Connect

MCP

Put Navige in front of an MCP server so its tools are governed.

Navige speaks MCP, so an MCP client — Claude Desktop, Claude Code, Cursor, Windsurf, Zed, an AWS AgentCore Gateway target — can point at it directly. Every tool call that client makes is then identified, recorded and decided before it runs.

POST/mcp

Configure a client

The key goes in the query string here, because an MCP client configuration is a URL and has nowhere to put a header.

json

{
  "mcpServers": {
    "navige": {
      "url": "https://api.navige.ai/mcp?api_key=nv_your_key_here"
    }
  }
}

For a client that only speaks stdio, bridge it with mcp-remote:

json

{
  "mcpServers": {
    "navige": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.navige.ai/mcp?api_key=nv_your_key_here"]
    }
  }
}

That URL contains a live credential

It sits in a config file on a laptop, so treat it like any other secret: one key per client, and revoke it rather than reusing it if a machine is lost. Minting another is two clicks.

What happens on a tool call

The call is attributed to the agent that key names.
The kill switch and spend cap apply, on every tier.
Policies are evaluated. On a paid account a deny stops the call and the client is told why; on Watchtower the decision is recorded and the call proceeds.
An approval rule holds the call until someone answers. MCP clients block on a tool call, so this works without any polling.

Claude Code

Claude Code is a first-class caller. Its workflow keys are derived automatically, so a Claude Code session shows up as real jobs on the spend page rather than as a wall of undifferentiated calls.

AWS AgentCore

An AgentCore Gateway can expose tools over MCP. Point a Gateway Target at https://api.navige.ai/mcp and every tool routed through that gateway is governed, with no code to deploy — the configuration is entirely on the AWS side.