Click on "Install 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.
| Name | Required | Description | Default |
|---|---|---|---|
| intent | Yes | What you want, in natural language | |
| max_cost_cents | Yes | Spend ceiling in cents for this one generation. Corent refuses if the estimate is higher. |
| Name | Required | Description |
|---|---|---|
| result | No | |
| message | No | |
| executed | No | |
| actual_cost_cents | No | |
| estimated_cost_cents | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behaviors: auto-selects media type, tier, aspect ratio, duration; budget cap with safe failure; different result types (URL vs job id); no billing for failed generations. Annotations are consistent, no contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with purpose. No unnecessary words, but could be slightly more structured with bullet points for clarity. Efficient overall.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers main functionality, parameters, conditional behavior, and output types. Existence of output schema fills in return details. Minor gap: no mention of error handling beyond cost refusal.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters with descriptions. The tool description adds behavioral context: intent as natural language, max_cost_cents as spend ceiling with refusal behavior. Enhances understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool combines planning and generation for image/video, with the 'zero decisions' path. It distinguishes from siblings like generate_image, generate_video, and plan by being the unified, automated option.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use (plain language, zero decisions) and the mandatory max_cost_cents parameter. It explains what happens if cost exceeds ceiling, but doesn't explicitly state when not to use (e.g., for specific media type choices).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| style | No | Optional content style hint | |
| prompt | Yes | What to generate, in plain language | |
| preference | No | What to optimize for; Corent picks the best model tier automatically | balanced |
| aspect_ratio | No | 1:1 |
| Name | Required | Description |
|---|---|---|
| id | No | |
| meta | No | |
| images | No | |
| status | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond annotations: synchronous (2-20 seconds), permanent public URL, billing details, and no billing on failures. Annotations already indicate readOnlyHint=false and openWorldHint=true, and the description does not contradict them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences: first states purpose, second clarifies return type, third adds timing and cost. No fluff, front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-parameter tool with output schema and annotations, the description covers synchronous nature, cost, and failure policy. It omits usage context relative to siblings, but otherwise is adequate for an AI agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 75%, but the tool's description adds no additional parameter meaning. It only repeats cost information, which is not parameter-specific. aspect_ratio lacks a description in both schema and tool description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Generate an image from a text prompt', which is a specific verb and resource. It distinguishes from siblings like generate_video. Additional details about synchronous execution and public URL reinforce clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., generate_video, create). The description does not mention conditions, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | What to generate, in plain language | |
| image_url | No | If set, animates this image instead of pure text-to-video | |
| duration_s | No | Requested duration in seconds | |
| preference | No | balanced | |
| aspect_ratio | No | 16:9 |
| Name | Required | Description |
|---|---|---|
| id | No | |
| meta | No | |
| error | No | |
| images | No | |
| status | No | |
| videos | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses asynchronous job creation, cost tier, and no-billing for failures. These details go beyond annotations (readOnlyHint, openWorldHint) to inform agent behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with core action, no extraneous information. Efficiently conveys all critical points.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers async polling, cost, and failure billing. Given the output schema exists, return values are not needed. Provides sufficient context for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema includes descriptions for all parameters, so baseline is 3. The description adds context for prompt and image_url but does not elaborate on duration_s, preference, or aspect_ratio. Schema coverage is reported as 60%, but actual schema text shows full descriptions, so the description adds only marginal value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: generating a video from a text prompt, with optional source image animation. It distinguishes itself from sibling tools like generate_image and get_job by mentioning asynchronous behavior and cost comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: use get_job to poll for completion, cost comparison with images helps choose between tools, and failed generations are not billed. Lacks explicit when-not-to-use scenarios but covers main usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the Corent account's remaining balance in cents. Useful before starting expensive video generations. Read-only and free.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| balance_cents | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses read-only and free aspects, adding value beyond annotations (which already include readOnlyHint, idempotentHint). Provides non-obvious cost context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. Information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no parameters, rich annotations, and output schema present, the description fully covers the tool's purpose and usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so description need not compensate. Schema coverage is 100% trivially. Baseline of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it returns the account balance in cents, with a specific verb and resource. Distinguishes from sibling tools like create, generate_image, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly suggests use before expensive video generations, giving context. Does not list alternatives or when to avoid, but sibling tools are available.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | The job id returned by generate_video or generate_image |
| Name | Required | Description |
|---|---|---|
| id | No | |
| meta | No | |
| error | No | |
| images | No | |
| status | No | |
| videos | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds valuable behavioral context: that the tool is free, and when the job is completed, the response includes the permanent media URL and cost. This goes beyond the annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, no wasted words. It front-loads the main purpose and adds key details efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a single parameter, full annotations, and an output schema (not shown but present), the description provides sufficient context for a simple status check tool. The minor inaccuracy ('mainly videos') slightly reduces completeness but does not significantly hinder understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage for the single parameter job_id, the schema already explains it. The description adds no additional semantic detail beyond that, which is acceptable. No improvement needed but no extra value either.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool checks job status for generation jobs, especially videos. It distinguishes from siblings like create, generate_image, generate_video, and get_balance. However, the phrase 'mainly videos' is slightly misleading because the accepted job IDs can come from both video and image generation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description mentions 'Read-only and free', giving some context on when to use. However, it provides no explicit guidance on when not to use this tool or alternatives among siblings (e.g., get_status might overlap). No prerequisites or side effects are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get live operational status of Corent's generation tiers (operational/degraded). Read-only and free; useful to pick a healthy tier.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| tiers | No | |
| status | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds that it is live and free, providing minor additional context beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, with only two sentences that front-load the purpose and key traits. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and an output schema exists, the description fully covers what the agent needs to know: it returns live status, is read-only and free, and helps select a healthy tier.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and schema coverage is 100%. The description does not need to add parameter details, so baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets live operational status of Corent's generation tiers, specifying the type of status (operational/degraded). It distinguishes itself from siblings like get_balance and get_job as the only tool for tier health.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions it is useful for picking a healthy tier, providing clear usage context. It does not explicitly state when not to use it, but the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| intent | Yes | What you want, in natural language, e.g. 'a 10s vertical clip of a sunrise for TikTok' |
| Name | Required | Description |
|---|---|---|
| plan | No | |
| estimated_cost_cents | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations state readOnlyHint=true, idempotentHint=true, destructiveHint=false, which align with the description of a non-generating preview. The description adds valuable context: costs a fraction of a cent, Corent decides image/video/tier/aspect/duration, returns plan + cost, and handles unfulfillable requests with reason. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no filler. The purpose is stated upfront, and each sentence provides essential information: preview behavior, cost, decision factors, and fallback for unsupported requests.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no nested objects, output schema exists), the description covers returns (plan, estimated cost, can_fulfill with reason) and edge cases (unsupported request types). No gaps for an agent to select and invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter 'intent'. The description supplements the schema by providing an example ('a 10s vertical clip of a sunrise for TikTok') and explaining usage context (plain-language request, cost preview). This adds meaningful value beyond the schema's minimal description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Preview how Corent would handle a plain-language request WITHOUT generating anything'. It distinguishes from sibling tools like create, generate_image, generate_video by emphasizing no generation, and specifies the resource (plan/cost preview).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises 'Use this to decide or confirm cost before spending.' It also provides examples of when not to use (audio, text, 3D, editing, real-world actions) and explains the can_fulfill false behavior with reason, giving clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI image, video & audio generation tools for AI agents, powered by Varoriya.
Generate images, video, and audio with Glif's media-generation agent
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Generate reproducible image, video, and audio assets with leading models and your own provider keys.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gg13121/corent-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
