Connect
Optimize
Secure
Re:amaze MCP Server
for AI Agents
Production-ready Re:amaze MCP server with 33 extensible actions — plus built-in authentication, security, and optimized execution.
Re:amaze MCP Server
Built by 
StackOne
StackOne 
Coverage
33 Agent Actions
Create, read, update, and delete across Re:amaze — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Re:amaze MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Re:amaze 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 Re:amaze call.
Tools Discovery →What is the Re:amaze MCP Server?
A Re:amaze MCP server lets AI agents read and write Re:amaze data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Re:amaze MCP server ships with 33 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 Re:amaze MCP Tools and Actions
Every action from Re:amaze's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Articles
- Create Article
Create a new help article
- List Articles
Retrieve help articles with search and filtering
- Get Article
Retrieve a specific article by slug
- Update Article
Update an existing help article
Channels
- List Channels
Retrieve all communication channels for the brand
- Get Channel
Retrieve a specific channel by slug
Contact Notes
- Create Contact Note
Add a note to a contact
- List Contact Notes
Retrieve notes for a specific contact
- Update Contact Note
Update an existing contact note
- Delete Contact Note
Delete a contact note
Contacts
- Create Contact
Create a new contact
- List Contacts
Retrieve contacts with search and filtering
- Update Contact
Update an existing contact
Conversations
- Create Conversation
Create a new conversation or ticket
- List Conversations
Retrieve conversations with filtering and pagination
- Get Conversation
Retrieve a specific conversation by slug
- Update Conversation
Update an existing conversation
Messages
- Create Message
Add a message or reply to a conversation
- List Messages
Retrieve messages across all conversations or filtered
Response Templates
- Create Response Template
Create a new canned response template
- List Response Templates
Retrieve canned response templates
- Get Response Template
Retrieve a specific response template
- Update Response Template
Update an existing response template
Other (10)
- Create Contact Identity
Attach an email, mobile number, social handle to a contact
- Create Staff Member
Create a new staff user
- Get Contact Identities
Retrieve all identities for a contact
- Get Volume Report
Retrieve daily conversation volume statistics
- Get Response Time Report
Retrieve response time metrics
- Get Staff Report
Retrieve staff performance metrics
- Get Tags Report
Retrieve tag usage statistics
- Get Channel Summary
Retrieve channel-wise conversation breakdown
- List Satisfaction Ratings
Retrieve customer satisfaction survey ratings
- List Staff
Retrieve staff members for the brand
Set Up Your Re:amaze MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Re:amaze 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
Re:amaze 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
Re:amaze MCP Server FAQ
Re:amaze MCP server vs direct API integration — what's the difference?
A Re:amaze MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Re:amaze. A Re:amaze 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 Re:amaze at runtime. StackOne provides both.
How does Re:amaze authentication work for AI agents?
Re:amaze 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 Re:amaze account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Re:amaze MCP tools vulnerable to prompt injection?
Yes — Re:amaze 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 Re:amaze agent and how do I avoid it?
Context bloat happens when Re:amaze tool schemas and API responses eat your Re:amaze agent's memory, preventing it from reasoning effectively. A single Re:amaze 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 Re:amaze agent can access?
Yes — you can limit which actions your Re:amaze 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 Re:amaze MCP server?
Yes — you can create custom agent actions for your Re:amaze MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Re:amaze's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Re:amaze MCP server?
Skip a Re:amaze MCP server if your integration is purely software-to-software — direct Re:amaze 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 Re:amaze actions at runtime.
What AI frameworks and AI clients does the StackOne Re:amaze MCP server support?
The StackOne Re:amaze 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.