// MCP TOOL REFERENCE

METRILLM TOOLS

4 tools from the Metrillm MCP Server, categorised by risk level.

READ TOOLS

get_results Retrieve previously saved benchmark results from ~/.metrillm/results/. Optionally filter by model name. Returns an array of full benchmark result o... list_models List all LLM models available locally on the inference runtime (e.g. Ollama). Returns model name, size, parameter count, quantization, and family.

WRITE TOOLS

share_result Upload a benchmark result to the public MetriLLM leaderboard. Uses official upload defaults; METRILLM_* environment variables can override for self... 2/5

EXECUTE TOOLS

run_benchmark Run an MetriLLM benchmark on a local model. Measures performance (tokens/s, TTFT, memory) and optionally quality (reasoning, math, coding, instruct... 3/5

// FAQ

How many tools does the Metrillm MCP server have? +

The Metrillm MCP server exposes 4 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Metrillm tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Metrillm server.

What risk categories do Metrillm tools fall into? +

Metrillm tools are categorised as Read (2), Write (1), Execute (1). Each category has a recommended default policy.

Enforce policies on Metrillm

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →