load_mcp_server_dynamically · MCP Proxy MCP: Risk & Policy

WHAT IT DOES

What load_mcp_server_dynamically does on MCP Proxy

AI agents invoke load_mcp_server_dynamically to trigger actions in MCP Proxy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why load_mcp_server_dynamically needs a policy

The tool name strongly implies it dynamically loads MCP servers at runtime, which is an execution-class operation — it triggers external server processes and integrates new tools into the environment. The server description confirms dynamic loading and hot-reloading of MCP servers. This could expose new attack surfaces or execute arbitrary server code depending on what server is loaded.

From the tool's definition Tool name 'load_mcp_server_dynamically' and server context: 'Enables dynamic loading, hot-reloading, and orchestration of MCP servers without restarting Claude Code, allowing programmatic tool calling and workflow automation across multiple servers.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

load_mcp_server_dynamically Rate-limited

load_mcp_server_dynamically 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Proxy, so you can run agents against it safely.

FAQ

Questions about load_mcp_server_dynamically

What does the load_mcp_server_dynamically tool do? +

load_mcp_server_dynamically. It is categorised as a Execute tool in the MCP Proxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on load_mcp_server_dynamically? +

Register the MCP Proxy MCP server in PolicyLayer and add a rule for load_mcp_server_dynamically: 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 MCP Proxy. Nothing to install.

What risk level is load_mcp_server_dynamically? +

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

Can I rate-limit load_mcp_server_dynamically? +

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

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

load_mcp_server_dynamically is provided by the MCP Proxy MCP server (lizthedeveloper/mcp_proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.