Kansei MCP Server

Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes, error resolution, and monthly efficiency reports

Local serverstdioGo

What is the Kansei MCP server?

Kansei MCP server exists for a simple reason — assistants are far more useful when they can act on Kansei directly instead of describing what you should do. Reduce your AI agent's token waste with collective intelligence — SaaS integration recipes, error resolution, and monthly efficiency reports.

What you get

Your agent burns tokens on three things: searching for SaaS docs it could look up locally, retrying errors other agents already solved, and re-reading context it already processed. KanseiLink tackles the first two — and measures all three so you know exactly where your tokens go.

What the assistant can call

Once Kansei is connected, these are the calls the assistant has available:

  • search_services — --
  • lookup — 8 modes
  • report — 4 modes
  • inspect — 8 modes
  • analyze — 4 modes

Setting it up

The server ships on npm as @kansei-link/mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

You will need 2 environment variables: KANSEI_USAGE_HOOK, KANSEI_REPORT_HOOK. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Kansei's toolset — search_services, lookup, report and 2 more — is a fair guide to whether it matches your workflow. It is maintained by kansei-link; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Kansei's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the kansei mcp server does with a few real requests.

Available tools

ToolWhat it does
search_services--
lookup8 modes
report4 modes
inspect8 modes
analyze4 modes

How to install the Kansei MCP server

{
  "mcpServers": {
    "kansei": {
      "command": "npx",
      "args": ["-y", "@kansei-link/mcp-server"],
      "env": {
        "KANSEI_USAGE_HOOK": "your-value",
        "KANSEI_REPORT_HOOK": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
KANSEI_USAGE_HOOKConfiguration value read at startup.Optional
KANSEI_REPORT_HOOKConfiguration value read at startup.Optional

Example prompts to try

  • Use Kansei to search services.
  • Use Kansei to lookup.
  • Use Kansei to report.

Frequently asked questions

It connects Kansei to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (search_services, lookup, report, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Kansei directly.