Local Delegate runs on your own machine — the client starts it, so there is no endpoint to ping. 3 666 installs a week from pypi. Last commit 5 Nov 2026.
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
We read the source, 3 d ago · rules 995398eba69f
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.
этот файл ставится пользователю, но в репозитории его нет
proc = subprocess.run(
return os.path.join(cwd, path)
if (txt != null) ranuras[i].innerHTML = txt.split("{v}").join(VERSION);
…de soporte para io.js y corrige versión estable en Python 3. **Version 0.11.1** Restringe sobrescritura de prefijo por .npmrc. **Version 0.11.0** Añade compatibilidad con Python 3, opción `--config-file` y mejora reglas de dpkg. **Version 0.10.0** Añade soporte para archivos …
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 local-delegate -- uvx local-delegate-mcp
{
"mcpServers": {
"local-delegate": {
"command": "uvx",
"args": [
"local-delegate-mcp"
]
}
}
}
[mcp_servers.local-delegate]
command = "uvx"
args = ["local-delegate-mcp"]
{
"mcpServers": {
"local-delegate": {
"command": "uvx",
"args": [
"local-delegate-mcp"
]
}
}
}
{
"servers": {
"local-delegate": {
"type": "stdio",
"command": "uvx",
"args": [
"local-delegate-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
LOCAL_DELEGATE_BASE_URL (OpenAI-compatible endpoint (llama-swap, Ollama, LM Studio, vLLM). Default http://127.0.0.1:9292/v1), LOCAL_DELEGATE_API_KEY (Bearer token for the endpoint, if it requires one).
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
Transcribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.
Delegate coding tasks from Claude Code, Codex or opencode to any model opencode can run.
MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
MCP server mode for Qoder CLI — delegate coding tasks to local Qoder agents from any MCP client.
Delegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Answers built from our own checks of this server.