Skip to content

OpenTrain MCP server

io.github.OpenTrain-AI/opentrainOpenTrain-AIstreamable-httpv0.49.1Scanned

Hire human data labelers, RLHF annotators, and evaluators from your coding agent.

2 tools: 2 only read.

Tools: 0 delete, 0 irreversible, 0 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the OpenTrain MCP server can do

The OpenTrain MCP server is published by the GitHub account OpenTrain-AI. It has 2 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

2 tools bring in text other people can write (opentrain_search_jobs and opentrain_get_job); 1 tool can send data out of your system (opentrain_get_job).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 19, 2026, version 0.49.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

2 tools

Only reads 2Show 2 read-only tools
  • opentrain_get_jobRead one OpenTrain job in full: pay, languages, countries, skills and the plain-text description.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "opentrain_get_job" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read one OpenTrain job in full: pay, languages, countries, skills and the plain-text description. Use it after opentrain_search_jobs, or when someone shares an OpenTrain job link. Pass id, or url as the job page link (https://www.opentrain.ai/jobs/<slug>--<id>/). A job that is closed or not public returns status "closed". Anonymous and read-only.

    Annotations the server declares

    • title: Get an OpenTrain Job
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • opentrain_search_jobsFind open jobs on OpenTrain, a marketplace for paid AI training and data work such as labeling, evaluation and subject-matter review.Reads text others writeNo findings

    Why it is in this group

    • The name "opentrain_search_jobs" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "find" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Find open jobs on OpenTrain, a marketplace for paid AI training and data work such as labeling, evaluation and subject-matter review. Use it when someone looks for this kind of work. Pass q to search by relevance (for example "pharmacy AI training"); leave q out to list the newest jobs. Filter by category, domain, language, country or payType. Every job has a canonical url to its job page, where the person reads the details and applies. Anonymous and read-only: it returns public job listings only.

    Annotations the server declares

    • title: Search Open OpenTrain Jobs
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:19 UTC, unchanged since Nov 19, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
0
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://app.opentrain.ai/.well-known/oauth-protected-resource
Authorization servers
https://app.opentrain.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
no
Client ID metadata documents
yes

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.49.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http opentrain https://app.opentrain.ai/mcp/jobs
claude mcp add --transport http opentrain https://app.opentrain.ai/mcp/jobs

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__opentrain__opentrain_search_jobs"
    ],
    "ask": [
      "mcp__opentrain__opentrain_get_job"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as opentrain. Review it before you use it.

Capability tags behind 2 rules
  • mcp__opentrain__opentrain_search_jobs untrusted-input
  • mcp__opentrain__opentrain_get_job untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.OpenTrain-AI/opentrain/verify?hash=2c47dbb34ee734efe3437cec12b2b02bb2804ba201f426f74e28ceeda40f3f26" | jq -e '.changed == false'

Pinned hash 2c47dbb34ee7, from Nov 19, 2026, 11:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.OpenTrain-AI/opentrain/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.OpenTrain-AI/opentrain
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.OpenTrain-AI/opentrain.svg)](https://radar.anlyon.com/servers/io.github.OpenTrain-AI/opentrain)

Source: MCP Registry · repository. Synced Nov 19, 2026, 11:18 UTC.

OpenTrain MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the OpenTrain MCP server safe?

No scan can promise that. What its definitions show: 2 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the OpenTrain MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the OpenTrain MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the OpenTrain MCP server have?

2 tools: 2 read. opentrain_search_jobs and opentrain_get_job.

Does the OpenTrain MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the OpenTrain MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): opentrain_get_job.

Has the OpenTrain MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.