5 minutes with AI Governance MCP, the AI Governance Model Context Protocol Server. Model Context Protocol (MCP) is an open standard that lets AI assistants call external tools. It is read-only and has three tools: check_inventory, build_decision_pack, and validate_passport.

git clone https://github.com/GLOBAL-AI-GOVERNANCE/ai-governance-mcp && cd ai-governance-mcp
python3 -m venv .venv && . .venv/bin/activate && pip install -e .
./scripts/fetch_upstreams.sh
gag-mcp                      # stdio (Claude Desktop and other local clients)
gag-mcp --http --port 8000   # Streamable HTTP at /mcp

Claude Desktop (local): add "gag": {"command": "/ABS/PATH/ai-governance-mcp/.venv/bin/gag-mcp"} under mcpServers.
Anthropic API: {"type": "url", "name": "gag", "url": "https://YOUR-HOST/mcp", "authorization_token": "TOKEN"}.
OpenAI API: tool {"type": "mcp", "server_label": "gag", "server_url": "https://YOUR-HOST/mcp", "headers": {"Authorization": "Bearer TOKEN"}}.
xAI API: tool {"type": "mcp", "server_label": "gag", "server_url": "https://YOUR-HOST/mcp", "headers": {"Authorization": "Bearer TOKEN"}}.

Remote use needs an HTTPS endpoint you host yourself; Global AI Governance operates no hosted endpoint. Any network-reachable server must set GAG_MCP_ALLOWED_HOSTS and GAG_MCP_BEARER_TOKEN (32+ characters); without them it refuses to start. Consumer connector UIs that cannot send a static bearer token (ChatGPT on the web today; Claude.ai outside its request-headers beta) cannot connect. These remote recipes have not been tested against a live provider; see the repository README. The command and Python package keep the names gag-mcp and gag_mcp.

Where your data goes: the browser Toolkit processes files only in this browser. Through MCP, the inventory or passport you pass becomes part of your AI client's conversation, so a hosted assistant sends it to its provider, and a remote server you host receives it over HTTPS. validate_passport checks a passport document; it does not monitor, enforce, or revoke anything at runtime.

For labs and teams

Run a pilot

One authorized AI system inventory, one accountable owner, one Decision Pack, and one documented decision boundary. Pilots can cover agent authority and passports, vulnerability closure evidence, cyber-resilience boundaries, or wiring AI Governance MCP into an internal agent platform.

Contact: start with the Pilots and integrations: start here thread, or open a new thread in GitHub Discussions, with your use case. Do not post confidential, personal, or regulated information.

Specifications

Read the spec

• Global AI Assurance Envelope: the portfolio-level, reference-only interoperability object.
• Toolkit machine interface and v2.3.0 contracts.
• Agentic AI Governance v0.1.0-alpha.2 schemas: agent authority, passport, expiry, and revocation.

Product map

What exists today