inReels MCP

Turn your AI agent into an ad studio. Generate video ads, UGC ads, static image ads, voiceover and faceless videos from Claude, Cursor, Codex, ChatGPT or any MCP client.

https://www.inreels.ai/api/mcp

Remote MCP (Streamable HTTP) · 17 tools · 28 image, video and speech models · OAuth 2.1 with dynamic client registration, or a bearer API key

Website · Setup guide · llms.txt

Connect

Claude Code

claude mcp add --transport http --scope user inreels https://www.inreels.ai/api/mcp

Then run /mcp, pick inreels and sign in from the browser.

Claude, ChatGPT, Muse: add a custom connector with the URL above and sign in when asked.

Cursor (~/.cursor/mcp.json)

{ "mcpServers": { "inreels": { "url": "https://www.inreels.ai/api/mcp" } } }

Codex

codex mcp add inreels --url https://www.inreels.ai/api/mcp
codex mcp login inreels

Any other client: use the URL above, plus either OAuth or an Authorization: Bearer <API key> header. Create keys at https://www.inreels.ai/dashboard/settings/api-keys.

Local stdio (for clients without remote MCP support, or to keep the key in your own environment). This repo is that server; it forwards to the hosted API, so the tool list, pricing and validation stay the server's.

INREELS_API_KEY=... npx -y inreels inreels-mcp

Related MCP server: commercial-creator

Tools

Read-only tools are free. Generating tools spend credits; quote returns the exact price first, and failed runs are refunded in full.

Two layers, deliberately. Capabilities (create_*) return a finished deliverable and choose the model for you, exposing creative controls only. Primitives (generate_*) render one asset and expose the full parameter surface, for an agent that wants to drive the models itself.

Try it

"Make me a 15-second UGC ad for this product: <link or image>"

"Three static ad variations for my cold-brew cans, 1:1 for Instagram"

"A 60-second faceless video about the history of coffee, for YouTube Shorts"

How it behaves

• Every generating tool returns a run id immediately. Nothing blocks.

• get_run_status with wait: true blocks up to 45 seconds and usually returns a finished image in one call.

• Video is slower and has two stages — the scenes are built, then the MP4 is rendered. Roughly 5–10 minutes in total. A run reports completed only once the file exists, so an agent should keep polling rather than hand over a watch page as the finished thing.

• An unlisted model id is rejected, never quietly substituted.

• Every option is validated against the provider's live schema before it ships, so an agent cannot be handed a combination that fails.

• Tools are tagged read, write or sensitive write. Anything that spends credits is a sensitive write and is annotated destructive, so your host can ask you each time instead of taking blanket permission.

• No rate limits beyond the account's credit balance.

CLI

The same surface from a terminal.

npx inreels login ir_live_...
npx inreels tools
npx inreels describe create_faceless_video
npx inreels run generate_image --prompt "serum bottle on wet marble" --wait
npx inreels status <run_id>

--json on any command for scripting. inreels run works for any tool, including ones added after this version was published.

REST

Every tool is also a plain endpoint, same key.

curl -X POST https://www.inreels.ai/api/v1/generate_image \
  -H "Authorization: Bearer ir_live_..." \
  -H "Content-Type: application/json" \
  -d '{"prompt":"serum bottle on wet marble","aspect_ratio":"9:16"}'

https://www.inreels.ai/api/v1 returns every tool with its JSON Schema, unauthenticated. https://www.inreels.ai/llms.txt is the same thing written for an agent to read.

Links

• Setup guide — https://www.inreels.ai/connect

• Support — https://www.inreels.ai/support

• Pricing — https://www.inreels.ai/pricing

MIT.