# Relay — agent service discovery

- Registry name: `site.chatgpt.orellise.relay-agent-services/relay` · version 0.11.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Web search, Search & data, Documents & retrieval
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=site.chatgpt.orellise.relay-agent-services%2Frelay
- Server page: https://mcpstation.net/s/site.chatgpt.orellise.relay-agent-services--relay.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://relay-agent-services.orellise.chatgpt.site/api/mcp`

## Tools (as reported by the server, not verified)

- `run\_discovery\_workflow`: Preferred 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 complete recommendation/search JSON string, optional maxCandidates 1–3, enrichment evi
- `search\_llm\_providers`: Read 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 supplied filters are retained; unknown arguments are rejected. Source observations
- `search\_discovered\_services`: Read 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 or suitability assessment. These records are NOT editorially reviewed or connec
- `get\_service\_evidence`: Read 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 independent certification; failed-attempt timing is not a latency benchmark. No privat
- `find\_service\_alternatives`: Read-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 conditions; never broadens a query or drops filters. A skipped service is caller-selecte
- `recommend\_services`: Full 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 shortlist for an explicitly selected web\_search, read\_page, pdf\_parse, browser\_automati
- `get\_benchmark\_suite`: Read 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 independently tested capabilities. The suite publishes no shared live evidence, quality r
- `plan\_benchmark`: Plan 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 intended constraint inside requestJson; unknown and duplicate inner fields are r
- `search\_services`: Find 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 string to preserve every field through connectors. query and queryEnglish each allow
- `get\_service`: Read one full catalogue entry, including documentation links, pricing caveats and source check date. Does not connect to the provider.
- `compare\_services`: Retrieve 2–3 selected catalogue entries for comparison. Does not test providers or infer performance from their listing.
- `get\_connection\_spec`: Read 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 for client authentication and session steps. Unknown fields remain unknown/null
- `get\_connection\_handoff`: Read 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. Configure credentials only in your agent host; ToolSkipper does not inspect accounts, p
- `get\_task\_options`: Plan 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 \(auto, exa, tavily, jina-ai, firecrawl or browserless\), optional web\_search sourceUrls \(1–

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html