kineti

Name: kineti
Author: therawlogs

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

by therawlogs(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from the official MCP registry - entry io.github.therawlogs/kineti v0.3.4. Ratings and installs below are from this marketplace.

io.github.therawlogs/kineti

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

Packages

npm: kineti @ 0.3.4

Source: https://github.com/therawlogs/kineti

Registry entry: io.github.therawlogs/kineti

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "mcp-io-github-therawlogs-kineti", ...}

Installed into a catalogue, chosen by a router

Install kineti and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

mcp-io-github-therawlogs-kineti.ocm.jsonjson

{
  "ocm": "1",
  "id": "mcp-io-github-therawlogs-kineti",
  "kind": "tool",
  "name": "kineti",
  "description": "Kineti: spend cap, undo, and test proof for AI coding agents",
  "publisher": "therawlogs",
  "version": "0.3.4",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "mcp",
      "mcp-server",
      "npm",
      "mcp-registry"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Kineti: spend cap, undo, and test proof for AI coding agents"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "mcp-registry",
      "repository": "https://github.com/therawlogs/kineti",
      "path": "server.json",
      "ref": "0.3.4",
      "url": "https://github.com/therawlogs/kineti",
      "key": "io.github.therawlogs/kineti",
      "registry": "https://registry.modelcontextprotocol.io"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/mcp-io-github-therawlogs-kineti/manifest?version=0.3.4