Local Coding Agent runs on your own machine — the client starts it, so there is no endpoint to ping. 458 installs a week from pypi. Last commit 21 Oct 2026.
Delegate small coding tasks to local Ollama/llama.cpp models; patches gated by real test runs.
We read the source, 3 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
cp = subprocess.run(
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.
cp = subprocess.run(
shell=True,
exec(compile(source, str(path), "exec"), namespace)
for p in workspace.rglob("*"):
spawn_env = dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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-coding-agent -- uvx local-coding-agent
{
"mcpServers": {
"local-coding-agent": {
"command": "uvx",
"args": [
"local-coding-agent"
]
}
}
}
[mcp_servers.local-coding-agent]
command = "uvx"
args = ["local-coding-agent"]
{
"mcpServers": {
"local-coding-agent": {
"command": "uvx",
"args": [
"local-coding-agent"
]
}
}
}
{
"servers": {
"local-coding-agent": {
"type": "stdio",
"command": "uvx",
"args": [
"local-coding-agent"
]
}
}
}
Code changes and unit tests by local MLX models, behind a gate a machine can run.
MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.
Read-only MCP server: a coding agent reads test sessions recorded in QA Wrap. Local only.
Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Finds real dead code and proposes a safe, test-gated branch+PR to remove it.
End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.
Answers built from our own checks of this server.