# Relay (npm · @relaygpu/mcp)

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

- Trust score: 74/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.relaygpu.com`: 37/100, [markdown](https://verifymcp.io/servers/com-relaygpu-mcp/mcp.md), [page](https://verifymcp.io/servers/com-relaygpu-mcp/mcp)
- npm · `@relaygpu/mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/com-relaygpu-mcp/relaygpu-mcp.md), [page](https://verifymcp.io/servers/com-relaygpu-mcp/relaygpu-mcp)

## Channel facts

- Registry: `npm`
- Package: `@relaygpu/mcp`
- Version: `0.1.8`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 11 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2436 tokens (~174/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Relay MCP server?

Relay runs locally as an npm package, launched with npx -y @relaygpu/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-relaygpu-mcp -- npx -y @relaygpu/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-relaygpu-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@relaygpu/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-relaygpu-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@relaygpu/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-relaygpu-mcp -- npx -y @relaygpu/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-relaygpu-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@relaygpu/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-relaygpu-mcp --command npx --arg -y --arg @relaygpu/mcp
```

### Hermes

```yaml
mcp_servers:
  com-relaygpu-mcp:
    command: "npx"
    args: ["-y", "@relaygpu/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-relaygpu-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@relaygpu/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-relaygpu-mcp -t stdio -c npx -a -y @relaygpu/mcp
```

### Other

```json
{
  "mcpServers": {
    "com-relaygpu-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@relaygpu/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 70, +1)

- [functional] Package version: 0.1.4 → 0.1.8

### 2026-10-25 (score 69, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-24 (score 53, −20)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → fail
- [functional] Package version: 0.1.7 → 0.1.8
- [functional] Package version: 0.1.4 → 0.1.7

### 2026-10-23 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (14)

### `search_models` (~202 tokens)

Search Relay 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. image-to-image also lists every image model that takes an input image. Returns name, tag, route and accepts (input media the model takes, e.g. ["image"]; [] for none) per model (at most 50). With a credential the list is your account's view (what its tier and grants can run), public otherwise. Then call get_model with a name for its input schema.

Input parameters:

- `query` (string): Words to match, case-insensitive; every word must appear in the name, display name or tag (e.g. 'kling v3').
- `tag` (string): Model type tag, e.g. text-to-image or image-to-video. Omit for every tag.

### `get_model` (~95 tokens)

Get a Relay model

Returns one model's route, request_schema (what run_model's input must follow), request_example, pricing and availability. With a credential the answer is your account's view (what its tier and grants can run), public otherwise. Then call run_model with an input shaped like request_example.

Input parameters:

- `model` (string, required): Exact model name from search_models, e.g. google/gemini-nano-banana-2.1.

### `get_pricing` (~110 tokens)

Get Relay pricing

Returns Relay's list prices (USD), optionally for one model (with a credential your account's view: its tier and grants; public otherwise), plus media_storage: the per-file fees of the store_output / upload retention SKUs (relay1d, relay7d, …). Then estimate_cost for a number.

Input parameters:

- `model` (string): Model name (e.g. google/gemini-nano-banana-2.1) to keep only its rows. Omit for every model.

### `estimate_cost` (~194 tokens)

Estimate a Relay cost

Estimates the USD cost of a call from the price list (with a credential your account's view: its tier and grants; public otherwise): 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.

Input parameters:

- `model` (string, required): Exact model name, e.g. KlingTeam/v3-T2V.
- `usage` (object, required): What the call uses; only the fields of the model's billing type matter.

### `run_model` (~391 tokens)

Run a Relay model

Runs any Relay model by name (billed to your key). input follows get_model's request_schema (request_example runs as is). Every model whose schema takes async (image, video, audio) is submitted as a task: it waits up to 45 s, past that it returns a task_id — do not resubmit, call check_task. Chat models answer inline. 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.

Input parameters:

- `idempotency_key` (string): Your key for this submit (task models; a chat answer is not replayed): a retry with the same key and the same input replays the first task instead of starting (and billing) a new one; the same key wi…
- `inline_images` (boolean): Also return images ≤ 1 MB as image content blocks (default false: links only).
- `input` (object, required): Request body per get_model's request_schema, without model, store_output or async (run_model sets them). Pass media as *_url links (upload_file makes one). mode: direct (Relay's providers, the defaul…
- `model` (string, required): Exact model name from search_models / get_model, e.g. google/gemini-nano-banana-2.1.
- `store_output` (string): Keep result media longer: a media_storage SKU from get_pricing (e.g. relay7d, adds its per-file fee), or provider (default, 1 h).
- `wait_seconds` (integer): Seconds to wait for it to finish (0–45, default 45); 0 returns the task_id at once.

### `check_task` (~148 tokens)

Check a Relay 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.

Input parameters:

- `inline_images` (boolean): Also return images ≤ 1 MB as image content blocks (default false: links only).
- `task_id` (string, required): The task_id from run_model, e.g. direct:2f9c…
- `wait_seconds` (integer): Seconds to wait for it to finish (0–30, default 30); 0 just reads the status.

