caddy_upstreams

THE RISK

Low Risk

Why caddy_upstreams needs a policy

The caddy_upstreams tool queries and returns monitoring/status data about reverse proxy upstreams. It retrieves existing state without creating, modifying, deleting, or executing operations. This is a read-only diagnostic tool, making it Read category with low severity since exposure poses minimal risk — an AI querying upstream health status cannot damage infrastructure or cause unintended operational changes.

From the tool's definition Tool description states it 'Get[s] the current health status' and 'Shows address, active requests, and failure counts' — purely informational retrieval with no modifications or side effects.

Documented attack patterns abuse exactly the kind of access caddy_upstreams gives an agent:

POLICY

How to control caddy_upstreams

PolicyLayer is an MCP gateway — it sits between your AI agents and Caddy, and nothing reaches the server without passing your rules. This is the rule we recommend for caddy_upstreams:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "caddy_upstreams": {}
  }
}

caddy_upstreams is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Caddy — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Caddy tools

Destructive caddy_config_delete Delete config at a JSON path. Removes the config node at the specified path. Deleting a pa Destructive caddy_remove_route Remove a route. Target by @id (preferred — stable across reorderings) or by array index on Destructive caddy_load Replace the entire Caddy configuration atomically. Accepts a JSON config object, or a Cadd Execute caddy_stop Gracefully shut down the Caddy server. Requires confirm=true to prevent accidental shutdow Write caddy_add_route Add a route with full control over match conditions and handlers. Supports any Caddy handl Write caddy_config_set Write config at a JSON path. Mode Write caddy_reverse_proxy Add a reverse proxy route. The most common operation — just specify where traffic comes fr Write caddy_revert Manage config snapshots for rollback. Snapshots are auto-captured before caddy_load and ke

All 18 Caddy tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about caddy_upstreams

What does the caddy_upstreams tool do? +

Get the current health status of all reverse proxy upstreams. Shows address, active requests, and failure counts. It is categorised as a Read tool in the Caddy MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on caddy_upstreams? +

Register the Caddy MCP server in PolicyLayer and add a rule for caddy_upstreams: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Caddy. Nothing to install.

What risk level is caddy_upstreams? +

caddy_upstreams is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit caddy_upstreams? +

Yes. Add a rate_limit block to the caddy_upstreams rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block caddy_upstreams completely? +

Set action: deny in the PolicyLayer policy for caddy_upstreams. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides caddy_upstreams? +

caddy_upstreams is provided by the Caddy MCP server (yawlabs/caddy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Caddy tool call.

Start from Caddy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →