Telerivet provides a Model Context Protocol (MCP) server that allows AI agents and LLM-based tools such as Claude and ChatGPT to interact with the Telerivet REST API using the standard MCP interface.
Telerivet's MCP server enables AI agents to perform a wide range of actions within Telerivet, including sending and scheduling messages, retrieving data and usage statistics, importing contacts, and configuring projects, routes, and automated services.
The MCP endpoint is available at:
https://api.telerivet.com/mcp
MCP clients connect via Streamable HTTP transport using JSON-RPC 2.0 messages over HTTP POST requests.
The MCP endpoint requires authentication via OAuth 2.0. An OAuth Client must be manually configured in Telerivet for each MCP Client. (Telerivet does not support Dynamic Client Registration.)
Telerivet has pre-configured OAuth Clients for the following MCP Clients (click to view setup instructions):
To allow using another MCP client that Telerivet has not already configured, you can add a new OAuth Client in your Telerivet organization and configure the OAuth callback URLs required by the MCP client. (The service providing the MCP client may specify their OAuth callback URLs in their documentation.) When an OAuth Client is configured in this way, it will only be accessible by users within your own Telerivet organization.
The MCP server currently exposes six tools:
The tools and API methods exposed by the MCP server may change over time.
The links below show the JSON returned by the MCP server, which may help to get an understanding of the available tools and API methods:
The scopes granted to your OAuth token determine which API methods are available. Methods requiring a scope that your token does not have will be excluded from the list.