Gatewerk MCP server

Gatewerk

The open source review layer for AI agents.

One inbox where your agents' actions stop and wait for a person.

Review the exact payload, edit it, decide. Every decision on the record.

Your AI agent drafts an email, generates a report, or initiates a transaction. Before it reaches the real world, a human reviews it in a structured form, edits what needs fixing, and sends the decision back. The agent learns from what humans changed.

Works with any agent framework. Self hosted. Open source (AGPL-3.0; client SDKs are Apache-2.0). See LICENSING.md.

Why Gatewerk?

Your agents act for you: they send the proposals, run the campaigns, handle the invoices, write the replies. Before an action leaves the building, a human should decide. Gatewerk is the review layer between your agents and the real world. Human judgment enters the pipeline, exactly where you choose.

• Structured review forms: not just "approve/deny", but rich templates with editable fields.
• Feedback memory: agents query past decisions to improve over time
• Self hosted: your server, your data, no SaaS dependency
• Protocol first: works with any agent framework via REST API, TypeScript/Python SDKs, or MCP

Use Cases

Before Sending

Email drafts, customer support replies, Slack messages, SMS campaigns, outreach to candidates, proposals to clients

Before Executing

Code deployments, database migrations, financial transactions, infrastructure changes, API calls to third-party services

Before Publishing

Blog posts, social media content, ad campaigns, product listings, documentation updates, press releases, reports

Before Approving

Expense reports, refund requests, access permissions, contract terms, insurance claims, purchase orders

Between the gates, agents can also bring you the judgment calls: classify the edge case, pick the path, resolve the exception. Gatewerk makes human judgment callable: agents ask a structured question, you answer typed, and the pipeline continues.

How It Works

sequenceDiagram
    participant Agent
    participant API as Gatewerk API
    participant Reviewer as Reviewer Dashboard
    participant Webhook as Agent via webhook

    Agent->>API: POST /reviews (template + payload)
    API->>Reviewer: Review appears in inbox
    Reviewer->>API: Approve / Reject / Edit
    API->>Webhook: Decision + edited payload
    Webhook->>Agent: Deliver decision
    Agent->>API: GET /feedback (learn from past decisions)

Works With Any Agent Framework

Gatewerk is protocol-first, not framework-specific. Your agent framework already has a way to make HTTP calls or use MCP: that's all you need.

A review, not a yes/no ping

Without a review layer, every agent grows its own approval hack: a Slack button here, a weekend dashboard there, a shared sheet nobody audits. You end up building the same thing over and over, once per workflow. Gatewerk is that layer built once, properly:

Shortened. The full README is on GitHub.