Runware MCP

Live

OAUTH 2.1

MEDIA GENERATION

Media

Runware MCP gives agents authenticated access to media generation: run image, video, audio, and 3D models through one API with per-user OAuth 2.1.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Runware MCP
agent · Acme Q3
Run
Which Runware models can do text-to-image, and what would 50 renders at 1024x1024 cost?
S
runwaremcp_list_models
88ms
Runware agent
23 curated text-to-image models. FLUX.1 dev runs $0.0032 per 1024x1024 render, so 50 images cost $0.16. Cheapest option: Z-Image at $0.0019.
Sources: 23 models, 2 pricing lookups
runwaremcp
23 models
18:29
Message Claude...

Tools your media agent reaches for on Runware, scoped per user.

CALL ANY TOOL
Run media generation end to end: discover models, check schemas and pricing, execute inference, and audit every past task.
runwaremcp_account
Account
Retrieve Runware account information including balance and usage.
Parameters
Name
Type
Required
Description
operation
string
Required
Which account operation to perform. Currently only "getDetails" is supported.
includeCost
boolean
Optional
Include cost information
runwaremcp_get_task_details
Get task details
runwaremcp_image_upload
Upload image
runwaremcp_list_capabilities
List capabilities
runwaremcp_list_models
List models
runwaremcp_model_details
Model details
runwaremcp_model_examples
Model examples
runwaremcp_model_pricing
Model pricing
runwaremcp_model_schema
Model schema
runwaremcp_model_search
Search model
runwaremcp_model_upload
Upload model
runwaremcp_run
Run
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Runware tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["runwaremcp"], toolNames: [
    "runwaremcp_list_models",
    "runwaremcp_model_schema",
    "runwaremcp_run"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Generate a 1024x1024 hero image with FLUX.1 dev." }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["runwaremcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which models can generate video from text?" }],
  tools,
});

// Execute the tool call with the user's vaulted Runware credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["runwaremcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "What does FLUX.1 dev cost per 1024x1024 image?" }],
  tools,
});

// Tool call runs with the user's vaulted Runware credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["runwaremcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "runware_media_agent",
  model: "gemini-2.5-pro",
  instruction: "Generate and manage media on Runware for the signed-in user.",
  tools,
});

await agent.run("Upscale the product photo I uploaded to 4K.");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Runware tool. Click to copy, paste into your agent, done.
Find the right model
Copy the prompt
Copied
Which models can generate video from text?
Copy the prompt
Copied
What does FLUX.1 dev cost per 1024x1024 image?
Copy the prompt
Copied
Show me sample outputs for the cheapest upscaling model.
Generate assets
Copy the prompt
Copied
Generate a 1024x1024 hero image of a mountain cabin at dusk.
Copy the prompt
Copied
Remove the background from the product photo I just uploaded.
Copy the prompt
Copied
Render a 5-second clip of ocean waves with a text-to-video model.
Track spend and audit
Copy the prompt
Copied
What is my account balance and usage this month?
Copy the prompt
Copied
Pull the original request and output for task 8f3a.
Copy the prompt
Copied
How much did yesterday's video renders cost in total?
SEE HOW AUTH WORKS
Your users connect once. Their Runware credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Runware MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Runware MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Runware MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Runware MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other media connectors.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
GTM and RevOps Teams
CRM AI agent
Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
Test other agents
See the same per-user auth pattern across other media connectors.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Runware key looks fine in a demo. In production every render bills to one service account, and you cannot tell who generated an asset or burned the credits. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Runware today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Runware as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every generation and model upload in your audit trail is attributed to a real user, not a shared service account.
Where is the Runware token stored?
In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically under OAuth 2.1, and can be revoked from one dashboard.
Can I limit what the agent does in Runware?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example model discovery and pricing without run or model_upload. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
How do I keep agents from burning generation credits?
Every run is attributed to the user who triggered it, so spend traces to a person, not a bot. Gate expensive tools like runwaremcp_run behind a tool-name filter, have the agent check model_pricing first, and audit usage with the account tool.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""runwaremcp"": {
""url"": ""https://mcp.scalekit.com/runwaremcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.runwaremcp]
url = ""https://mcp.scalekit.com/runwaremcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""runwaremcp"": {
""url"": ""https://mcp.scalekit.com/runwaremcp"",
""type"": ""http""
}
}
}