Skip to content
pixserp logo

pixserp MCP server

Which MCP servers are pixserp'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 2026-10-21

← Back to pixserp

Whose server it is
  • Registry namecom.pixserp/searchverified in the MCP registry

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

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools1
  • Server calls itselfpixserp
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 88 ms.

Should an agent connect itSkip it
  • Answered on only 2 of 12 daily checks.
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • For "get cited answers from live web search results", the likely first call is search.

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: 12, the first on 2026-10-21
  • INITE MCP score54 of 100answers 17 · definitions 83 · context 100 · use 0 · connects 100
  • Answered17% of days2 of 12 daily checks
  • Median first answer182 ms
  • Space in an agent's context≈ 276 tokensthe definitions of all its tools (1), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 1 of 1

What an agent can do with it

  • can do · get cited answers from live web search results
  • not sure · pull structured product, flight, or hotel listings for an agent
  • not sure · summarize YouTube videos from their transcripts

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 offers1 tools · read 2026-10-21
  • search

    Search the live web and get an AI-synthesized answer with structured citations. One endpoint covers 10 answer shapes — web, news, images, places & maps, shopping, flights, hotels, YouTube, transcripts, any URL — the right one is picked…

How to connect

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

{
  "mcpServers": {
    "search": {
      "type": "http",
      "url": "https://pixserp.com/api/v1/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http pixserp https://pixserp.com/api/v1/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://pixserp.com/api/v1/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.