Connect
Optimize
Secure
Front MCP Server
for AI Agents
Production-ready Front MCP server with 53 extensible actions — plus built-in authentication, security, and optimized execution.
Front MCP Server
Built by 
StackOne
StackOne 
Coverage
53 Agent Actions
Create, read, update, and delete across Front — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Front MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Front 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 Front call.
Tools Discovery →What is the Front MCP Server?
A Front MCP server lets AI agents read and write Front data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Front MCP server ships with 53 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 Front MCP Tools and Actions
Every action from Front's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Conversations
- List Conversations
Retrieve a list of conversations from Front in reverse chronological order.
- Get Conversation
Retrieve a specific conversation by ID from Front.
- Search Conversations
Search for conversations in Front using query filters.
- Update Conversation
Update a conversation's properties in Front.
- Delete Conversation
Delete a conversation from Front.
Conversation Comments
- Add Conversation Comment
Add an internal comment to a conversation in Front.
- List Conversation Comments
Retrieve all comments on a conversation from Front.
Conversation Tags
- Add Conversation Tag
Add a tag to a conversation in Front.
- Remove Conversation Tag
Remove a tag from a conversation in Front.
Conversation Followers
- Add Conversation Followers
Add followers to a conversation in Front.
- List Conversation Followers
Retrieve all followers of a conversation from Front.
Contacts
- Create Contact
Create a new contact in Front.
- List Contacts
Retrieve a list of contacts from Front.
- Get Contact
Retrieve a specific contact by ID from Front.
- Update Contact
Update an existing contact in Front.
- Delete Contact
Delete a contact from Front.
Teammates
- List Teammates
Retrieve a list of teammates from Front.
- Get Teammate
Retrieve a specific teammate by ID from Front.
- Update Teammate
Update a teammate's profile in Front.
Inboxs
- Create Inbox
Create a new inbox in Front.
- Get Inbox
Retrieve a specific inbox by ID from Front.
Channels
- List Channels
Retrieve a list of channels from Front.
- Get Channel
Retrieve a specific channel by ID from Front.
- Update Channel
Update a channel's settings in Front.
Messages
- Send Message
Send an outbound message from a channel in Front.
- Get Message
Retrieve a specific message by ID from Front.
Tags
- Create Tag
Create a new tag in Front.
- List Tags
Retrieve a list of tags from Front.
- Get Tag
Retrieve a specific tag by ID from Front.
- Update Tag
Update a tag in Front.
- Delete Tag
Delete a tag from Front.
Child Tags
- Create Child Tag
Create a child tag under a parent tag in Front.
- List Child Tags
Retrieve child tags of a parent tag from Front.
Accounts
- Create Account
Create a new account in Front.
- List Accounts
Retrieve a list of accounts from Front.
- Get Account
Retrieve a specific account by ID from Front.
- Update Account
Update an existing account in Front.
- Delete Account
Delete an account from Front.
Events
- List Events
Retrieve a list of events from Front.
- Get Event
Retrieve a specific event by ID from Front.
Other (13)
- Add Contact Handle
Add a new handle (email, phone, etc.) to a contact in Front.
- Add Contact Note
Add a note to a contact in Front.
- Create Draft
Create a draft message which is the first message of a new conversation.
- List Conversation Messages
Retrieve all messages in a conversation from Front.
- List Contact Conversations
Retrieve all conversations for a contact from Front.
- Get Authenticated User
Retrieve the teammate associated with the current API token.
- List Inboxes
Retrieve a list of inboxes from Front.
- List Inbox Conversations
Retrieve conversations in an inbox from Front.
- List Inbox Channels
Retrieve channels associated with an inbox from Front.
- List Tagged Conversations
Retrieve conversations with a specific tag from Front.
- List Account Contacts
Retrieve contacts associated with an account from Front.
- List Conversation Events
Retrieve events for a specific conversation from Front.
- Update Conversation Assignee
Assign or unassign a conversation to a teammate in Front.
Set Up Your Front MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Front 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>"
]
}
}
}More Customer Support MCP Servers
Intercom
123+ actions
SurveyMonkey
104+ actions
Freshservice
84+ actions
ServiceNow
74+ actions
Freshdesk
71+ actions
Gorgias
69+ actions
Discourse
67+ actions
Front 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
Front MCP Server FAQ
Front MCP server vs direct API integration — what's the difference?
A Front MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Front. A Front 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 Front at runtime. StackOne provides both.
How does Front authentication work for AI agents?
Front 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 Front account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Front MCP tools vulnerable to prompt injection?
Yes — Front 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 Front agent and how do I avoid it?
Context bloat happens when Front tool schemas and API responses eat your Front agent's memory, preventing it from reasoning effectively. A single Front 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 Front agent can access?
Yes — you can limit which actions your Front 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 Front MCP server?
Yes — you can create custom agent actions for your Front MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Front's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Front MCP server?
Skip a Front MCP server if your integration is purely software-to-software — direct Front 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 Front actions at runtime.
What AI frameworks and AI clients does the StackOne Front MCP server support?
The StackOne Front 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.