Cheaplane runs on your own machine — the client starts it, so there is no endpoint to ping. 80 installs a week from pypi. Last commit 16 Aug 2026.
Offload grunt work from your premium agent to cheap models — auto-routing and billing isolation.
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
params = StdioServerParameters(command=PY, args=[SERVER], env=dict(os.environ))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 cheaplane -- uvx cheaplane
{
"mcpServers": {
"cheaplane": {
"args": [
"cheaplane"
],
"command": "uvx"
}
}
}
[mcp_servers.cheaplane]
command = "uvx"
args = ["cheaplane"]
{
"mcpServers": {
"cheaplane": {
"args": [
"cheaplane"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"cheaplane": {
"args": [
"cheaplane"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
DELEGATE_BASE_URL (OpenAI-compatible endpoint serving the cheap models — usually a local LiteLLM proxy.), DELEGATE_API_KEY (Key for that endpoint. A local proxy ignores it; set a real one for a hosted endpoint.), DELEGATE_TIMEOUT (Per-call timeout in seconds. Raise it for long documents.), DELEGATE_MODEL_MAP (JSON remapping the built-in aliases to your proxy's model names, e.g. {"deepseek": "deepseek-v4"}.), DELEGATE_NO_LOG (Set to 1 to disable the local savings ledger (metadata only, never task content).).
The author declared them in the registry entry; get the values from the project itself.
Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
Plan agent workload routes from evaluation and cost data. $1 USDC per plan; modeled savings only.
Give your AI agents the tools to build, manage, and run automation workflows.
Build and run visual creative-production workflows from your AI agent.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Let your coding agent write to your work tracker: issues, branches, PRs and CI, one contract.
Try other agents, models, and skills from your familiar AI workflow through a local MCP server
See each coding-agent subscription's live limits and offload work to one with headroom.
Answers built from our own checks of this server.