Enables AI agents to run video generation tasks, poll asynchronous results, and check pricing for InfiniteTalk models.
Also known as runapi-ai/infinitetalk-mcp, @runapi.ai/infinitetalk-mcp
- Stars
- 1
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 0.2.1
- Last commit
- Oct 22, 2026
- License
- Apache-2.0
What is InfiniteTalk MCP?
InfiniteTalk enables AI agents to run video generation tasks, poll asynchronous results, and check pricing for InfiniteTalk models. It exposes 4 tools, such as login, audio_to_video, get_task.
Summary generated from the project's README
About InfiniteTalk MCP server
Generating video from audio files through AI agents is what this server enables. It provides a specialized connection to the InfiniteTalk model line on RunAPI, allowing developers to integrate video generation directly into their existing workflows. By using this server, an assistant can manage the entire lifecycle of a video task, from checking costs to retrieving final output URLs.
This tool works with various MCP-compatible hosts including Claude Code, Cursor, Windsurf, VS Code, and Roo Code. It is designed for users who want to keep their agent scoped specifically to InfiniteTalk rather than loading a full model catalog. For local setups, users can authenticate via a browser login tool that saves credentials to a local config file, while headless or CI environments can use the RUNAPI_API_KEY environment variable.
Users can interact with three specific tools: audio_to_video for creating tasks using the infinitetalk-from-audio model, get_task to poll for asynchronous results, and check_pricing to view current costs without needing to sign in.
What you can do with it
- 1Generate video from audioAsk your assistant to create a video generation task using an audio file.
- 2Monitor asynchronous task progressCheck the current status and retrieve the output URLs for a video task that is still processing.
- 3Verify model costsHave your agent look up the current pricing for InfiniteTalk models before starting a job.
- 4Run tasks in CI environmentsConfigure the server for headless use by providing an API key through environment variables.
Written from the project's README. Every use case is checked against a quote from it.
How to install InfiniteTalk MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall InfiniteTalk MCP in Claude Code
$ claude mcp add --env 'RUNAPI_API_KEY=<YOUR_RUNAPI_API_KEY>' infinitetalk-mcp -- npx -y @runapi.ai/infinitetalk-mcpInstall InfiniteTalk MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"infinitetalk-mcp": {
"command": "npx",
"args": [
"-y",
"@runapi.ai/infinitetalk-mcp"
],
"env": {
"RUNAPI_API_KEY": "<YOUR_RUNAPI_API_KEY>"
}
}
}
}Install InfiniteTalk MCP in VS Code
.vscode/mcp.json
{
"servers": {
"infinitetalk-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@runapi.ai/infinitetalk-mcp"
],
"env": {
"RUNAPI_API_KEY": "<YOUR_RUNAPI_API_KEY>"
}
}
}
}Install InfiniteTalk MCP in VS Code CLI
$ code --add-mcp '{"name":"infinitetalk-mcp","type":"stdio","command":"npx","args":["-y","@runapi.ai/infinitetalk-mcp"],"env":{"RUNAPI_API_KEY":"<YOUR_RUNAPI_API_KEY>"}}'Install InfiniteTalk MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"infinitetalk-mcp": {
"command": "npx",
"args": [
"-y",
"@runapi.ai/infinitetalk-mcp"
],
"env": {
"RUNAPI_API_KEY": "<YOUR_RUNAPI_API_KEY>"
}
}
}
}Install InfiniteTalk MCP in Codex
$ codex mcp add infinitetalk-mcp --env 'RUNAPI_API_KEY=<YOUR_RUNAPI_API_KEY>' -- npx -y @runapi.ai/infinitetalk-mcpInstall InfiniteTalk MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.infinitetalk-mcp] command = "npx" args = ["-y", "@runapi.ai/infinitetalk-mcp"] [mcp_servers.infinitetalk-mcp.env] RUNAPI_API_KEY = "<YOUR_RUNAPI_API_KEY>"
Install InfiniteTalk MCP in Gemini CLI
$ gemini mcp add -s user -e 'RUNAPI_API_KEY=<YOUR_RUNAPI_API_KEY>' infinitetalk-mcp npx -- -y @runapi.ai/infinitetalk-mcpInstall InfiniteTalk MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"infinitetalk-mcp": {
"command": "npx",
"args": [
"-y",
"@runapi.ai/infinitetalk-mcp"
],
"env": {
"RUNAPI_API_KEY": "<YOUR_RUNAPI_API_KEY>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @runapi.ai/infinitetalk-mcp 0.2.1 in an isolated container with no network and no keys. It answered and listed 4 tools.
