Agent Exchange MCP server

Which MCP servers are Agent Exchange'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 2026-10-26

← Back to Agent Exchange

Whose server it is

Registry namework.agentexchange.aivisibility/ai-visibility-mcpverified in the MCP registry

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

When we asked itchecked 2026-10-26

Stateanswerschecked 2026-10-26
Tools2
Server calls itselfai-visibility-checker
Server version1.1.0
Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 113 ms.

Should an agent connect itNot proven either way yet

Whether its tools do the product's job has not been judged yet.
Checked on 1 of the 7 days it takes to judge reliability.

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 2026-10-27

INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
Answeredmeasuring1 of the 7 daily checks it takes to print a share
Median first answer75 ms
Space in an agent's context≈ 284 tokensthe definitions of all its tools (2), which an agent carries on every turn
Tool definitionsA · 100 of 100
Typed results2 of 2 toolsdeclared outputSchema: results come typed, read once

Every tool passes all six checks.

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 offers2 tools · read 2026-10-26

check_ai_visibility
Read-only estimate of brand visibility in a representative large-language-model buyer-prompt sample. It is not a measurement or ranking from ChatGPT, OpenAI, or any named assistant. Returns a 0-100 proxy score, named competitors, and top…
check_agent_readiness
Read-only audit of whether a public website is ready for AI agents: crawler access, llms.txt, structured data, discovery files, and metadata. Returns a 0-100 score and specific gaps. Free.

How to connect

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

{
  "mcpServers": {
    "ai-visibility-mcp": {
      "type": "http",
      "url": "https://aivisibility.agentexchange.work/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http agentexchange https://aivisibility.agentexchange.work/mcp

Add to Cursor Add to VS Code

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

Other servers listed as Agent Exchange's

work.agentexchange.planets/agent-planetsdid not answer on 2026-10-26verified in the MCP registry
work.agentexchange.tooldrift/monitordid not answer on 2026-10-26verified in the MCP registry
work.agentexchange/measured-datanot asked yetverified in the MCP registry

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.