What is MCP?
The Model Context Protocol (MCP) is a standard for AI agents to interact with external services. Instead of making REST API calls, agents use typed tools with structured inputs and outputs.Available MCP tools
Rendobar exposes 15 MCP tools, mirroring the REST API:Job management
| Tool | Description |
|---|---|
submit_job | Submit a video processing job |
submit_batch | Submit multiple jobs at once |
get_job | Get job status and details |
get_job_result | Get the output URL for a completed job |
list_jobs | List jobs with filtering and pagination |
cancel_job | Cancel a running or queued job |
list_job_types | List all available job types |
get_job_schema | Get the Zod schema for a specific job type |
Billing
| Tool | Description |
|---|---|
get_balance | Check current usage balance |
get_usage | Get usage analytics for a date range |
Account
| Tool | Description |
|---|---|
get_org | Get organization details and plan info |
list_members | List organization members |
list_api_keys | List API keys |
create_api_key | Create a new API key |
revoke_api_key | Revoke an existing API key |
Connecting an agent
Claude Desktop / Claude Code
Add to your MCP config:Custom agents
Any MCP-compatible agent can connect to Rendobar’s MCP endpoint. The server supports the SSE transport protocol.Example: Agent workflow
An AI agent can process videos end-to-end:Authentication
MCP tools authenticate via API key in theAuthorization header. The same API keys used for REST work with MCP.
Authentication
API key setup
Job Types
All available operations
Quickstart
REST API getting started
MCP Overview
Full MCP reference