Valca runs on your own machine — the client starts it, so there is no endpoint to ping. 189 installs a week from pypi. Last commit 10 Oct 2026.
Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.
We read the source, 1 d ago · rules ccca72095570
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
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.
result = subprocess.run(
" ~/.aws/scoped/<project>.credentials:/home/appuser/.aws/credentials:ro\n"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Valca and you get told the day something new turns up.
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 valca -- uvx valca
{
"mcpServers": {
"valca": {
"args": [
"valca"
],
"command": "uvx"
}
}
}
[mcp_servers.valca]
command = "uvx"
args = ["valca"]
{
"mcpServers": {
"valca": {
"args": [
"valca"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"valca": {
"args": [
"valca"
],
"command": "uvx"
}
}
}
Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Read-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
Create and manage secure sandboxes for running AI agent code
Validates AI-generated Python: syntax, lint, security scan and deterministic repair.
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Read-only guidance and report templates for reviewing application security with your own agent.
Answers built from our own checks of this server.