ProofFlow runs on your own machine — the client starts it, so there is no endpoint to ping. 71 installs a week from pypi. Last commit 20 May 2026.
Audit infrastructure for AI coding agents with evidence-backed review and policy gates.
We read the source, 20 h ago · rules 3dff92dd89df
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.
result = 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.
этот файл ставится пользователю, но в репозитории его нет
result = subprocess.run(
absPath = path.join(folders[0].uri.fsPath, relPath);
ENV VITE_PROOFFLOW_API_KEY=$VITE_PROOFFLOW_API_KEY
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 proofflow -- uvx proofflow-mcp
{
"mcpServers": {
"proofflow": {
"args": [
"proofflow-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.proofflow]
command = "uvx"
args = ["proofflow-mcp"]
{
"mcpServers": {
"proofflow": {
"args": [
"proofflow-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"proofflow": {
"args": [
"proofflow-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
PROOFFLOW_BASE_URL (ProofFlow backend URL (default: http://127.0.0.1:8787)), PROOFFLOW_API_KEY (API key for authenticated access to the ProofFlow backend).
The author declared them in the registry entry; get the values from the project itself.
Security reviews for coding agents: diffs checked against your org policy and live infrastructure.
Browser-backed QA with evidence and fix-ready reports for coding agents.
Local proof facts for AI coding clients: intent, tests, Graph Ops, and review evidence.
Evidence-backed web research for AI agents with citations and confidence scores.
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
Colter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.
Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.
Evidence-backed npm upgrade preflight and dependency audits for coding agents, paid via x402.
Answers built from our own checks of this server.