# Relay

> Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.

- name: com.relaygpu/mcp
- version: 0.1.7
- connection class: R2 (oauth_consent_once)
- trust: 94/100
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.relaygpu%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/com.relaygpu%2Fmcp/tools

**An agent can connect after a one-time OAuth consent by a human.** Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "relaygpu": {
      "type": "http",
      "url": "https://mcp.relaygpu.com/mcp",
      "headers": {
        "X-API-Key": "${X_API_KEY}"
      }
    }
  }
}
```

Placeholders to fill: `${X_API_KEY}`.

## Trust

- hygiene: 100
- liveness: 96
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-89% +updated-5d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: 100 (weight 15)

- pass `auth.prm`: Protected Resource Metadata (RFC 9728) published
- pass `auth.as_metadata`: authorization server metadata reachable
- pass `auth.cimd`: Client ID Metadata Documents supported
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 14 of 14 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 4 of 14 tools declare all four hints; missing: get_model (destructiveHint); get_pricing (destructiveHint); check_task (destructiveHint); …
- pass `tools.token_cost`: about 3,471 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @relaygpu/mcp@0.1.7

- tools: 14, about 3,471 tokens to load them all
- tool set hash: 4ec156a84b113fbaf6cff45d2c090b66
- badge: [![protogrid quality](https://protogrid.dev/badge/com.relaygpu/mcp.svg)](https://protogrid.dev/servers/com.relaygpu/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm @relaygpu/mcp@0.1.7: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.relaygpu.com/mcp (streamable-http, auth oauth2, reachable true, uptime30d 0.89285713)

## Packages

- npm @relaygpu/mcp@0.1.7 secrets: RELAY_API_KEY

## Tools (14)

- `cancel_workflow_run`: Cancel a workflow run. Cancels between steps only: a step already running completes and bills. A run that has already ended answers WORKFLOW_RUN_NOT_CANCELLABLE. Needs a Relay credential.
- `check_task`: Checks a task run_model returned (no key needed: the task_id is the capability). Waits up to 30 s for it to finish; returns the result when completed, else its status: then call check_task again, never resubmit. Task results are kept 1 h after they finish.
- `check_workflow_run`: Poll a workflow run by run_id, waiting up to wait_seconds (≤ 30) for it to end. Completed → the final output; failed / cancelled → the error; still running → its steps so far: call check_workflow_run again. No key needed: the run_id is the access token.
- `estimate_cost`: Estimates the USD cost of a call from the public price list: an estimate, not an invoice (the bill uses provider-reported usage and any custom pricing on your account). Pass only the usage fields the model's billing_type (see get_model or get_pricing) reads: per_token: input_tokens, output_tokens, cached_input_tokens; per_image: image_count, resolution_tier; per_second_video: duration_seconds, quality_mode, sound; per_second_audio: duration_seconds; per_character: character_count; per_media_token: media_input_tokens, media_output_tokens. Add store_output / retention / file_count for storage fees.
- `get_credits`: Read the account's credit balance, active promo credits and consumption. Needs a dashboard JWT or a custom-tier superkey; a plain inference key gets PERMISSION_DENIED (403). Needs a Relay credential.
- `get_model`: Returns one model's route, request_schema (what run_model's input must follow), request_example, pricing and availability. Then call run_model with an input shaped like request_example.
- `get_pricing`: Returns Relay's public list prices (USD), optionally for one model, plus media_storage: the per-file fees of the store_output / upload retention SKUs (relay1d, relay7d, …). Then estimate_cost for a number.
- `get_usage`: Read the account's usage and spend per API key. Pass period (e.g. 7d) for a by-date breakdown, or from + to. Needs a dashboard JWT or a custom-tier superkey; a plain inference key gets PERMISSION_DENIED (403). Needs a Relay credential.
- `list_workflows`: List Relay's workflow templates: multi-step pipelines (e.g. script → voiceover) run as one call. Each entry has workflow_id, input_schema and its steps (step_id + model). Run one with run_workflow; inputs follow input_schema.
- `run_model`: Runs any Relay model by name (billed to your key). input follows get_model's request_schema (request_example runs as is). Waits up to 45 s; past that it returns a task_id — do not resubmit, call check_task. Result links expire 1 h after completion unless store_output names a media_storage SKU from get_pricing. Pass an idempotency_key if you may retry the same submit. Needs a Relay credential.
- `run_workflow`: Start a workflow run (one submit) and wait up to wait_seconds (≤ 45) for it to finish. Completed → the final output; still running → run_id: call check_workflow_run with it, never resubmit (a new run bills again). Each step is billed as an ordinary request. webhook_url gets ONE signed workflow.completed / workflow.failed delivery when the run ends. Get workflow_id and the inputs shape from list_workflows. Needs a Relay credential.
- `search_docs`: Search Relay's public docs (bundled, offline) for how-to, auth, errors, limits, retries, webhooks, files and pricing rules. Returns the best-matching sections: page, heading, docs path with anchor and an excerpt. For a model's input fields use get_model instead; to find a model use search_models.
- `search_models`: Lists Relay models by tag and/or text. Common tags: text-to-image, image-to-image, text-to-video, image-to-video, video-to-video, text-to-speech, speech-to-text, text-to-text, text-to-embedding. Returns name, tag and route per model (at most 50). Then call get_model with a name for its input schema.
- `upload_file`: Hosts an image, video or audio file on Relay and returns its url: pass that url to any *_url input of run_model. Give exactly one of path (local server only, ≤ 100 MB), base64 (≤ 4 MB) or url (a public link Relay copies). retention: relay1h (default, free within a daily quota) or a media_storage SKU from get_pricing. Needs a Relay credential.