Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Cal.com MCP server with 52 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Cal.com — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Cal.com MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Cal.com tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Cal.com call.
Tools Discovery →A Cal.com MCP server lets AI agents read and write Cal.com data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Cal.com MCP server ships with 52 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.
Every action from Cal.com's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Get information about the currently authenticated user
Update the authenticated user's profile
Create a new booking
Get all bookings for the authenticated user
Get information about a specific booking
Add an attendee to an existing booking
Get all attendees for a booking
Get a specific attendee for a booking
Create a new event type
Get all event types for the authenticated user
Get information about a specific event type
Update an existing event type
Delete an event type
Create a new availability schedule
Get all schedules for the authenticated user
Get information about a specific schedule
Update an existing schedule
Delete a schedule
Get details of a reserved slot
Update a reserved slot
Delete a slot reservation
Create a new team
Get all teams accessible to the authenticated user
Get information about a specific team
Create a new out of office entry
Update an existing out of office entry
Delete an out of office entry
Create a new webhook
Get all webhooks for the authenticated user
Get details of a specific webhook
Update an existing webhook
Delete a webhook
Get the default conferencing application
Set the default conferencing application
Add guests to an existing booking
Get the default schedule for the authenticated user
Get available time slots for an event type
Get all connected calendars
Get OAuth URL to connect a calendar
Get all out of office entries for the authenticated user
Get all connected conferencing applications
Get OAuth URL to connect a conferencing app
Get URL to connect Stripe account
Cancel an existing booking
Reschedule an existing booking to a new time
Confirm a pending booking
Decline a pending booking request
Reserve a time slot temporarily
Check a calendar connection status
Disconnect a calendar integration
Connect a conferencing application
Disconnect a conferencing application
One endpoint. Any framework. Your agent is talking to Cal.com in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"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>"
]
}
}
}77+ actions
69+ actions
54+ actions
48+ actions
42+ actions
39+ actions
38+ actions
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
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
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
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.