by twilio-labs
Provides a Model Context Protocol server that exposes all Twilio APIs and generates MCP tools directly from OpenAPI specifications.
The monorepo hosts two core packages: an MCP server that wraps the entire Twilio public API suite, and an OpenAPI‑driven MCP server that can turn any OpenAPI spec into an MCP‑compatible service. This enables AI assistants and other MCP‑aware tools to interact with Twilio functionality without writing custom adapters.
The quickest entry point is the npx
command. Supply your Twilio credentials in the required ACCOUNT_SID/API_KEY:API_SECRET
format:
{
"mcpServers": {
"twilio": {
"command": "npx",
"args": ["-y", "@twilio-alpha/mcp", "YOUR_ACCOUNT_SID/YOUR_API_KEY:YOUR_API_SECRET"]
}
}
}
For the OpenAPI variant, replace the package name with @twilio-alpha/openapi-mcp-server
and add --apiPath
to point at your spec file.
--services
or --tags
to limit the context size and improve LLM performance.npx
launches the server without a permanent global install.npm test
, npm run lint
, and auto‑fix scripts are provided.Q: Do I need to install anything beforehand?
A: No. npx
fetches the package on demand. Ensure you have Node.js ≥14 and npm installed.
Q: How are credentials supplied?
A: Pass them as a single argument in the format ACCOUNT_SID/API_KEY:API_SECRET
. Alternatively, set environment variables TWILIO_ACCOUNT_SID
, TWILIO_API_KEY
, and TWILIO_API_SECRET
before invoking the server.
Q: Can I run multiple MCP servers simultaneously? A: It is discouraged to run community MCP servers alongside the official Twilio server, as this may expose your credentials to untrusted code.
Q: What if I exceed LLM context limits?
A: Use --services
or --tags
to load only the APIs needed for a particular conversation.
Q: Is there support for different API versions? A: Yes. Specify the desired version (e.g., v1, v2) when filtering services, or point the OpenAPI server at a version‑specific spec.
Q: Where can I find detailed configuration options?
A: Each package has its own README under packages/mcp/README.md
and packages/openapi-mcp-server/README.md
.
This is a monorepo for the Model Context Protocol server that exposes all of Twilio APIs.
The Model Context Protocol (MCP) is a protocol for exchanging model context information between AI tools and services. This implementation allows you to expose Twilio's APIs to AI assistants and other tools that support the MCP protocol.
This monorepo contains two main packages:
Each package has its own comprehensive README with detailed documentation:
The easiest way to get started is by using npx:
{
"mcpServers": {
"twilio": {
"command": "npx",
"args": [
"-y",
"@twilio-alpha/mcp",
"YOUR_ACCOUNT_SID/YOUR_API_KEY:YOUR_API_SECRET"
]
}
}
}
Visit Twilio API Keys docs for information on how to find/create your API Key and Secret.
To guard against injection attacks that may allow untrusted systems access to your Twilio data, the ETI team advises users of Twilio MCP servers to avoid installing or running any community MCP servers alongside our official ones. Doing so helps ensure that only trusted MCP servers have access to tools interacting with your Twilio account, reducing the risk of unauthorized data access.
Both packages accept configuration parameters. Here's a brief overview:
--services
and --tags
to filter which APIs to expose--apiPath
to specify OpenAPI spec files locationFor complete configuration details, refer to the package-specific documentation linked above.
# Run tests
npm test
# Run linting
npm run lint
# Fix linting issues
npm run lint:fix
--services
or --tags
For detailed troubleshooting guidance, see the package-specific documentation.
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the ISC License - see the LICENSE file for details.
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "twilio": { "command": "npx", "args": [ "-y", "@twilio-alpha/mcp", "YOUR_ACCOUNT_SID/YOUR_API_KEY:YOUR_API_SECRET" ], "env": { "TWILIO_ACCOUNT_SID": "<YOUR_ACCOUNT_SID>", "TWILIO_API_KEY": "<YOUR_API_KEY>", "TWILIO_API_SECRET": "<YOUR_API_SECRET>" } } } }
Discover more MCP servers with similar functionality and use cases
by zed-industries
Provides real-time collaborative editing powered by Rust, enabling developers to edit code instantly across machines with a responsive, GPU-accelerated UI.
by cline
Provides autonomous coding assistance directly in the IDE, enabling file creation, editing, terminal command execution, browser interactions, and tool extension with user approval at each step.
by continuedev
Provides continuous AI assistance across IDEs, terminals, and CI pipelines, offering agents, chat, inline editing, and autocomplete to accelerate software development.
by github
Enables AI agents, assistants, and chatbots to interact with GitHub via natural‑language commands, providing read‑write access to repositories, issues, pull requests, workflows, security data and team activity.
by block
Automates engineering tasks by installing, executing, editing, and testing code using any large language model, providing end‑to‑end project building, debugging, workflow orchestration, and external API interaction.
by RooCodeInc
An autonomous coding agent that lives inside VS Code, capable of generating, refactoring, debugging code, managing files, running terminal commands, controlling a browser, and adapting its behavior through custom modes and instructions.
by lastmile-ai
A lightweight, composable framework for building AI agents using Model Context Protocol and simple workflow patterns.
by firebase
Provides a command‑line interface to manage, test, and deploy Firebase projects, covering hosting, databases, authentication, cloud functions, extensions, and CI/CD workflows.
by gptme
Empowers large language models to act as personal AI assistants directly inside the terminal, providing capabilities such as code execution, file manipulation, web browsing, vision, and interactive tool usage.