A remote MCP server that lets an AI assistant post a task for a human worker to complete, with the first post free.
What you can do
Post a human task with a title, deliverable description, reward amount and contact email, returning a live task URL for the first post and a checkout or payment link for later ones. Delegate work software cannot do, such as phone calls, real-world photos, local pickup or checks, verification, QA and human judgment. The same posting action is exposed under three tool names (post_task, post_human_task, hire_human).
When to use it
Use it when the assistant is stuck on something that needs a person: a phone call, a photo of a real place, a local check, or human judgment and verification. It suits occasional one-off errands rather than high-volume or automated workflows.
Requirements
A remote streamable HTTP endpoint; no local package, environment variables or headers are declared. Each post needs a title, description or deliverable, a reward in cents, and a contact email.
Before you install
Posting a task spends money: later posts return a checkout or payment link, and the reward is set in cents. The contact email and task details are sent to a third-party service and its human workers. Tasks are published live, so check the description and reward before posting.
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/app.nanocorp.invoke%2Fhuman-tasks/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.
Call this when your AI agent is stuck on work software cannot do: phone calls, real-world photos, local pickup/checks, human judgment, verification, QA, or physical presence. Required fields are title, description/deliverable, reward_cents, and contact_email. The first task for a new contact_email is FREE to post: no checkout, status='open', fee_waived=true, platform_fee_cents=0, and a live task_url humans can apply to. Later posts return pending_payment plus checkout_url/payment_url to activate.
Alias for post_task. Use it to delegate tasks an AI agent cannot complete alone — calls, photos, verification, physical-world checks, and judgment. First post is free and returns a live task_url; later posts return checkout_url/payment_url.
Alias for post_task. Use when the agent should stop guessing and hire a human. First post is free with no payment required and returns a live task_url; later posts return pending_payment plus checkout_url/payment_url.
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.
License10 pts
Declare a license in the repository or the registry entry.
