Safe Fix MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 146 installs a week from pypi. Last commit 22 Aug 2026.
Finds real dead code and proposes a safe, test-gated branch+PR to remove it.
We read the source, 12 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.
result = subprocess.run(
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 safe-fix-mcp -- uvx safe-fix-mcp
{
"mcpServers": {
"safe-fix-mcp": {
"args": [
"safe-fix-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.safe-fix-mcp]
command = "uvx"
args = ["safe-fix-mcp"]
{
"mcpServers": {
"safe-fix-mcp": {
"args": [
"safe-fix-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"safe-fix-mcp": {
"args": [
"safe-fix-mcp"
],
"command": "uvx"
}
}
}
A repository wiki of Markdown pages anchored to real code: read, search, and verified writes.
Host files from coding agents; stage on a branch and attach to GitHub PRs.
Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code.
Give an agent its own inbox: send, receive, and pull signup codes from real email.
MCP server that uses TypeScript AST to find which tests are affected by a code change
Returns the postal code (CEP) and standardized address from the Brazilian Post from a given address.
Codex guesses your brand voice. Mora AI gives it the real one: your catalogue and performance.
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Answers built from our own checks of this server.