Agents Index

Relay — agent service discovery

Online

Discover agent services, compare sourced capabilities and inspect connection evidence. No execution.

Visit publisherConnectJSON

What it can do: 16 tools

  • search_reading_sources read-onlySearch a dated local index of exact public Markdown documents from reviewed official publishers. Literal title/URL terms only, not semantic search. Returns ids, source URLs, listing provenance and pagination. A listing i
  • read_official_document read-onlyRead one exact source id returned by search_reading_sources with consent:true only for a user-requested public document. Available through this public endpoint without a ToolSkipper login or discovery key; consent:true i
  • run_discovery_workflow read-onlyPreferred default for multi-step service discovery. One fixed read-only discovery workflow, inspired by Code Mode. Send requestJson containing mode recommend/catalogue, discoveryRequestJson with the exact original comple
  • search_llm_providers read-onlyRead dated official-documentation observations for LLM providers. Optional query uses literal metadata terms; planType distinguishes free-tier, evaluation, recurring-credit, trial-credit, paid-credit and unknown. All sup
  • search_discovered_services read-onlyRead the separate, automatically collected Official MCP Registry index. Send requestJson containing query, limit and offset. Literal substring matching over names, descriptions and registry names; no semantic translation
  • get_service_evidence read-onlyRead the published evidence for one current service. Source review, observed provider response and internal task review are separate. Inspect observation dates, failures, scope and validity. Internal tests are not indepe
  • find_service_alternatives read-onlyRead-only alternatives. Send the original complete requestJson used for recommend_services and excludedProviders (1–20 distinct service slugs). Preserves all task, account, payment, protocol, budget and language conditio
  • recommend_services read-onlyFull standalone recommendation response. Prefer run_discovery_workflow when a shortlist with evidence, connection details or comparison is needed; use this tool for the full candidate/exclusion records. Read-only shortli
  • get_benchmark_suite read-onlyRead 20 predefined public-documentation task cases across English, Turkish, German and Spanish, with source URLs and review rubrics. Five task families have four language variants; this is a test design, not 20 independe
  • plan_benchmark read-onlyPlan a predefined benchmark case without running it. Read get_benchmark_suite for a caseId, then send requestJson containing {caseId,constraints?:{maxTaskCostUsd?,maxDurationMs?,requireMeasuredQuality?}}. Preserve every
  • search_services read-onlyFind services using deterministic keywords, bounded language aliases and category/protocol/pricing filters. Prefer requestJson (at most 8192 UTF-16 code units): serialize the complete request as JSON in this single strin
  • get_service read-onlyRead one full catalogue entry, including documentation links, pricing caveats and source check date. Does not connect to the provider.
  • compare_services read-onlyRetrieve 2–3 selected catalogue entries for comparison. Does not test providers or infer performance from their listing.
  • get_connection_spec read-onlyRead recorded endpoint, declared interfaces, authentication method, setup gaps and source evidence. Transport can come from matching Registry evidence or an exact-endpoint reviewed setup guide. Read the setupGuide option
  • get_connection_handoff read-onlyRead a reviewed host-managed connection plan for Exa, Jina or Browserless. Only provider is accepted. Returns official endpoints, authentication method, setup steps, source evidence and account-check limitations. Configu
  • get_task_options read-onlyPlan an optional keyless task without contacting a provider. Send requestJson containing only task (web_search, read_page, pdf_parse or browser_screenshot), input (public search text or URL), optional provider (auto, exa

Connect it

Claude Code
claude mcp add --transport http relay-agent-service-discovery https://relay-agent-services.orellise.chatgpt.site/api/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://relay-agent-services.orellise.chatgpt.site/api/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "relay-agent-service-discovery": {
      "url": "https://relay-agent-services.orellise.chatgpt.site/api/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "relay-agent-service-discovery": {
      "type": "http",
      "url": "https://relay-agent-services.orellise.chatgpt.site/api/mcp"
    }
  }
}

Questions

What does Relay — agent service discovery do?

Discover agent services, compare sourced capabilities and inspect connection evidence. No execution. It exposes 16 tools to AI assistants.

What tools does Relay — agent service discovery provide?

16 tools, including search_reading_sources, read_official_document, run_discovery_workflow, search_llm_providers, search_discovered_services, get_service_evidence, find_service_alternatives, recommend_services, get_benchmark_suite, plan_benchmark, search_services, get_service….

How do I connect Relay — agent service discovery to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://relay-agent-services.orellise.chatgpt.site/api/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Relay — agent service discovery require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Relay — agent service discovery online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Relay — agent service discovery?

relay-agent-services.orellise.chatgpt.site. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Web Search & Scraping