Security & governancePublic source

Approval MCP Server

A multi-stage approval workflow engine for ADK-Rust Enterprise legal and media-content agents. 17 MCP tools: configurable workflow templates, stage rules (all-of / any-of / quorum), decisions with delegation and…

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 approval capabilities through a typed MCP contract.

Architecture

How Approval 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.

→

Approval MCP Server

Validates the request and owns 17 documented tool contracts.

→

Domain system

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

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

Approval MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask Approval 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.

17 named tools

list_workflows

List workflow templates, optionally by domain

read only

get_workflow

Get a workflow template's stage definitions

read only

create_workflow

Create a custom workflow template (ordered stages with rules and approvers)

internal write

create_request

Create an approval request bound to a workflow (optionally submit immediately)

internal write

get_request

Get an approval request's full detail including stages, votes, and audit trail

read only

search_requests

Search/filter approval requests by text, domain, type, status, or approver

read only

submit_request

Submit a draft request for review (activates the first stage)

internal write

decide

Record an approver's decision on the active stage and evaluate the stage rule

internal write

my_queue

List requests awaiting a given approver's decision

read only

cancel_request

Cancel/withdraw a request with a reason

internal write

escalate

Reassign the active stage to new approvers (escalation)

internal write

delegate

Delegate approval authority from one approver to another for a request

internal write

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.

10 internal write7 read only

Gated writes — decide, cancel_request, escalate, and delegate require approval in production (requires_approval); reads are read_only.
Defensible audit — every state change is recorded immutably with actor and timestamp.
No raw documents — items under approval and attachments are opaque references/URIs, never embedded content.
Integration scaffold — the in-memory store is for development; back it with a durable store and bind approver/actor to authenticated identities in production.

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.

The current README concentrates on its tool surface. Check the source and release notes before relying on optional MCP capabilities beyond tool discovery and invocation.

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-approval

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-approval",
    ["mcp-approval"],
).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.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Architecture ↗docs/architecture.svg Issues and support ↗github.com issues

Keep exploring