needhuman-mcp: Instructions file for Codex

AGENTS.md

needhuman-mcp AGENTS.md is an instructions file for Codex, OpenCode from MariusAure/needhuman-mcp. It costs 601 tokens per session, scanned A, original, MIT.

Project instructions for NeedHuman, a service where an AI agent can ask a real person to complete a task and return proof. Examples include accepting terms, solving CAPTCHAs, identity checks and filling web forms.

In plain words
What is it for?
Submitting tasks to a human, checking their status and result, and listing tasks associated with the API key.
Why use it?
An AI agent may reach a step that requires human action or judgment. The service lets it pause that task, track the request and continue after the person responds.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is MariusAure/needhuman-mcp's own configuration. It tells Codex and OpenCode how to work on needhuman-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything needhuman-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MariusAure/needhuman-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MariusAure/needhuman-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/MariusAure/needhuman-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for needhuman-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mariusaure/needhuman-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/mariusaure/needhuman-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mariusaure/needhuman-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mariusaure/needhuman-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for needhuman-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mariusaure/needhuman-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mariusaure/needhuman-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 601 This file is loaded in full into every session.
When invoked 601 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00601 $0.00601
Opus 5.5 $0.00240 $0.00240
Sonnet 5.5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 2mo ago against content hash d0c169d96bb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

needhuman-mcp AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://needhuman.ai/api/v1/keys/register \
AGENTS.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository contains the MCP server for NeedHuman — a Human-as-a-Service API for AI agents.

What this does

When your agent hits a step requiring a real human (accept ToS, create accounts, CAPTCHA, identity verification, web forms), it calls need_human. A human completes the task and returns proof. The agent continues.

Quick start

Remote (no install needed)

Connect to https://needhuman.ai/mcp using streamable HTTP transport. Pass your API key as a Bearer token in the Authorization header.

Local (stdio)

npx -y @needhuman/mcp-server

Env vars:

  • NEEDHUMAN_API_KEY — your API key (required)
  • NEEDHUMAN_API_URL — defaults to https://needhuman.ai

Get an API key (3 free tasks, no signup)

curl -X POST https://needhuman.ai/api/v1/keys/register \
  -H "Content-Type: application/json" \
  -d '{"name": "my-agent"}'

Tools

  • need_human — submit a task for a human. Returns task ID. Pass demo: true for an instant synthetic response (no credits used).
  • check_task_status — poll by task ID. Returns status, result, proof.
  • list_tasks — list all tasks for the current API key.

File structure

mcp-server.ts    — MCP server source (stdio transport, 3 tools, ~280 lines)
package.json     — npm package config (@needhuman/mcp-server)
smithery.yaml    — Smithery directory config
server.json      — Official MCP Registry config
glama.json       — Glama directory config

Build and test

npm install
npm run build        # compiles to dist/
npm run dev          # runs with tsx

Test locally:

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | NEEDHUMAN_API_KEY=test npx tsx mcp-server.ts

Constraints

  • Do not include passwords, API keys, card numbers, or secrets in task descriptions.
  • Poll check_task_status no more than once per 30 seconds.
  • Typical task completion: 2-30 minutes during CET business hours.
  • 3 free tasks per API key. Pre-v1.0 — API stable but may change.

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 74 lines · 601 tokens per session scan A d0c169d96bb9

Subscribe to this mod's changes

needhuman-mcp AGENTS.md is an instructions file published in the GitHub repository MariusAure/needhuman-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 601 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

needhuman-mcp AGENTS.md compared with instructions from other repositories

needhuman-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
needhuman-mcp AGENTS.mdMariusAure/needhuman-mcpInstructions file17mo agoMITA601Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot