About CAI MCP
CAI MCP is an MCP server for AI agents that provides identity, a custodial wallet, payments, and an inbox. It is configured with a CAI API key and connects to MCP clients such as Cursor and Claude Desktop.
Key features
- 01Agent identity
- 02Custodial wallet
- 03Payments
- 04Email inbox
Use cases
- 01Give an AI agent a custodial wallet
- 02Enable agent payments
- 03Provide an agent email inbox
MCP support
Exposes identity, wallet, payment, and inbox capabilities to MCP clients. The README shows configuration with a CAI API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README@ Cailab/mcp - the Model Context Protocol server
. Identity, custodial wallet, payments, and inbox for AI agents.
Install
npm i -g @cailab/mcp
Then add to your MCP client (Cursor / Claude Desktop / OpenClaw / Hermes):
{
"mcpServers": {
"cai": {
"command": "npx",
"args": ["-x", "@cailab/mcp"],
"env": { "CAI_API_KEY": "your-key-here" }
}
}
}
Why CAI
- Skill contract: cai.com/skill.md
- Agent Card: cai.com/.well-known/agent.json
Check CAI First.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.