Connect
Optimize
Secure
Twilio MCP Server
for AI Agents
Production-ready Twilio MCP server with 36 extensible actions — plus built-in authentication, security, and optimized execution.
Twilio MCP Server
Built by 
StackOne
StackOne 
Coverage
36 Agent Actions
Create, read, update, and delete across Twilio — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Twilio MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Twilio tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Twilio call.
Tools Discovery →What is the Twilio MCP Server?
A Twilio MCP server lets AI agents read and write Twilio data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Twilio MCP server ships with 36 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Twilio MCP Tools and Actions
Every action from Twilio's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Messages
- Send Message
Send a new SMS or MMS message
- List Messages
List all messages sent or received by your Twilio account
- Get Message
Retrieve details of a specific message by SID
- Update Message
Update a message (redact message body or cancel scheduled message)
- Delete Message
Delete a message record
Message Medias
- List Message Media
List all media associated with a message
- Delete Message Media
Delete a specific media instance
Calls
- List Calls
List all calls made to and from your Twilio account
- Get Call
Retrieve details of a specific call by SID
- Update Call
Modify an in-progress call (redirect, cancel, or complete)
- Delete Call
Delete a call record
Make Calls
- Make Call
Initiate an outbound call
Accounts
- Create Account
Create a new account under the main account
- Get Account
Retrieve account information and current status
- List Accounts
List all accounts including the main account and subaccounts
- Update Account
Update account properties (friendly name or status)
Conversations
- Create Conversation
Create a new conversation
- List Conversations
List all conversations in your account
- Get Conversation
Retrieve details of a specific conversation by SID
- Update Conversation
Update an existing conversation
- Delete Conversation
Delete a conversation
Conversation Messages
- Create Conversation Message
Create a new message in a conversation
- List Conversation Messages
List all messages in a conversation
- Get Conversation Message
Retrieve details of a specific message in a conversation
- Update Conversation Message
Update an existing message in a conversation
- Delete Conversation Message
Delete a message from a conversation
Conversation Participants
- Add Conversation Participant
Add a new participant to a conversation
- List Conversation Participants
List all participants in a conversation
- Get Conversation Participant
Retrieve details of a specific participant in a conversation
- Update Conversation Participant
Update a participant in a conversation
- Delete Conversation Participant
Delete a participant from a conversation
Conversation Users
- Create Conversation User
Create a new user in the conversations service
- List Conversation Users
List all users in the conversations service
- Get Conversation User
Retrieve details of a specific user
- Update Conversation User
Update an existing user
- Delete Conversation User
Delete a user from the conversations service
Set Up Your Twilio MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Twilio in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Twilio MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Twilio MCP Server FAQ
Twilio MCP server vs direct API integration — what's the difference?
A Twilio MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Twilio. A Twilio MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Twilio at runtime. StackOne provides both.
How does Twilio authentication work for AI agents?
Twilio authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Twilio account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Twilio MCP tools vulnerable to prompt injection?
Yes — Twilio MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Twilio agent and how do I avoid it?
Context bloat happens when Twilio tool schemas and API responses eat your Twilio agent's memory, preventing it from reasoning effectively. A single Twilio query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Twilio agent can access?
Yes — you can limit which actions your Twilio agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Twilio MCP server?
Yes — you can create custom agent actions for your Twilio MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Twilio's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Twilio MCP server?
Skip a Twilio MCP server if your integration is purely software-to-software — direct Twilio API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Twilio actions at runtime.
What AI frameworks and AI clients does the StackOne Twilio MCP server support?
The StackOne Twilio MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.