Skip to content
FeatQ logo

FeatQ MCP server

Which MCP servers are FeatQ'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 2026-10-12

← Back to FeatQ

Whose server it is
  • Addresshttps://featq.com/api/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on featq.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools7
  • Server calls itselffeatq
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 552 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: collect feature requests from store reviews and support tickets; let users vote on requests by email.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 6 of 7 tools: check arguments before calling.

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: 1, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it0 of 2 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer605 ms
  • Space in an agent's context≈ 660 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsC · 69 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 7
  • Not saying whether it only reads or can destroy: 7 of 7

What an agent can do with it

  • cannot · collect feature requests from store reviews and support tickets
  • cannot · let users vote on requests by email
  • not sure · ship top-voted requests and notify voters

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 offers7 tools · read 2026-10-28
  • list_requests

    List feature requests for the connected FeatQ board.

  • get_request

    Get one feature request with its comments for the connected FeatQ board.

  • get_board_stats

    Get request counts, vote totals, and top requests for the connected FeatQ board.

  • get_ranked_requests

    Get the top feature requests by demand score, excluding requests already marked done. Requests are ranked by demand: each vote counts as one point and each comment as half a point, with scores gradually decaying as a request ages (90-day…

  • generate_spec

    Generate an agent-ready markdown implementation spec for one feature request.

  • update_request_status

    Update the status of a feature request. Marking a request done makes it appear in the public changelog.

  • list_competitor_claims

    List what watched competitor comparison pages say about this product. Read only. Claims are signals, not votes.

How to connect

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

{
  "mcpServers": {
    "featq": {
      "type": "http",
      "url": "https://featq.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http featq https://featq.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://featq.com/api/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.