### `upload_file` (~281 tokens)

Upload a file to Relay

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.

Input parameters:

- `base64` (string): File content as base64 or a data: URI, at most 4 MB decoded. Larger files: pass url.
- `filename` (string): File name to record (defaults to the path's base name).
- `path` (string): Local file path (stdio server only; the hosted server cannot read your disk). Max 100 MB.
- `retention` (string): How long the link lives: relay1h (default, free within a daily quota) or a media_storage SKU from get_pricing (relay1d, relay7d, …).
- `slot` (boolean): true: get a single-use upload URL (10 minutes): run the curl line in your shell on the local file, or open open_url in a browser and pick the file; either prints the hosted link.
- `url` (string): Public http(s) link to copy onto Relay.

### `list_workflows` (~61 tokens)

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_workflow` (~298 tokens)

Run a 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.

Input parameters:

- `idempotency_key` (string): Idempotency-Key for the submit: the same key and inputs within 24 h return the same run_id instead of a new run. Generated when omitted.
- `inputs` (object, required): Template inputs, an object matching the workflow's input_schema.
- `store_output` (string): Run-level storage for every media step: `provider` (default, 1 h link) or `relay1d` / `relay7d` / `relay30d` (billed per file, see get_pricing).
- `wait_seconds` (integer): Seconds to wait for it to finish (0–45, default 45); 0 returns the run_id at once.
- `webhook_url` (string): HTTPS URL for one signed workflow.completed / workflow.failed delivery when the run ends.
- `workflow_id` (string, required): Workflow template id from list_workflows, e.g. `script-voiceover`.

### `check_workflow_run` (~126 tokens)

Check a 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.

Input parameters:

- `run_id` (string, required): The run id returned by run_workflow (`wf:…`).
- `wait_seconds` (integer): Seconds to wait for it to finish (0–30, default 30); 0 answers the current state at once.

### `cancel_workflow_run` (~71 tokens)

Cancel a 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.

Input parameters:

- `run_id` (string, required): The run id returned by run_workflow (`wf:…`).

### `get_credits` (~50 tokens)

Get credit balance

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_usage` (~215 tokens)

Get usage

Read the account's usage and spend per API key, newest keys first, 10 keys per page (pass starting_after = the previous answer's next_cursor for the next page; limit up to 1000). Pass period (e.g. 7d, max 30d) 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.

Input parameters:

- `from` (string): Start date `YYYY-MM-DD`; use together with `to`.
- `limit` (integer): Keys per page (default 10, max 1000).
- `period` (string): Time period shorthand, e.g. `7d` or `30d` (max 30 days); adds a by-date breakdown.
- `starting_after` (string): Cursor: the `next_cursor` of the previous page.
- `to` (string): End date `YYYY-MM-DD`; use together with `from`.

### `search_docs` (~126 tokens)

Search the Relay 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.

Input parameters:

- `limit` (integer): How many sections to return (1–10, default 5).
- `query` (string, required): What to look for, in plain words, e.g. `idempotency key` or `file retention`.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-relaygpu-mcp/relaygpu-mcp#diagnostics

## Score history

- 2026-11-05: 74
- 2026-11-04: 73
- 2026-11-03: 73
- 2026-11-02: 72
- 2026-11-01: 72
- 2026-10-31: 71
- 2026-10-30: 71
- 2026-10-29: 70
- 2026-10-28: 70
- 2026-10-27: 69
- 2026-10-26: 69
- 2026-10-25: 69
- 2026-10-24: 53
- 2026-10-23: 73
- 2026-10-22: 72
- 2026-10-21: 72
- 2026-10-20: 71
- 2026-10-19: 71
- 2026-10-18: 70
- 2026-10-17: 70
- 2026-10-16: 70
- 2026-10-15: 59
- 2026-10-14: 69
- 2026-10-13: 38
- 2026-10-12: 38

## Common questions

### What is the Relay MCP server?

Relay is an MCP server listed in the public MCP registry as com.relaygpu/mcp. Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs. This page covers its npm package (@relaygpu/mcp).

### Is the Relay MCP server safe to use?

Relay scores 74 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Relay MCP server expose?

Relay exposes 14 tools: search_models, get_model, get_pricing, estimate_cost, run_model, and 9 more. Their descriptions and schemas cost roughly 2,368 tokens of context every time the server is loaded.

### Is the Relay MCP server still maintained?

Relay is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Relay MCP server under?

Relay declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@relaygpu/mcp
- Socket report: https://socket.dev/npm/package/@relaygpu/mcp
- Repository: https://github.com/OpenGPU-Network/relaygpu-mcp
- Website: https://docs.relaygpu.com/sdk/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-relaygpu-mcp/relaygpu-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-relaygpu-mcp/relaygpu-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-relaygpu-mcp/relaygpu-mcp