InfiniteTalk MCP tools 4
Read from the server with tools/listloginAuthenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
audio_to_videoCreate a InfiniteTalk task on RunAPI (audio to video). Returns a task id, status, and output URLs.
get_taskFetch the current status and latest result payload for a infinitetalk task.
check_pricingLook up RunAPI pricing for the infinitetalk model line.
Configuration
RUNAPI_API_KEYSecretOptional RunAPI API key for headless hosts. Interactive MCP hosts can use the login tool, which writes shared RunAPI config.
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubWhy This Package?
@runapi.ai/infinitetalk-mcp is a focused Model Context Protocol server for the InfiniteTalk model line on RunAPI.
It gives MCP-compatible assistants direct access to 1 endpoint and 1 model variant without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to InfiniteTalk. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
Install
Add it to Claude Code:
claude mcp add infinitetalk -s user -- npx -y @runapi.ai/infinitetalk-mcp
Use project scope when the server should be shared with a repository:
claude mcp add infinitetalk -s project -- npx -y @runapi.ai/infinitetalk-mcp
Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"infinitetalk": {
"command": "npx",
"args": ["-y", "@runapi.ai/infinitetalk-mcp"]
}
}
}
check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login.
Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.
Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.
Tools
| Tool | Auth | Purpose |
|---|---|---|
audio_to_video |
Yes | Create an InfiniteTalk audio to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
get_task |
Yes | Fetch the current status and latest payload for an existing task. |
check_pricing |
No | Look up current pricing for a InfiniteTalk model and endpoint. |
Models
InfiniteTalk covers 1 model variant across 1 endpoint. Each tool accepts the models listed for it:
| Tool | Models |
|---|---|
audio_to_video |
infinitetalk-from-audio |
Model availability can change between releases. Use check_pricing or the InfiniteTalk model page for the current catalog view.
Agent Prompts
Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
Create a task
Run an InfiniteTalk audio to video task with RunAPI.
The assistant can call check_pricing, then audio_to_video, and return the task id, status, and output URLs.
Submit without waiting
Create the task but don't wait for it to finish.
The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.
Check pricing before creating
Check current InfiniteTalk pricing, then create the task if it matches my request.
The assistant calls check_pricing and can link to the InfiniteTalk model page for the canonical catalog entry.
Configuration
The server resolves auth in this order:
RUNAPI_API_KEYenvironment variable, useful for headless and CI hosts~/.config/runapi/config.json, created by the MCPlogintool orrunapi login- No key, which still allows
check_pricing
The config file is normally managed by login. A pre-provisioned headless config can use:
{
"apiKey": "your_runapi_key"
}
Do not commit real API keys.
Links
| Resource | URL |
|---|---|
| InfiniteTalk model page | https://runapi.ai/models/infinitetalk |
| npm package | @runapi.ai/infinitetalk-mcp |
| GitHub repository | runapi-ai/infinitetalk-mcp |
| RunAPI MCP overview | runapi.ai/mcp |
| RunAPI docs | runapi.ai/docs |
License
Licensed under the Apache License, Version 2.0.
InfiniteTalk MCP questions
How do I add InfiniteTalk MCP to Claude Code?
Run claude mcp add --env 'RUNAPI_API_KEY=<YOUR_RUNAPI_API_KEY>' infinitetalk-mcp -- npx -y @runapi.ai/infinitetalk-mcp in your terminal. Add --scope user to make it available in every project.
How do I add InfiniteTalk MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does InfiniteTalk MCP provide?
It exposes 4 tools, including login, audio_to_video, get_task, check_pricing.
How do I authenticate with the server?
You can use the RUNAPI_API_KEY environment variable or use the login tool to save credentials to ~/.config/runapi/config.json.
Can I check pricing without logging in?
Yes, the check_pricing tool works even without an active sign-in.
Can I create a video task without waiting for it to complete?
Yes, you can instruct your assistant to call the tool with wait: false to receive a task ID immediately.