server_upgrade

THE RISK

High Risk

Why server_upgrade needs a policy

This tool executes a software upgrade process on the MCP server itself, running external commands (uvx) to update the server binary/package. It also performs configuration backup and restoration operations. Upgrading live server software is an Execute-category action with high blast radius — a misused or mistimed upgrade could break the running server, cause downtime, or introduce incompatible changes.

From the tool's definition 'Upgrade this MCP server when installed via uvx with automatic configuration backup and restoration'

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

POLICY

How to control server_upgrade

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "server_upgrade": {
      "limits": [
        {
          "counter": "server_upgrade_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

server_upgrade stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Agent Knowledge MCP tools

Destructive delete_document Delete a document from Elasticsearch index by document ID Destructive delete_index Delete an Elasticsearch index and all its documents permanently Destructive delete_index_metadata Delete metadata documentation for an Elasticsearch index Destructive reset_config Reset config.json to defaults from config.default.json (manual reset - overwrites current Execute reload_config Reload configuration from config.json file and reinitialize all components with updated se Execute setup_elasticsearch Auto-setup Elasticsearch using Docker with optional Kibana and force recreate options Write batch_index_directory Batch index all documents from a directory into Elasticsearch with AI-enhanced metadata ge Write index_document Index a document into Elasticsearch with smart duplicate prevention and intelligent docume

All 27 Agent Knowledge MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Agent Knowledge MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about server_upgrade

What does the server_upgrade tool do? +

Upgrade this MCP server when installed via uvx with automatic configuration backup and restoration. It is categorised as a Execute tool in the Agent Knowledge MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on server_upgrade? +

Register the Agent Knowledge MCP server in PolicyLayer and add a rule for server_upgrade: 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 Agent Knowledge MCP. Nothing to install.

What risk level is server_upgrade? +

server_upgrade is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit server_upgrade? +

Yes. Add a rate_limit block to the server_upgrade 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 server_upgrade completely? +

Set action: deny in the PolicyLayer policy for server_upgrade. 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 server_upgrade? +

server_upgrade is provided by the Agent Knowledge MCP server (itshare4u/agentknowledgemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agent Knowledge MCP tool call.

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

CHECK YOUR STACK →