Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "jobs": {
      "type": "http",
      "url": "https://aitrainer.work/mcp"
    }
  }
}

claude mcp add --transport http jobs https://aitrainer.work/mcp

[mcp_servers.jobs]
url = "https://aitrainer.work/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jobs": {
      "type": "remote",
      "url": "https://aitrainer.work/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "jobs": {
      "type": "http",
      "url": "https://aitrainer.work/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=jobs&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWl0cmFpbmVyLndvcmsvbWNwIn0%3D"
}

{
  "servers": {
    "jobs": {
      "type": "http",
      "url": "https://aitrainer.work/mcp"
    }
  }
}

{
  "mcpServers": {
    "jobs": {
      "httpUrl": "https://aitrainer.work/mcp"
    }
  }
}

extensions:
  "jobs":
    enabled: true
    name: "jobs"
    type: streamable_http
    uri: "https://aitrainer.work/mcp"
    timeout: 300

Quality 88 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations6 of 6 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 1,107 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump
pass
tools.hidden_textno hidden text in tool names, descriptions, schemas or annotations

stability83 · weight 15

warn
stability.changes14 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name
pass
stability.new_linksno tool change named a new site

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

6 tools, about 1,107 tokens to load them all · tool set aee0f8180b93 · tools last changed 2026-10-23 · checked 2026-11-14 06:30 UTC

Tool changes

2026-10-23get_interview_prepchangeddescription
before
How a platform hires (steps, interview format, our guides) and practice questions with strong-answer outlines for a role. Use to explain what an interview involves or to run a mock interview. Practice questions are aitrainer.work's own, not a platform's real interview questions.
after · 97% of words in common
How a platform hires (steps, interview format, aitrainer.work guides) and practice questions with strong-answer outlines for a role. Use to explain what an interview involves or to run a mock interview. Practice questions are aitrainer.work's own, not a platform's real interview questions.
2026-10-23get_jobchangedoutput schema
2026-10-23search_jobschangeddescription, output schema
before
Search open AI training / AI evaluation roles (RLHF, model rating, expert data work) across 20+ platforms by keyword and filters. Returns title, platform, pay, eligible countries and the aitrainer.work page for each role, most relevant first (newest first when there is no keyword).
after · 80% of words in common
Search open AI training / AI evaluation roles (RLHF, model rating, expert data work) across 20+ platforms by keyword and filters. Returns title, platform, pay, eligible countries and the aitrainer.work page for each role, most relevant first (newest first when there is no keyword). Every keyword must appear in the role, so use one to three words.
2026-10-23match_jobs_to_profilechangeddescription, output schema
before
Rank open AI training / AI evaluation roles for one person, from their profession, skills, languages, country and minimum pay. Use when the user describes their background ("I am a nurse in Canada"). Returns the best matches with the reasons each one fits. Nothing about the person is stored.
after · 70% of words in common
Rank open AI training and AI evaluation roles for one person by their profession, skills, languages, country and minimum hourly pay (USD). Use when the user describes their own background, e.g. "I am a nurse in Canada". Returns up to 10 roles, highest match first, each with the reasons it fits. Nothing about the person is stored.
2026-10-23get_pay_statschangedoutput schema
2026-10-23list_platformschangedoutput schema
2026-10-23get_interview_prepadded
How a platform hires (steps, interview format, our guides) and practice questions with strong-answer outlines for a role. Use to explain what an interview involves or to run a mock interview. Practice questions are aitrainer.work's own, not a platform's real interview questions.
2026-10-23get_jobchangedoutput schema
2026-10-23search_jobschangeddescription, output schema
before
Search open AI training / AI evaluation roles (RLHF, model rating, expert data work) across 20+ platforms. Returns title, platform, pay, eligible countries and the aitrainer.work page for each role, newest first.
after · 77% of words in common
Search open AI training / AI evaluation roles (RLHF, model rating, expert data work) across 20+ platforms by keyword and filters. Returns title, platform, pay, eligible countries and the aitrainer.work page for each role, most relevant first (newest first when there is no keyword).
2026-10-23match_jobs_to_profileadded
Rank open AI training / AI evaluation roles for one person, from their profession, skills, languages, country and minimum pay. Use when the user describes their background ("I am a nurse in Canada"). Returns the best matches with the reasons each one fits. Nothing about the person is stored.

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 82 / 100

no-repository

provenance55

liveness99

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-97% +updated-19d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://aitrainer.work/mcp` streamable-http	none	yes	97%	388 ms	2025-06-18	2026-11-14

Tools (6)

`get_interview_prep`read-only	How a platform hires (steps, interview format, aitrainer.work guides) and practice questions with strong-answer outlines for a role. Use to explain what an interview involves or to run a mock interview. Practice questions are aitrainer.work's own, not a platform's real interview questions.
`get_job`read-only	Full details of one role: description, requirements, pay and its source, hours, interview, countries.
`get_pay_stats`read-only	Market pay for AI training work (median and quartiles of hourly rates stated in listings, by platform) and hiring outcomes from the latest monthly AI Training Pay Index.
`list_platforms`read-only	Platforms we track, with open role counts, median hourly pay, payout speed and availability.
`match_jobs_to_profile`read-only	Rank open AI training and AI evaluation roles for one person by their profession, skills, languages, country and minimum hourly pay (USD). Use when the user describes their own background, e.g. "I am a nurse in Canada". Returns up to 10 roles, highest match first, each with the reasons it fits. Nothing about the person is stored.
`search_jobs`read-only	Search open AI training / AI evaluation roles (RLHF, model rating, expert data work) across 20+ platforms by keyword and filters. Returns title, platform, pay, eligible countries and the aitrainer.work page for each role, most relevant first (newest first when there is no keyword). Every keyword must appear in the role, so use one to three words.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "work.aitrainer/jobs",
  "title": "aitrainer.work AI training jobs",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://aitrainer.work/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.2.0",
  "websiteUrl": "https://aitrainer.work/open-data#mcp",
  "description": "Search open AI training and RLHF jobs from 20+ platforms, with pay, countries and hiring stats."
}