MCP Hangar runs on your own machine — the client starts it, so there is no endpoint to ping. 1 984 installs a week from pypi. Last commit 17 Sep 2026.
Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.
We read the source, 23 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.
elapsed = now - self.last_update
self.tokens = min(self.capacity, self.tokens + elapsed * self.rate)
result = subprocess.run(
self._env = dict(env) if env is not None else dict(os.environ)
"docker": "/var/run/docker.sock",
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 hangar -- uvx mcp-hangar
{
"mcpServers": {
"hangar": {
"args": [
"mcp-hangar"
],
"command": "uvx"
}
}
}
[mcp_servers.hangar]
command = "uvx"
args = ["mcp-hangar"]
{
"mcpServers": {
"hangar": {
"args": [
"mcp-hangar"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"hangar": {
"args": [
"mcp-hangar"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
MCP_CONFIG (Path to config.yaml declaring the upstream MCP servers and policy. Without it Hangar starts on a demo config that serves no real upstream.).
The author declared them in the registry entry; get the values from the project itself.
Credential enforcement middleware for MCP servers — verifies scoped tokens on every tool call
Deterministic policy enforcement and MCP management for AI agent tool calls.
Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.
AI governance MCP server for policy enforcement, cost control, and observability.
Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Self-hostable policy control plane for AI coding agents.
Self-hosted MCP server for AI agent trading on Polymarket prediction markets
Answers built from our own checks of this server.