Relay is answering right now. Last checked 4 min ago. 387 installs a week from npm. It exposes 14 tools. Last commit 24 Oct 2026.
Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.
Installs per day
peak 734 · avg 54 · +153% w/w
a month agotoday
Uptime history
22 days of history · worst day 99%
22 days agonow
100.0%
Uptime 24h
91 of 91 checks
14
Tools
read from the server
224 ms
Response time
average over 24h
387
Installs / week
npm and PyPI
Nothing serious here today
Today is the operative word: we check Relay every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
run in your terminal
claude mcp add mcp --transport http https://mcp.relaygpu.com/mcpSettings → Connectors → Add custom connector, then paste this address
https://mcp.relaygpu.com/mcp~/.codex/config.toml
[mcp_servers.mcp]
url = "https://mcp.relaygpu.com/mcp".cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.relaygpu.com/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://mcp.relaygpu.com/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
Available tools 14
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
model
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.
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.
workflow
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.
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.
cancel
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.
credits
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.
docs
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.
estimate
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.
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.
pricing
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.
task
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.
upload
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.
usage
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.
workflows
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.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.relaygpu.com/mcp | streamable-http | sign-in | 170 ms | 4 min ago |
Alternatives to Relay
same job, measured the same wayPipe2.ai
by pipe2
Run multi-step AI pipelines for video, image, audio and text: upload media, run, poll results.
PopNow API
by popnow-ai
Developer MCP for PopNow: run any AI image, video and audio model with an API key, billed in USD.
WaveSpeed
by wavespeed
Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
Printables
by feodor-ra
Search Printables.com 3D models, read model cards, list files and get download links.
Cloudinary Asset Management
by subomi
Upload, organize, search, and transform images, videos, and files with AI-powered tools.
Runapi MCP
by runapi-builder
130+ AI models for image, video, music, and audio — 18 model families, one RunAPI account.
Runway ML
by mindstone
Runway ML MCP server: AI video, image, audio, voice generation, and task management
Pinterest MCP
by sunkimk
Search Pinterest, see pins, find similar, read boards, download images and videos. No login.
Relay — questions
Answers built from our own checks of this server.
What can Relay do?
It exposes 14 tools, read directly from the server on our last check. Among them: cancel_workflow_run, check_task, check_workflow_run, estimate_cost, get_credits, get_model and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
What is Relay mostly used for?
Its tools cluster around workflow and model. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Relay working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 224 ms. The bar chart above shows every period we have measured.
How do I connect Relay?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to Relay?
No API key is involved. Relay answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is Relay?
It answers our handshake in 224 ms on average, which is faster than 63% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Relay?
The npm package @relaygpu/mcp was installed 387 times in the last week. Week over week that is +153%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Relay open source?
The code is open source: it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at mcp.relaygpu.com, which runs on its operator's own terms.