llm_test_capabilities · LLM MCP Bridge MCP: Risk & Policy

WHAT IT DOES

What llm_test_capabilities does on LLM MCP Bridge

AI agents invoke llm_test_capabilities to trigger actions in LLM MCP Bridge. 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 llm_test_capabilities needs a policy

The tool actively tests/runs prompts against an external LLM API across multiple capability areas (reasoning, code, creativity, facts, instructions). This triggers external API calls and executes test operations, placing it in the Execute category. The severity is medium as misuse could incur API costs or trigger unintended code generation, but blast radius is limited to the LLM API context.

From the tool's definition 'Prueba las capacidades del modelo en diferentes áreas: razonamiento, código, creatividad, hechos, instrucciones' — runs active capability tests against an LLM model across multiple domains including code execution

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

llm_test_capabilities Rate-limited

llm_test_capabilities 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": {
    "llm_test_capabilities": {
      "limits": [
        {
          "counter": "llm_test_capabilities_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 LLM MCP Bridge, so you can run agents against it safely.

FAQ

Questions about llm_test_capabilities

What does the llm_test_capabilities tool do? +

Prueba las capacidades del modelo en diferentes áreas: razonamiento, código, creatividad, hechos, instrucciones. It is categorised as a Execute tool in the LLM MCP Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on llm_test_capabilities? +

Register the LLM MCP Bridge MCP server in PolicyLayer and add a rule for llm_test_capabilities: 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 LLM MCP Bridge. Nothing to install.

What risk level is llm_test_capabilities? +

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

Can I rate-limit llm_test_capabilities? +

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

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

llm_test_capabilities is provided by the LLM MCP Bridge MCP server (ramgeart/llm-mcp-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.