AgentFabric — Human-in-the-Loop Review & Approval

io.github.enzoduitPublished by GitHub account enzoduitv1.0.0Updated Oct 24, 2026

Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.

The publisher's own server: Approval Studio

VerifiedStreamable HTTPWeb executableProductivity & WorkflowSecurity & Monitoring

Overview

AI-generated overview

Lets an assistant route agent actions through human review and approval, with an audit trail and approval policies.

What you can do
AgentFabric provides human-in-the-loop review and approval for AI agents. It is described as offering an audit trail and approval policies, and as being native to MCP. It is a remote MCP endpoint, so an assistant connects to it rather than running it locally.
When to use it
Worth considering when an assistant takes actions that should be checked by a person before they go through, or when you need a record of what was approved and by whom. Useful for teams that want policy-based sign-off around agent activity.
Requirements
A remote MCP endpoint at over streamable HTTP. No packages, environment variables, or headers are declared, and no authentication is declared in the manifest.
Before you install
The manifest declares no authentication, so it is unclear how access to the endpoint is controlled or who can see approval data. Review and approval flows may involve sending agent action details to a third-party service. Confirm how approvals are enforced and what data leaves your environment before relying on it.

Installation

In SourceWeft

  1. Open AgentFabric — Human-in-the-Loop Review & Approval in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.enzoduit%2Fagentfabric/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentfabric-human-in-the-loop-review-app": {
      "type": "http",
      "url": "https://mcp.agentfabric.dev/"
    }
  }
}

Tools

1

create_tenant

Create a new agentfabric.dev tenant and receive admin and consumer API keys. No authentication required. Save both keys from the response for later tool calls.

ParameterspasswordrequiredownerNameownerEmailrequiredtenantNamerequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Approval integrations