Skip to content
DataClue logo

DataClue MCP server

Which MCP servers are DataClue's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to DataClue

Whose server it is
  • Registry nameapp.dataclue/catalogverified in the MCP registry

The registry name sits under dataclue.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools4
  • Server calls itselfdataclue
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 144 ms.

Should an agent connect itConnect it
  • Its tools do every use case we checked: License household and warehouse egocentric video for robot training; Request quotes for custom teleoperation or hand-pose data collection.

Once connected

  • For "License household and warehouse egocentric video for robot training", the likely first call is search_datasets.
  • For "Request quotes for custom teleoperation or hand-pose data collection", the likely first call is request_quote.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 7, the first on 2026-10-28
  • INITE MCP score100 of 100answers 100 · does the job 100 · definitions 100 · context 100 · connects 100
  • What an agent can do with it2 of 2 use cases
  • Answered100% of days7 of 7 daily checks
  • Median first answer775 ms
  • Space in an agent's context≈ 819 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · License household and warehouse egocentric video for robot training
  • not sure · Preview de-identified clips and measured specs before buying
  • can do · Request quotes for custom teleoperation or hand-pose data collection

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-28
  • search_datasets

    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…

  • get_dataset

    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.

  • get_pricing_and_terms

    DataClue's list prices, what is included, quote paths (free samples, paid pilot, volume quote, custom collection), licensing, payment and consent terms.

  • request_quote

    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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "catalog": {
      "type": "http",
      "url": "https://dataclue.app/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://dataclue.app/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.