Otterkit MCP Server

by useotterkit Your server? Claim it

local only

Otterkit runs on your own machine — the client starts it, so there is no endpoint to ping. 46 installs a week from npm. Last commit 13 Aug 2026.

Tunnels and webhooks for AI agents: capture, await, verify, replay, and send signed test events.

Installs per day peak 141 · avg 20 · -33% w/w

a month agotoday

Installs / week

npm · otterkit

Stars

0 open issues

13 Aug 2026

Last commit

10 releases in 90 days

MIT

License

language unknown

Nothing serious here today

Today is the operative word: we check Otterkit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add otterkit -- npx -y otterkit

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "otterkit": {
      "command": "npx",
      "args": [
        "-y",
        "otterkit"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.otterkit]
command = "npx"
args = ["-y", "otterkit"]

.cursor/mcp.json

{
  "mcpServers": {
    "otterkit": {
      "command": "npx",
      "args": [
        "-y",
        "otterkit"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "otterkit": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "otterkit"
      ]
    }
  }
}

Alternatives to Otterkit

same job, measured the same way

Hooklistener

by hooklistener

Webhook, email, WebSocket and tunnel testing for AI agents: capture, wait, verify, replay.

answering

Enoki

by enokilabs

Test your AI agents for security and safety weaknesses, and re-verify the fixes.

answering

WebhookTest.net

by webhooktest

Anonymous webhook capture, inspection, waiting, and response configuration for AI agents.

8 tools answering

Sendora

by sendora

Sendora's docs and API for coding agents: send test mail, read the log, set up webhooks.

300 installs/wk 2 tools answering

TestChimp

by testchimp

QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.

849 installs/wk answering

FailTrace

by lbarimi

Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.

129 installs/wk local only

Agent Verifier

by packet

Test and debug your AI agent's Web Bot Auth (RFC 9421) signature: is it valid, and what to fix?

1 tools answering

Kineti

by therawlogs

Kineti: spend cap, undo, and test proof for AI coding agents

567 installs/wk local only

Otterkit — questions

Answers built from our own checks of this server.

Why is there no uptime for Otterkit?

Otterkit runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package otterkit was installed 46 times last week.

How do I connect Otterkit?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls otterkit straight from npm; nothing to host, nothing to sign up for.

How many people use Otterkit?

The npm package otterkit was installed 46 times in the last week. Week over week that is -33%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Otterkit open source?

Yes — it is published under the MIT licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.