Relay MCP server

• cancel_workflow_runwrite actionFree

  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_taskFree

  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_runwrite actionFree

  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_costFree

  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_creditsFree

  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_modelFree

  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_pricingFree

  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_usageFree

  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_workflowsFree

  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_modelwrite actionFree

  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_workflowwrite actionFree

  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_docsFree

  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_modelsFree

  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_filewrite actionFree

  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.

• Code scan6 source files scanned25/25
• Live reliabilityremote reachable in 2127ms17/20
• Tool poisoning14 tool descriptions checked15/15
• Auth qualityAPI key sent as a header8/15
• Maintenancelast push 0 days ago15/15
• Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10

Relay: common questions

Is Relay MCP server safe?

Yes, by our scan: it is graded A (88/100). Read the Relay safety report

How do I install Relay?

It runs remotely at mcp.relaygpu.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Relay need an API key?

Yes. The registry entry asks for RELAY_API_KEY, X-API-Key.

Is Relay maintained?

The last commit was in the last day (2026-10-12). The latest release is v0.1.4.

Is Relay up?

100% of our last 2 checks got an answer. We check remote servers about four times a day.

What can I use instead of Relay?

Servers from other publishers that do the same job: Open Agreements MCP server, CometChat Docs MCP server and gflow-cli MCP server. Compare all Relay alternatives.