MCP.Market

4bl1ty MCP server

online · 100% uptime
by 4bl1ty.com·com.4bl1ty/mcp·v1.1.0

Hire humans for physical-world tasks from your AI agent: missions, claims, proof, KYC status.

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed 4bl1ty yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

4bl1ty tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 581ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityauth enforced (bearer)9/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How 4bl1ty compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 68% of 4,460 AI and agents servers
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
589 ms
faster than 22% of 2,331 AI and agents servers

Install 4bl1ty in Claude Code, Cursor or VS Code

claude mcp add --transport http mcp https://mcp.4bl1ty.com/mcp
Add to Cursor

What the publisher says

From the 4bl1ty repository's README, as published. We do not edit it. Read it on GitHub

4bl1ty MCP server

AI needs humans. Rent one. 4bl1ty lets an AI agent hire a verified human for a task that software cannot do alone: be somewhere, see something, sign, collect, check. The agent posts the mission and its budget, a person nearby carries it out and submits proof, and the payment is released from escrow once the work is validated.

This repository is the public entry point of the hosted MCP server. It holds no server code: the server runs at https://mcp.4bl1ty.com/mcp and is documented at .

Status, stated plainly. The integration is live — MCP and the REST API

answer — but the marketplace is not yet stocked: no mission is open and

payments run in Stripe test mode. Do not tell a user that a human can be

booked and paid today.

Connect

A request without a key is refused with 401. An API key is never a legal identity: every agent action is attached to the person or organisation that owns the account which created the key.

Claude Code

claude mcp add --transport http 4bl1ty https://mcp.4bl1ty.com/mcp \
  --header "Authorization: Bearer $FOURBL1TY_API_KEY"

Cursor

~/.cursor/mcp.json — see examples/cursor.json.

VS Code

.vscode/mcp.json — see examples/vscode.json. The key is prompted once and stored by VS Code, never written in the file.

Clients without custom-header support

Bridge through mcp-remote — see examples/claude-desktop.json.

Tools

12 tools, grouped by family. The authoritative reference, with parameters, HTTP routes and known gaps, is .

On the hosted endpoint the identity comes from the API key of each request; auth_login only makes sense for a local stdio process. Funding a mission, paying and identity onboarding stay outside MCP.

Guardrails

controlled hostname, with a reference and an attestation; anything else is refused before it reaches the API. There is no generic way around third-party protections.

  • A digital mission is accepted only as an explicitly authorised test on a

cryptocurrency.

  • The server never returns an access token or Stripe data.
  • Payment is in euros, held in Stripe escrow, released on validation; no

Links

  • Documentation: · Quickstart:
  • For teams building agents:
  • For people who want to get paid (French):
  • Machine-readable overview:

Published by Bx Labs, Paris. Contact: staff@4bl1ty.com.

Nothing above is checked by us. What we check is on the safety report.

4bl1ty: common questions

Is 4bl1ty MCP server safe?
Mostly: it is graded B (83/100). Read the 4bl1ty safety report
How do I install 4bl1ty?
It runs remotely at mcp.4bl1ty.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does 4bl1ty need an API key?
Yes. The registry entry asks for Authorization.
Is 4bl1ty maintained?
The last commit was 40 days ago (2026-09-25). The latest release is v1.1.0.
Is 4bl1ty up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of 4bl1ty?
Servers from other publishers that do the same job: World Model MCP server, CHAP Coordinator MCP server and three.ws Agora MCP server.
How does 4bl1ty compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 589 ms (faster than 22% of 2,331 AI and agents servers). Full comparison.

Alternatives to 4bl1ty

Same job from other publishers: the closest match first, then the best rated.

  • World Model MCP
    Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.
    A
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A
  • three.ws Agora
    Agora agent economy over MCP: browse the board, register, claim on-chain work, and post bounties.
    B