Skip to content

DataClue — AI training data MCP server

app.dataclue/catalogdataclue.appstreamable-httpv1.0.0Scanned

Search and license real-world AI training data: egocentric video, UMI gripper demos, custom EEG.

4 tools: 1 can delete or cancel things and 3 only read.

Tools: 1 delete, 0 irreversible, 0 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • 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 DataClue — AI training data MCP server can do

The DataClue — AI training data MCP server is published by dataclue.app, a domain the MCP Registry verified. It has 4 tools. It can delete or cancel things (1 tool: request_quote). 3 tools only read.

1 tool brings in text other people can write (request_quote).

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 8, 2026, version 1.0.0.

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.

4 tools

Deletes or cancels 1Claude Code: deny
  • request_quoteSend a request to DataClue's sales team on the user's behalf: free evaluation samples, a paid pilot, a volume quote, or a custom collection.Reads text others writeNo findings

    Why it is in this group

    • The name "request_quote" says "request": a word for a change.
    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Send a request to DataClue's sales team on the user's behalf: free evaluation samples, a paid pilot, a volume quote, or a custom collection. Side effect: emails the request (including the user's name, work email and company) to DataClue, who reply to that email. Only call this when the user has asked to contact DataClue and has provided their own work email, and show them the details to confirm before sending. Each call sends a new request, so do not retry a successful call.

    Annotations the server declares

    • title: Request samples or a quote
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_datasetFull details for one DataClue dataset: overview, scenarios with measured sample specs, delivered resolution, sensors, annotation, delivery format, licensing, FAQs, sample clip URLs…No findings

    Why it is in this group

    • The name "get_dataset" says "get": a word for reading.
    Description, as the server wrote it
    Full details for one DataClue dataset: overview, scenarios with measured sample specs, delivered resolution, sensors, annotation, delivery format, licensing, FAQs, sample clip URLs and price.

    Annotations the server declares

    • title: Get dataset details
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • get_pricing_and_termsDataClue's list prices, what is included, quote paths (free samples, paid pilot, volume quote, custom collection), licensing, payment and consent terms.No findings

    Why it is in this group

    • The name "get_pricing_and_terms" says "get": a word for reading.
    Description, as the server wrote it
    DataClue's list prices, what is included, quote paths (free samples, paid pilot, volume quote, custom collection), licensing, payment and consent terms.

    Annotations the server declares

    • title: Get pricing and terms
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • search_datasetsSearch DataClue's catalog of licensable AI training data (egocentric video of real work, UMI gripper demonstrations) with a plain-English need, e.g.No findings

    Why it is in this group

    • The name "search_datasets" says "search": a word for reading.
    Description, as the server wrote it
    Search DataClue's catalog of licensable AI training data (egocentric video of real work, UMI gripper demonstrations) with a plain-English need, e.g. "50,000 hours of household manipulation video, 1080p, long sessions". Returns matching datasets with hours in stock, price per hour, scenarios and which requirements they meet, plus custom-collection options when nothing in stock fits.

    Annotations the server declares

    • title: Search datasets
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

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 or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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 15, 2026, 13:22 UTC, unchanged since Oct 24, 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 destructive). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://dataclue.app/mcp: tools/list returned 4 tools to an anonymous client, including request_quote (destructive)

    What this check looks for

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http catalog https://dataclue.app/mcp
claude mcp add --transport http catalog https://dataclue.app/mcp

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__catalog__search_datasets",
      "mcp__catalog__get_dataset",
      "mcp__catalog__get_pricing_and_terms"
    ],
    "ask": [],
    "deny": [
      "mcp__catalog__request_quote"
    ]
  }
}

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 catalog. Review it before you use it.

Capability tags behind 1 rule
  • mcp__catalog__request_quote untrusted-input

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/app.dataclue/catalog/verify?hash=997d9de2d81313901937b1932b32cc96aa49f27692bb4c0c3f278ba49ba35efb" | jq -e '.changed == false'

Pinned hash 997d9de2d813, from Nov 8, 2026, 23:17 UTC.

Watch

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

https://radar.anlyon.com/servers/app.dataclue/catalog/changes.xml

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

Badge

Anlyon Radar badge for app.dataclue/catalog
[![Anlyon Radar](https://radar.anlyon.com/badge/app.dataclue/catalog.svg)](https://radar.anlyon.com/servers/app.dataclue/catalog)

Source: MCP Registry. Synced Oct 24, 2026, 02:17 UTC.

DataClue — AI training data MCP server: questions and answers

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

Is the DataClue — AI training data MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the DataClue — AI training data MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: request_quote.

Can the DataClue — AI training data 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 DataClue — AI training data MCP server have?

4 tools: 1 destructive, 3 read. request_quote, search_datasets, get_dataset and get_pricing_and_terms.

Does the DataClue — AI training data MCP server need sign-in or OAuth?

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

Does the DataClue — AI training data MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the DataClue — AI training data MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.