Gia MCP Server

Enterprise AI governance: audit trails, compliance, human-in-the-loop gates for Claude.

Remote serverstreamable-http

What is the Gia MCP server?

Gia MCP server exists for a simple reason — assistants are far more useful when they can act on Gia directly instead of describing what you should do. Enterprise AI governance: audit trails, compliance, human-in-the-loop gates for Claude.

What you get

A key is only for Option 2, the hosted endpoint, where the ledger, gates, and knowledge packs are shared infrastructure rather than local state. → Starter key at gia.aceadvising.com/get-api-key — email in, key out, under 2 minutes, no credit card. Starter tier is 30 req/min and 1,000 tool calls/day.

What the assistant can call

Once Gia is connected, these are the calls the assistant has available:

  • classify_decision — Classify any AI agent decision using the MAI Framework. decision and domain are both required; the impact flags default to false
  • request_context — Governed Context Authority. Agents declare what context they need. GIA decides what to serve based on role, scope, and contract
  • score_governance — Score any agent output on three dimensions. operation is required — the score is recorded against a named operation, not scored in the abstract
  • evaluate_threshold — The Storey Threshold measures governance health by tracking MANDATORY escalation rate

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration and credentials

You will need 2 environment variables: DATABASE_URL, GIA_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Gia's toolset — classify_decision, request_context, score_governance and 1 more — is a fair guide to whether it matches your workflow. It is maintained by knowledgepa3; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the gia mcp server does with a few real requests.

Available tools

ToolWhat it does
classify_decisionClassify any AI agent decision using the MAI Framework. decision and domain are both required; the impact flags default to false.
request_contextGoverned Context Authority. Agents declare what context they need. GIA decides what to serve based on role, scope, and contract.
score_governanceScore any agent output on three dimensions. operation is required — the score is recorded against a named operation, not scored in the abstract.
evaluate_thresholdThe Storey Threshold measures governance health by tracking MANDATORY escalation rate.

How to install the Gia MCP server

{
  "mcpServers": {
    "gia": {
      "command": "npx",
      "args": ["gia-mcp-server"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
DATABASE_URLEndpoint or connection string the server talks to.Yes
GIA_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Gia to classify decision.
  • Use Gia to request context.
  • Use Gia to score governance.

Frequently asked questions

It connects Gia to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (classify_decision, request_context, score_governance, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Gia directly.