Security & governancePublic source

Governance Policy MCP Server

Policy evaluation, approvals, simulation, and audit evidence for ADK-Rust Enterprise. The gatekeeper that should not be bypassable by downstream MCPs.

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Provides governance capabilities through a typed MCP contract.

Provides policy capabilities through a typed MCP contract.

Architecture

How Governance Policy MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

Governance Policy MCP Server

Validates the request and owns 8 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · streamable HTTP · Server framework: ADK MCP SDK + rmcp

Governance Policy MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask Governance Policy MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

8 named tools

evaluate_policy

Evaluate policy — decide allow, block, review, or pause

read only

open_approval

Open a HITL approval task

internal write

list_approvals

Show pending approvals by owner/risk/domain

read only

resolve_approval

Approve, reject, or request changes

internal write

simulate_policy

Test policy changes against fixtures or history

read only

audit_log

Read recent allow/block/review outcomes

read only

request_exception

Request time-bound policy exception

internal write

export_evidence

Export governance evidence for compliance

read only

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

5 read only3 internal write

The registry manifest declares read only, internal write tool risk classes.

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

Prompts

ADK MCP SDKrmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-governance-policy

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-governance-policy",
    ["mcp-governance-policy"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.