agentfabric.dev
MCP server live AI agents connect in one line →

Human-in-the-loop for AI agents

Send agent output to humans. Get approval, feedback, and an audit trail.

agentfabric.dev is the review and approval layer for AI agents. Route generated URLs, images, and documents to human reviewers, enforce approval policies, and keep a complete record of who signed off — over MCP or REST.

Agents self-signup. Call create_tenant or POST /v1/signup to get API keys instantly — no human account creation or setup required.

Connect your agent Read the docs

No credit card required.

Loading…

For AI agents

Built for agents first

agentfabric.dev exposes a native Model Context Protocol server, so any MCP-compatible agent gets human review as a set of tools — no glue code, and no human needed to sign up.

MCP endpoint https://mcp.agentfabric.dev

Add this server to Cursor, Claude, or any MCP client. The agent calls create_tenant to self-signup (no human required), then opens review requests, polls for decisions, and reads reviewer comments.

create_tenant create_review_request get_review_request list_review_requests get_review_comments add_reviewer remind_reviewers cancel_review_request
  1. 1

    Add the MCP server

    Drop the endpoint into your MCP client config. No SDK, no build step.

  2. 2

    Call create_tenant

    The agent self-signs up and gets admin and consumer API keys back automatically — no human onboarding step.

  3. 3

    Request human review

    Send content with create_review_request, then poll get_review_request for the verdict.

Agents sign themselves up

Call create_tenant over MCP or POST /v1/signup over REST. API keys return instantly — no human setup.

Transparent audit trail

Every comment, approval, and rejection is recorded per reviewer — accountable, traceable decisions for autonomous systems.

Policies you control

All must approve, any approval, quorum, or first rejection wins — at the request level or per item.

FAQ

Questions agents and builders ask

What is agentfabric.dev?

A human-in-the-loop review and approval layer for AI agents. Agents send generated content — URLs, images, PDFs, or documents — to human reviewers who approve, reject, or comment. Every decision lands in an audit trail.

How does an AI agent connect?

The fastest path is MCP. Point any MCP-compatible client at the agentfabric.dev MCP server and the agent gets tools to create a tenant, open review requests, poll results, and read comments. A REST API is available for backend services.

Do agents need a human to sign up?

No. Agents create their own tenant and receive API keys by calling create_tenant (MCP) or POST /v1/signup (REST). No dashboard login, email verification, or human setup is required. Humans only enter the loop when you send content for review.

Do human reviewers need an account?

No. Reviewers get an email with a personal, scoped link. They comment, approve, or reject in the browser — no signup.

What approval policies are supported?

ALL_APPROVE, ANY_APPROVE, ANY_REJECT, and QUORUM. Decisions can be scoped to the whole request or to individual items.

Ready to ship with oversight?

Agents self-signup in one MCP call. Humans only review the content you send them — not your onboarding. No credit card required.

Connect your agent Sign up