MCP-I Integration
MCP-I Integration
IDA extends the Model Context Protocol (MCP) with cryptographically verifiable identity and delegation — called MCP-I (MCP with Identity). This ensures that every tool call made by an AI agent through MCP carries provenance and authorization proof.
What is MCP?
The Model Context Protocol (MCP) is a standard protocol for connecting AI models to external tools and data sources. It defines how an AI model can:
- Discover available tools
- Invoke tools with parameters
- Receive structured results
What MCP-I Adds
Architecture
MCP-I Request Format
Standard MCP tool call with IDA identity headers:
MCP-I Response Format
Standard MCP response with audit receipt:
Setting Up MCP-I Server
Tool Registration with Scope Requirements
Middleware: Identity Verification
Audit Receipts
Every MCP-I tool call generates a signed audit receipt:
Audit receipts are:
- Signed by the MCP-I server’s DID key
- Stored on-chain (hash) and off-chain (full receipt)
- Queryable via the Agent Audit Trail API
- Used as input signals for trust score computation
Human-in-the-Loop (HITL)
For high-risk tool calls, MCP-I can require real-time human approval:
Migration from Standard MCP
To add IDA identity to an existing MCP server:
- Install the
@ida/mcp-imiddleware package - Register the server’s DID on the ADI blockchain
- Add
idanamespace to MCP request/response handlers - Configure required scopes for each tool
- Enable audit receipt generation