Tidio MCP Server
Integrates the Tidio customer service platform with LLMs, enabling management of conversations, contacts, tickets, and operators through natural language.
README
Tidio MCP Server
A Model Context Protocol (MCP) server that integrates with the Tidio customer service platform.
It acts as a layer over the Tidio OpenAPI (REST API), making Tidio functionality available directly in LLM clients such as Claude Desktop.
Requirements
- Tidio Account — Tidio Plus plan (or higher)
- API Credentials — Client ID and Client Secret (see the authorization guide)
- Environment — Docker, or Python 3.13+ with uv
Setup
Option 1: Non-Technical Users (Claude Desktop + Docker)
You can quickly get started using the ready-to-use Docker image adrmrn/tidio-mcp from Docker Hub.
-
Install and run Docker Desktop
-
Install and open Claude Desktop
-
In Claude Desktop, go to Settings → Developer → Edit Config, and open the
claude_desktop_config.jsonfile in a text editor -
Add the following configuration, replacing the placeholders with your Tidio credentials:
{ "mcpServers": { "Tidio": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "TIDIO_CLIENT_ID", "-e", "TIDIO_CLIENT_SECRET", "adrmrn/tidio-mcp:latest" ], "env": { "TIDIO_CLIENT_ID": "PASTE_YOUR_CLIENT_ID_HERE", "TIDIO_CLIENT_SECRET": "PASTE_YOUR_CLIENT_SECRET_HERE" } } } } -
Save the file and restart Claude Desktop
Option 2: Technical Users (Python)
-
Clone this repository
-
Install dependencies with
uv sync -
Copy
.env.exampleto.envand set your Tidio credentials -
Add the following configuration to your MCP client:
{ "mcpServers": { "Tidio": { "command": "uv", "args": [ "--directory", "/absolute/path/tidio-mcp", "run", "server.py" ] } } } -
Restart your MCP client to apply the configuration
Available Tools
- Get Departments
- Get Operators
- Get Contacts
- Get Contact Details
- Delete Contact
- Get Tickets
- Get Ticket Details
- Create Ticket
- Update Ticket
- Delete Ticket
- Unassign Ticket
- Reply to Ticket
- Add Internal Note to Ticket
- Create Contact
- Update Contact
Missing Endpoints
The following endpoints are not yet implemented but are planned for future updates:
- [ ] Create multiple contacts (
POST /contacts/batch) - [ ] Update multiple contacts (
PATCH /contacts/batch) - [ ] Get viewed pages history (
GET /contacts/{contact_id}/viewed-pages) - [ ] Get contact messages (
POST /contacts/{contact_id}/messages)
Contributing
Contributions are welcome!
If you’d like to improve this project, feel free to open an issue or submit a PR.
For development, the repository includes a Makefile with handy commands to build, debug, and test the project.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.