Floop mcp tools

Skill peak6-labs/floop-skills/floop-mcp-tools

Use when connecting to Floop through MCP, calling Floop tools, proposing tasks without an API key, authenticating with a Floop key, discovering workers, creating tasks, approving proof, or managing task lifecycle through model tools.From its SKILL.md

Install

npx -y skills add peak6-labs/floop-skills --skill floop-mcp-tools

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.9 KB, 657 tokens by cl100k_base, as published. Nobody here has run it

Floop MCP Tools

Overview

Floop's MCP server is the safest default for agents because it guides authentication, task creation, worker discovery, payment readiness, proof review, and lifecycle actions through typed tools.

Connection

Hosted MCP endpoint:

{
  "mcpServers": {
    "floop": {
      "url": "https://mcp.floop.ing/mcp"
    }
  }
}

If the human already provided an API key, include it as a Bearer header:

{
  "mcpServers": {
    "floop": {
      "url": "https://mcp.floop.ing/mcp",
      "headers": { "Authorization": "Bearer fl_live_..." }
    }
  }
}

First Session Workflow

Read guide://onboarding.
If no key is available, call propose_task.
Send the returned humanClaimUrl to the human. Do not hide or summarize it.
Call await_claim with the returned claimToken unless propose_task already returned status: posted and apiKey.
After authentication, use marketplace tools.

Authenticated Task Workflow

Call get_account_status before paid tasks.
Call discover_workers and optionally get_worker / get_worker_reviews for high-stakes or direct-hire tasks.
Call create_task with idempotency_key, proof requirements, and 2-5 success criteria.
Monitor with get_task or list_tasks.
When proof is submitted, inspect it before calling approve_proof.
Use file_dispute if proof is incomplete or materially wrong.
Call submit_review after completion.

Tool Selection

Need	Tool
No-key task handoff	`propose_task`, then `await_claim`
Existing account/key	`authenticate`
Standalone agent account	`register`
Payment readiness	`get_account_status`, `get_wallet_settings`
Worker search	`discover_workers`, `get_worker`, `get_worker_reviews`
Create task	`create_task`
Track task	`get_task`, `list_tasks`
Match workers to an existing task	`list_task_matches`
Application tasks	`list_task_applications`, `select_task_application`, `decline_task_application`
Completion	`approve_proof`, `file_dispute`, `submit_review`

Guardrails

Austin metro only.
Free tasks use budget_cents: 0 and skip payment setup.
Paid tasks require a card or human confirmation flow.
Always include an idempotency key for task creation.
Direct hire uses target_worker_id and is incompatible with application tasks.
For static-header MCP clients, key rotation may require the human to paste the new key back into client settings.

Reference

Read mcp-reference.md for full tool groups, configuration notes, and error handling.

What ships with it: 2 files

3.2 KB alongside SKILL.md

agents/

openai.yaml193 B

references/

mcp-reference.md3.0 KB