Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Corent MCP Server Plan a 15-second vertical video of a sunset for TikTok."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Give any AI agent the ability to generate images and videos through the Corent API — one key, automatic model routing, provider fallback built in.
Tool | What it does |
| Describe a request in plain language; Corent returns the plan (image vs video, tier, settings) + cost estimate, without generating |
| Describe what you want + a spend ceiling; Corent decides everything and generates it (the "zero decisions" path) |
| Text → image, synchronous, returns a permanent URL |
| Text (or image) → video, async job |
| Poll a job until completed |
| Remaining account balance |
| Live tier health |
The plan and create tools are the agent-native path: an agent says
what it wants ("a 10s vertical clip of a sunrise for TikTok") and Corent picks
image-vs-video, the tier, aspect ratio, and duration — the agent never manages
models. create enforces a per-call spend ceiling so an autonomous agent can't
overspend.
Related MCP server: Agnes MCP Server
Get an API key at corent.tech, then add to your MCP client config:
{
"mcpServers": {
"corent": {
"command": "npx",
"args": ["-y", "corent-mcp"],
"env": { "CORENT_API_KEY": "co_live_..." }
}
}
}For Claude Code: claude mcp add corent -e CORENT_API_KEY=co_live_... -- npx -y corent-mcp
The hosted server at https://mcp.corent.tech/mcp uses the Streamable HTTP
transport. Pass your API key in the Authorization header — this is the way
to authenticate:
{
"mcpServers": {
"corent": {
"url": "https://mcp.corent.tech/mcp",
"headers": { "Authorization": "Bearer co_live_..." }
}
}
}X-Corent-Api-Key: co_live_... is accepted as an equivalent header.
Smithery note: for compatibility with Smithery, the hosted server also accepts the key via query parameters (
?corent_api_key=...or Smithery's base64?config=). Avoid this form anywhere else — URLs can be logged by proxies, gateways, and access logs, which would expose your key. Prefer the Authorization header.
npm install
npm run build
CORENT_API_KEY=... node dist/index.jsDescribe what you want in plain language and Corent plans AND generates it — choosing image vs video, tier, aspect ratio, and duration for you (the 'zero decisions' path). You MUST pass max_cost_cents as a spend ceiling; if the estimated cost exceeds it, nothing is generated and you're told the estimate so you can raise the ceiling. Image results come back with a URL; video results come back as a job id to poll with get_job. Failed generations are never billed.
Inputs: intent (required), max_cost_cents (required). Returns: result, message, executed, actual_cost_cents, +1 more
Generate an image from a text prompt. Returns a permanent public URL. Synchronous: typically completes in 2-20 seconds. Costs a few cents, billed to the Corent account. Failed generations are never billed.
Inputs: prompt (required), style, preference, aspect_ratio. Returns: id, meta, images, status
Start generating a video from a text prompt (optionally animating a source image). Asynchronous: returns a job id immediately; poll get_job until status is 'completed'. Video costs more than images (tens of cents to a few dollars depending on tier). Failed generations are never billed.
Inputs: prompt (required), image_url, duration_s, preference, +1 more. Returns: id, meta, error, images, +2 more
Get the Corent account's remaining balance in cents. Useful before starting expensive video generations. Read-only and free.
Inputs: no named parameters. Returns: balance_cents
Check the status of a generation job (mainly videos). When completed, the response includes the permanent media URL and the cost. Read-only and free.
Inputs: job_id (required). Returns: id, meta, error, images, +2 more
Get live operational status of Corent's generation tiers (operational/degraded). Read-only and free; useful to pick a healthy tier.
Inputs: no named parameters. Returns: tiers, status
Preview how Corent would handle a plain-language request WITHOUT generating anything (costs a fraction of a cent). Corent decides whether it's an image or video, which tier, aspect ratio, and duration, and returns the plan plus an estimated cost. Use this to decide or confirm cost before spending. If the request is something Corent can't generate (audio, text, 3D, editing, real-world actions), can_fulfill is false with a reason.
Inputs: intent (required). Returns: plan, estimated_cost_cents
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool has a distinct purpose: 'create' handles combined planning and generation, 'generate_image' and 'generate_video' are direct generation for specific media, 'plan' provides cost estimation without execution, and the 'get_*' tools retrieve account and status info. There is no overlap.
Tool names follow a verb_noun pattern (e.g., generate_image, get_balance), with the exception of 'create' and 'plan' which are single verbs. Despite this minor deviation, the naming is mostly consistent and intuitive.
Seven tools cover core functionality—generation, planning, balance, job tracking, and status—without unnecessary duplication or bloat. The count is well-scoped for the domain.
Essential workflows are covered: plan, generate (image/video), monitor jobs, check balance, and system status. Missing features like job cancellation or history are minor gaps; the surface supports the primary use cases.
AI image, video & audio generation tools for AI agents, powered by Varoriya.
Generate and edit images, video, voice, lip-sync and 3D models from your AI agent.
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Generate images, video, and audio with Glif's media-generation agent
