Floop mcp tools

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

Floop agent skills

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.

What its author says it does

Copied from the file, not written here

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.

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.

Gives 0 of the 12 instructions most mcp tooling skills give in 657 tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-06

create ten complex read-only evaluation questionsin 71 of 638, across 17 files
test servers using MCP Inspectorin 60 of 638, across 18 files
provide actionable error messagesin 56 of 638, across 14 files
prioritize comprehensive API coverage over specific workflowsin 54 of 638, across 12 files
use TypeScript and Streamable HTTP for remote serversin 53 of 638, across 7 files
define structured output schemas where possiblein 51 of 638, across 9 files
use Zod or Pydantic for input schemasin 48 of 638, across 6 files
fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
load framework documentation using WebFetchin 45 of 638, across 3 files
verify each evaluation answer independentlyin 45 of 638, across 3 files
implement API client with authentication and paginationin 45 of 638, across 3 files
Define input schemas with validationin 28 of 638, across 10 files

Said here and by no other author read

read the onboarding guide first
call propose task without an api key
send the human claim url directly
call await claim with the claim token
check account status before paid tasks
discover workers before creating tasks

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.