AI Agent Products & x402 APIs MCP server

Which MCP servers are AI Agent Products & x402 APIs'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 2026-11-03

← Back to AI Agent Products & x402 APIs

Whose server it is

Registry nameai.signalharness/mcpverified in the MCP registry

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

When we asked itchecked 2026-11-03

Stateanswerschecked 2026-11-03
Tools3
Server calls itselfsignalharness-x402-service-factory
Server version1.0.0
Protocol version2025-11-25

On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 295 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 2 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: 2, the first on 2026-11-03

INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
Answeredmeasuring2 of the 7 daily checks it takes to print a share
Median first answer1440 ms
Space in an agent's context≈ 641 tokensthe definitions of all its tools (3), which an agent carries on every turn
Tool definitionsA · 100 of 100
Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once

Every tool passes all six checks.

What an agent can do with it

not sure · run per-call AI search over supplied results
not sure · analyse crypto and blockchain data per call
cannot · map agent tool permissions to risk tiers

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 offers3 tools · read 2026-11-03

list_services
Discover the currently enabled public SignalHarness service catalog before choosing a service. This free, read-only call takes no arguments and returns a compact service array with canonical IDs, descriptions, prices, and supported…
get_service
Inspect one enabled public SignalHarness service before invoking it. Use an exact service_id returned by list_services. This free, read-only call returns the canonical description, input and output schemas, price, endpoint, and supported…
invoke_service
Run exactly one enabled public SignalHarness service with caller-supplied input. Call get_service first and validate input against its input_schema. An unpaid call returns the canonical x402 V2 PAYMENT-REQUIRED challenge plus the…

How to connect

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

{
  "mcpServers": {
    "signalharness": {
      "type": "http",
      "url": "https://signalharness.ai/api/agent/services/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http signalharness https://signalharness.ai/api/agent/services/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://signalharness.ai/api/agent/services/mcp as a custom connector in the settings.

OpenAPI spec

230 paths, read 2026-11-03. Open the spec ↗

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.