HumanTool

io.github.rmtonmoyPublished by GitHub account rmtonmoyv0.2.0Updated Oct 24, 2026

Lets AI agents use a real human as a tool: visual checks, taste, phone calls, unblocking, approvals

The publisher's own server: TAP

VerifiedStreamable HTTPWeb executableProductivity & Workflow

Overview

AI-generated overview

Remote MCP endpoint that lets an AI agent hand tasks to a real human, such as visual checks, taste judgments, phone calls, unblocking and approvals.

What you can do
  • The manifest lists no individual tools, so capabilities come from the description only.
  • The assistant can delegate work that needs a person: visual checks and subjective taste judgments.
  • It can also route tasks such as phone calls, unblocking a stuck step, or getting an approval from a human.
  • Access is through a hosted remote endpoint rather than a local package.
When to use it
Worth adding when an agent hits something only a person can settle: judging how something looks or feels, making a call, or signing off on a step before it continues.
Requirements
A remote MCP endpoint at the provider's hosted address, reachable over the network. A bearer API key sent in the Authorization header; keys are issued per agent by the HumanTool operator, so you must request one from them.
Before you install
The service depends on real people doing the work, so expect latency and likely cost or quota terms from the operator; confirm pricing before relying on it. The API key in the Authorization header is a secret and should be scoped per agent and kept out of logs. Task details you send, including images or phone-call context, go to the operator and the humans handling them, so avoid confidential material.

Installation

In SourceWeft

  1. Open HumanTool in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. 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.rmtonmoy%2Fhumantool/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": {
    "humantool": {
      "type": "http",
      "url": "https://humantool.fly.dev/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v0.2.0LatestSep 30, 2026

Score

39% 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

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • 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 Human integrations

TAP

tech.humanOfficial publisher

TAP is a hosted remote MCP endpoint that isolates AI agents' credentials using placeholder secrets, policy checks and optional human approval.

Streamable HTTPWeb executableAuth
Developer ToolsCredential requiredOct 24, 2026

UGC, the Human Ad Network

africa.ugcOfficial publisher

Remote MCP endpoint for UGC, a "Human Ad Network", letting an assistant work with ad campaigns, clipping and Clip Studio from chat.

Streamable HTTPWeb executableAuth
Business & CommerceCredential requiredOct 24, 2026

Human Creative AI Workflow & Eval Lab

Published by GitHub account jdurey

Remote MCP server for multi-model AI workflow diagnostics, agent eval sandboxes, guardrail audits, judge rubric calibration and SOP-to-SCORM/QTI compilation.

Streamable HTTPWeb executable
Developer Tools5 toolsNov 14, 2026

A Human For Hire

com.ahumanforhire

Lets an assistant hire a real human: browse a paid task catalog, pay USDC on Solana via x402, post a task, and poll for replies.

STDIODesktop only
Finance6 toolsNov 14, 2026

HumanCalls

Published by GitHub account Hire-Overseas

Lets an assistant have a real person phone a US or Canadian business, then retrieve the call summary, answers, cost, recording and transcript.

Streamable HTTPWeb executableAuth
Productivity & WorkflowCredential requiredNov 12, 2026