Metrillm
by MetriLLMcommunityv0.2.6
5
MetriLLM benchmarks local LLM models, providing performance metrics and quality evaluations with a shareable score and public leaderboard.
From the registry: Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
Install & configure
Prerequisites
- requiredNode.js 20+Node.js version 20 or higher
- requiredLocal LLM runtimeOllama (http://127.0.0.1:11434) or LM Studio (http://127.0.0.1:1234) running locallyhttps://ollama.com/
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `metrillm` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Node.js version 20 or higher
- **Local LLM runtime** — Ollama (http://127.0.0.1:11434) or LM Studio (http://127.0.0.1:1234) running locally (https://ollama.com/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["metrillm-mcp@latest"]
- optional environment variables:
- `OLLAMA_HOST`: Ollama base URL (example: `http://127.0.0.1:11434`)
- `LM_STUDIO_BASE_URL`: LM Studio base URL (example: `http://127.0.0.1:1234`)
- `LM_STUDIO_API_KEY`: LM Studio API key
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Tools (4)
list_models
List locally available LLM models
run_benchmark
Run full benchmark (performance + quality) on a model
get_results
Retrieve previous benchmark results
share_result
Upload a result to the public leaderboard
Environment variables
LM_STUDIO_API_KEYrequiredAPI key for LM Studio backendLM_STUDIO_BASE_URLrequiredBase URL for LM Studio backendPrerequisites
- • Node 20+
Packages
metrillm-mcp
npmv0.2.6transport: stdio
Details
- Language
- TypeScript
- License
- Apache-2.0
- Released
- Mar 16, 2026
- Last commit
- Jun 2, 2026
- Registry name
- io.github.MetriLLM/metrillm
Categories
Related Servers
Claude Flow
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
68.0k
Codebase Memory Mcp
Persistent codebase knowledge graph. Survives session restarts and context compaction.
39.2k
Serena
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
28.1k