Cakemail API MCP Server
Enables AI assistants to browse, inspect, and call the Cakemail API via dynamically loaded OpenAPI spec.
README
apidoc.mcp.cakemail.com
MCP server that lets AI assistants discover and call the Cakemail API. Loads the OpenAPI specification dynamically and exposes it through three tools for discovery and execution. Deployed on Vercel.
Architecture
api.cakemail.dev/openapi.json → Loaded into memory on first request
↓
MCP Server (Vercel)
├── list_endpoints (browse/search)
├── get_endpoint (full details)
└── call_api (execute)
↑
AI Assistant (Claude, Cursor, etc.)
- Source: OpenAPI spec fetched from
https://api.cakemail.dev/openapi.json - Spec size: ~470KB, 222 operations, 497 schemas
- Transport: MCP Streamable HTTP protocol
MCP Tools
list_endpoints
Browse available API endpoints with optional filters.
| Parameter | Type | Required | Description |
|---|---|---|---|
tag |
string | no | Filter by category (e.g. Campaign, Contact, Account) |
search |
string | no | Search in path, summary, or operationId |
get_endpoint
Get full details for a specific endpoint (parameters, request/response schemas).
| Parameter | Type | Required | Description |
|---|---|---|---|
operationId |
string | no | Endpoint operationId (e.g. listCampaigns) |
path |
string | no | API path (e.g. /campaigns) |
method |
string | no | HTTP method (e.g. GET, POST) |
Provide either operationId or both path + method.
call_api
Read data from the Cakemail API (GET only). Useful for verifying API behavior with real data.
| Parameter | Type | Required | Description |
|---|---|---|---|
path |
string | yes | API path (e.g. /campaigns, /contacts/123) |
query |
object | no | Query parameters as key-value pairs |
Authentication
Two methods are supported:
- Basic Auth — use your Cakemail email and password (recommended for MCP clients)
- Bearer token — admin API key or a Cakemail access token from
/api/auth
Generate your Basic Auth credentials
echo -n 'you@example.com:your-password' | base64
Get a token via /api/auth
curl -X POST https://apidoc.mcp.cakemail.com/api/auth \
-H "Content-Type: application/json" \
-d '{"username":"you@example.com","password":"your-password"}'
Connecting to the MCP Server
Claude Code
claude mcp add cakemail-api \
--transport http \
https://apidoc.mcp.cakemail.com/api/mcp \
--header "Authorization: Basic BASE64_ENCODED_CREDENTIALS"
Any MCP client
{
"mcpServers": {
"cakemail-api": {
"type": "streamable-http",
"url": "https://apidoc.mcp.cakemail.com/api/mcp",
"headers": {
"Authorization": "Basic BASE64_ENCODED_CREDENTIALS"
}
}
}
}
API Endpoints
| Endpoint | Method | Auth | Description |
|---|---|---|---|
/api/mcp |
POST/GET | Basic or Bearer | MCP Streamable HTTP endpoint |
/api/auth |
POST | None | Get access token with Cakemail credentials |
/api/usage |
GET | Admin API key | Tool usage stats. Optional: ?since=2026-03-01&until=2026-03-31 |
Environment Variables
| Variable | Description |
|---|---|
API_KEY |
Admin API key for service authentication |
SUPABASE_URL |
Shared Supabase project URL (same as kb.mcp) |
SUPABASE_SERVICE_KEY |
Supabase service role key |
Development
npm install
npm test # run tests
npm run test:watch # run tests in watch mode
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.