Connect
Optimize
Secure
Envoy MCP Server
for AI Agents
Production-ready Envoy MCP server with 42 extensible actions — plus built-in authentication, security, and optimized execution.
Envoy MCP Server
Built by 
StackOne
StackOne 
Coverage
42 Agent Actions
Create, read, update, and delete across Envoy — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Envoy MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Envoy 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 Envoy call.
Tools Discovery →What is the Envoy MCP Server?
A Envoy MCP server lets AI agents read and write Envoy data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Envoy MCP server ships with 42 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 Envoy MCP Tools and Actions
Every action from Envoy's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Invites
- Create Invite
Create a new visitor invitation
- List Invites
List visitor invitations
- Get Invite
Get details of a specific invitation
- Update Invite
Update an existing visitor invitation
- Delete Invite
Delete a visitor invitation
Recurring Invites
- Create Recurring Invite
Create a new recurring visitor invitation
- Get Recurring Invite
Get details of a specific recurring invitation
- Update Recurring Invite
Update an existing recurring visitor invitation
Blocklist Entrys
- Create Blocklist Entry
Create a new blocklist entry
- Get Blocklist Entry
Get details of a specific blocklist entry
- Update Blocklist Entry
Update an existing blocklist entry
- Delete Blocklist Entry
Delete a blocklist entry
Employees
- List Employees
List all employees in the workspace
- Get Employee
Get details of a specific employee
Flows
- List Flows
List all visitor flows
- Get Flow
Get details of a specific visitor flow
Locations
- List Locations
List all locations in the workspace
- Get Location
Get details of a specific location
Work Schedules
- Create Work Schedule
Create a new employee work schedule
- List Work Schedules
List employee work schedules
- Get Work Schedule
Get details of a specific work schedule
- Delete Work Schedule
Delete an employee work schedule
Spaces
- List Spaces
List all spaces such as desks or rooms
- Get Space
Get details of a specific space
Desks
- Create Desk
Create a new desk
- List Desks
List all desks in the workspace
- Get Desk
Get details of a specific desk
- Update Desk
Update an existing desk
- Delete Desk
Delete a desk
Reservations
- Create Reservation
Create a new reservation
- List Reservations
List all reservations
- Get Reservation
Get details of a specific reservation
Other (10)
- Get Company
Get company details
- List Entries
List visitor entries (check-ins and check-outs)
- Get Entry
Get details of a specific entry
- List Blocklist Entries
List all blocklist entries
- Check In Invite
Check in a visitor by converting an invite into an entry
- Check In Work Schedule
Check in to a work schedule
- Check Out Work Schedule
Check out from a work schedule
- Check In Reservation
Check in to a reservation to start using the space
- Check Out Reservation
Check out from a reservation to end usage and free the space
- Cancel Reservation
Cancel a pending reservation
Set Up Your Envoy MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Envoy 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 Calendar & Scheduling MCP Servers
Outlook Calendar
77+ actions
Planday
69+ actions
Zoom
54+ actions
Cal.com
52+ actions
Deputy
48+ actions
Microsoft Outlook
39+ actions
Calendly
38+ actions
Envoy 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
Envoy MCP Server FAQ
Envoy MCP server vs direct API integration — what's the difference?
A Envoy MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Envoy. A Envoy 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 Envoy at runtime. StackOne provides both.
How does Envoy authentication work for AI agents?
Envoy 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 Envoy account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Envoy MCP tools vulnerable to prompt injection?
Yes — Envoy 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 Envoy agent and how do I avoid it?
Context bloat happens when Envoy tool schemas and API responses eat your Envoy agent's memory, preventing it from reasoning effectively. A single Envoy 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 Envoy agent can access?
Yes — you can limit which actions your Envoy 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 Envoy MCP server?
Yes — you can create custom agent actions for your Envoy MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Envoy's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Envoy MCP server?
Skip a Envoy MCP server if your integration is purely software-to-software — direct Envoy 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 Envoy actions at runtime.
What AI frameworks and AI clients does the StackOne Envoy MCP server support?
The StackOne Envoy 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.