Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

claude mcp add --transport http aiwebsignals https://aiwebsignals.com/mcp

[mcp_servers.aiwebsignals]
url = "https://aiwebsignals.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "aiwebsignals": {
      "type": "remote",
      "url": "https://aiwebsignals.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "aiwebsignals": {
      "type": "http",
      "url": "https://aiwebsignals.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=aiwebsignals&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWl3ZWJzaWduYWxzLmNvbS9tY3AifQ%3D%3D"
}

{
  "servers": {
    "aiwebsignals": {
      "type": "http",
      "url": "https://aiwebsignals.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "aiwebsignals": {
      "httpUrl": "https://aiwebsignals.com/mcp"
    }
  }
}

extensions:
  "aiwebsignals":
    enabled: true
    name: "aiwebsignals"
    type: streamable_http
    uri: "https://aiwebsignals.com/mcp"
    timeout: 300

Quality 67 / 100needs work

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_normalized_report (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compare_public_machine_web_evidence (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_machine_capabilities (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 1,175 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability25 · weight 15

warn
stability.changes7 tool changes in 30 days
fail
stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

9 tools, about 1,175 tokens to load them all · tool set d2f5f912472c · tools last changed 2026-10-12 · checked 2026-10-19 10:20 UTC

Tool changes

2026-10-12request_machine_capabilityadded
Declare a missing capability by bounded technical slug and category. This records aggregate research evidence only; it will not execute, charge, provision, queue or promise future delivery.
2026-10-12diagnose_agent_connectionadded
FREE: read-only MCP/A2A compatibility guidance for version negotiation, legacy/modern header errors, invalid params and unavailable A2A task methods. Never send raw headers, IPs or secrets.
2026-10-12evaluate_ai_web_readinessadded
FREE ONE-CALL EVALUATION: run the existing bounded public readiness scan, retrieve the matching persisted normalized evidence report, verify scan ID + hostname, then return observed findings and next actions in this one response. Unknown evidence is not a successful observation. Never charges or changes a website.
2026-10-11scan_ai_web_readinesschangeddescriptionmeaning changed
before
Run AIWebSignals' existing bounded public readiness scanner for a public hostname or HTTP(S) URL. Private/local network targets are rejected. The target website is not modified; AIWebSignals may persist its normalized observation in scan history.
after · 33% of words in common
FREE EVALUATION FIRST: run a bounded public website readiness scan and get an explicit next-tool recommendation for a normalized evidence report. Read-only; no account or charge. Private/local network targets are rejected; observations may be saved to public scan history.
2026-10-11compare_public_machine_web_evidenceadded
Compare observable public machine-web readiness and evidence coverage for two to six public domains.
2026-10-11get_scan_historyadded
Retrieve public, exact-target scan history and observed changes for a domain; excludes private connected-site evidence.
2026-10-11get_normalized_reportadded
Read an existing or boundedly refreshed public AI web-readiness evidence report for a public domain. Unknown evidence remains unknown.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 94 / 100

provenance80

liveness99

freshness100

hygiene100

+repository +namespace-matches-repo +reachable +uptime-98% +updated-29d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://aiwebsignals.com/mcp` streamable-http	none	yes	98%	398 ms	2026-07-28	2026-10-19

Tools (9)

`compare_public_machine_web_evidence`	Compare observable public machine-web readiness and evidence coverage for two to six public domains.
`diagnose_agent_connection`	FREE: read-only MCP/A2A compatibility guidance for version negotiation, legacy/modern header errors, invalid params and unavailable A2A task methods. Never send raw headers, IPs or secrets.
`evaluate_ai_web_readiness`	FREE ONE-CALL EVALUATION: run the existing bounded public readiness scan, retrieve the matching persisted normalized evidence report, verify scan ID + hostname, then return observed findings and next actions in this one response. Unknown evidence is not a successful observation. Never charges or changes a website.
`get_machine_capabilities`	Return the current public capability contract served at /api/capabilities, including active protocol, evidence, and security boundaries.
`get_machine_pricing`	Return the same public plan catalog served at /api/machine-pricing. Provider configuration identifiers and payment credentials are excluded.
`get_normalized_report`	Read an existing or boundedly refreshed public AI web-readiness evidence report for a public domain. Unknown evidence remains unknown.
`get_scan_history`	Retrieve public, exact-target scan history and observed changes for a domain; excludes private connected-site evidence.
`request_machine_capability`	Declare a missing capability by bounded technical slug and category. This records aggregate research evidence only; it will not execute, charge, provision, queue or promise future delivery.
`scan_ai_web_readiness`	FREE EVALUATION FIRST: run a bounded public website readiness scan and get an explicit next-tool recommendation for a normalized evidence report. Read-only; no account or charge. Private/local network targets are rejected; observations may be saved to public scan history.

Schemas: list_tools.

More from io.github.Galanai

Official server.json

{
  "name": "io.github.Galanai/aiwebsignals",
  "title": "AIWebSignals",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://aiwebsignals.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "2.1.7",
  "repository": {
    "url": "https://github.com/Galanai/aiwebsignals-api",
    "source": "github"
  },
  "description": "Public AI web-readiness scanner and machine-facing observability discovery service."
}