Skip to content
YourAITools logo

YourAITools MCP server

Which MCP servers are YourAITools'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 YourAITools

Whose server it is
  • Registry nameco.youraitools/agentgateverified in the MCP registry

The registry name sits under youraitools.co. 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
  • Tools1
  • Server calls itselfagentgate
  • Server version0.2.3
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 920 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: compare x402 APIs by task and per-call price; check what one call costs before an agent pays; list your own pay-per-call API for buyers.
  • Checked on 6 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: 6, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it0 of 3 use cases
  • Use2,878 npm downloads a week
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer229 ms
  • Space in an agent's context≈ 188 tokensthe definitions of all its tools (1), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 1 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • cannot · compare x402 APIs by task and per-call price
  • cannot · check what one call costs before an agent pays
  • cannot · list your own pay-per-call API for buyers

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 2026-10-28
  • check_agent

    Check whether an AI agent is registered in the Concordium Agent Registry (CIS-8004), Active (not revoked), and Verified by Concordium (its Agent Card hash matches the on-chain metadata_hash). Accepts a badge (CIS-2 token address, e.g…

How to connect

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

{
  "mcpServers": {
    "agentgate": {
      "type": "http",
      "url": "https://api.youraitools.co/agentgate/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http youraitools https://api.youraitools.co/agentgate/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.youraitools.co/agentgate/mcp as a custom connector in the settings.

Other servers listed as YourAITools's
  • co.youraitools/agentreadyanswers, 1 toolsverified in the MCP registry
  • co.youraitools/counterpartycheckanswers, 1 toolsverified in the MCP registry
  • co.youraitools/creditsnot asked yetverified in the MCP registry
  • co.youraitools/domainchecknot asked yetverified in the MCP registry
  • co.youraitools/hubnot asked yetverified in the MCP registry
  • co.youraitools/injectscannot asked yetverified in the MCP registry
  • co.youraitools/leakguardnot asked yetverified in the MCP registry
  • co.youraitools/payguardnot asked yetverified in the MCP registry
  • co.youraitools/perpchecknot asked yetverified in the MCP registry
  • co.youraitools/perpradarnot asked yetverified in the MCP registry
  • co.youraitools/pkgguardnot asked yetverified in the MCP registry
  • co.youraitools/signchecknot asked yetverified in the MCP registry
  • co.youraitools/smartperpsnot asked yetverified in the MCP registry
  • co.youraitools/solverdictnot asked yetverified in the MCP registry
  • co.youraitools/stackdetectnot asked yetverified in the MCP registry
  • co.youraitools/tasignalnot asked yetverified in the MCP registry
  • co.youraitools/tokenverdictnot asked yetverified in the MCP registry
  • co.youraitools/toolfitnot asked yetverified in the MCP registry
  • co.youraitools/toolpicknot asked yetverified in the MCP registry
  • co.youraitools/toolroutenot asked yetverified in the MCP registry
  • co.youraitools/transcribenot asked yetverified in the MCP registry
  • co.youraitools/webreadnot asked yetverified in the MCP registry
  • co.youraitools/x402fixnot 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.