RunAPICAUTION
RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
RunAPI MCP Server
AI image generation, video generation, music creation, text-to-speech, prompt search, and model discovery — 160+ executable models across 4 modalities in one MCP server.
Works with Claude Code, Codex, Cursor, Windsurf, VS Code, Roo Code, and any MCP-compatible host.
Quick Start | Tools | Examples | Catalog | Platforms
What Is This?
RunAPI MCP Server connects MCP-compatible coding tools to RunAPI. It lets an assistant browse the RunAPI catalog, inspect model inputs, check current runtime pricing, create media tasks, poll task status, and check account balance.
The discovery tools work without an API key because they use the embedded build-time catalog. Authenticated operations use the login tool, runapi login, RUNAPI_API_KEY, or shared RunAPI config.
This package is a pure client. It does not run a local generation backend and only needs RunAPI sign-in for authenticated tools.
Hosted MCP
Remote MCP clients can connect directly to:
https://mcp.runapi.ai/mcp
No Node.js installation is required. Use OAuth when the client supports remote MCP authorization, or configure a RunAPI API key as the bearer credential. See the [Hosted MCP se
ec219e2a9a94OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp --env RUNAPI_API_KEY=${RUNAPI_API_KEY} -- npx -y @runapi.ai/[email protected]Exposed tools (8)
6 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_balance | read | Return the authenticated RunAPI account balance and spending metrics. |
check_pricing | read | Return current runtime pricing for a RunAPI model/action pair. |
create_task | write | Run a RunAPI operation with a caller-generated idempotency key. Asynchronous operations can optionally poll until completion. |
get_model_info | write | Get supported endpoint, current runtime pricing, and input constraints for a RunAPI model slug. Add service and action when the model supports multiple endpoints. |
get_task | read | Fetch the current status and latest payload for an existing RunAPI task. |
list_actions | read | List RunAPI endpoint names grouped by output modality. |
list_models | read | List RunAPI models from the embedded catalog. Optional filters: modality, service, or action. |
search_prompts | read | Search RunAPI prompt examples by modality, category, tags, text query, model, or featured status. Free, no API key required. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
3. For interactive MCP hosts, tell the user you can call the RunAPI `login` tool to open browser login and save credentials to `~/.config/runapi/config.json`.
.codexignore
.node-version
export { SERVER_INSTRUCTIONS } from "../../src/server-instructions.js";path.resolve("../../node_modules/.bin/tsx")import { readContract } from "../../src/lib/data.js";import { PollTimeoutError, RunApiClientError } from "../../src/lib/errors.js";import { RunApiClient } from "../../src/lib/runapi-client.js";const apiUrl = `http://127.0.0.1:${(api.address() as AddressInfo).port}`;@modelcontextprotocol/sdk, zod, @types/node, esbuild, tsx, typescript, vitest
Gates applied: no_behavioural_pass.
ec219e2a9a94full audit observations/trust-audit/mcp-server/runapi-ai__runapi.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | ec219e2a9a94 | CAUTION | B | 89 | first audit |
Questions
What is the RunAPI MCP server?
RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.
What tools does RunAPI expose?
8 in total: 6 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is RunAPI safe to connect to an agent?
With care. The audit graded it B (89/100) and found 10 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does RunAPI need?
It reads RUNAPI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does RunAPI run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @runapi.ai/mcp at 0.15.0.
How current is this page?
The grade is for one exact copy of the source (ec219e2a9a94), read on 2026-10-08. The repository is watched and re-audited when it changes.