Kodiak runs on your own machine — the client starts it, so there is no endpoint to ping. 58 installs a week from npm.
Verifiable fact-checking: verdict, confidence, sources, and a tamper-evident certificate.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 mcp add kodiak -e 'KODIAK_API_KEY=<KODIAK_API_KEY>' -- npx -y kodiak-mcp
{
"mcpServers": {
"kodiak": {
"command": "npx",
"args": [
"-y",
"kodiak-mcp"
],
"env": {
"KODIAK_API_KEY": "<KODIAK_API_KEY>"
}
}
}
}
[mcp_servers.kodiak]
command = "npx"
args = ["-y", "kodiak-mcp"]
env = { KODIAK_API_KEY = "<KODIAK_API_KEY>" }
{
"mcpServers": {
"kodiak": {
"command": "npx",
"args": [
"-y",
"kodiak-mcp"
],
"env": {
"KODIAK_API_KEY": "<KODIAK_API_KEY>"
}
}
}
}
{
"servers": {
"kodiak": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kodiak-mcp"
],
"env": {
"KODIAK_API_KEY": "<KODIAK_API_KEY>"
}
}
}
}
Put your own value in place of
<KODIAK_API_KEY> (Kodiak API key as a Bearer token. Get one at https://azurecarbon.com).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
KODIAK_URL (API base URL (default https://azurecarbon.com)).
AI product expert answering from live source code, with sources and a verification status.
Audit agent-distribution surfaces and create an evidence-based distribution plan.
Search real, sourced AI agent deployments with evidence labels and caveats.
Browser-local and CLI static evidence for deployed AI model artifacts.
Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.
Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.
Cloud architecture and migration planning with costs, controls, evidence, and deployable IaC.
Azure + GCP cost management: spending, forecasts, anomalies, budgets, idle resources, and tags.
Answers built from our own checks of this server.