Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

TypeMCP_SERVER
Supported agentsclaude-code, cursor
LicenseSource did not declare a license
Last updated2026-03-02
Quality signal49 / 100
SourceView source

Install

npx metrillm-mcp
Evaluation status

A local static scan is available. This is not an official security certification or benchmark.

Claim this skill (are you the author?)

Similar skills

MCP_SERVER
engram
by HBarefoot
62

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

MCP & Tools / 工具连接器ShellNetworkScanned
MCP_SERVER
61

Pool 18 LLM providers through MCP: ask, panel, tokenmax, route, models, quota, and stats.

MCP & Tools / 工具连接器ShellNetworkScanned
MCP_SERVER
amicus
by BourbonDog
57

Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.

MCP & Tools / 工具连接器ShellNetworkScanned
MCP_SERVER
github-twin
by ChristopherDavenport
55

Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.

MCP & Tools / 工具连接器ShellNetworkScanned
MCP_SERVER
nan-forget
by NaNMesh
55

Long-term memory for AI coding tools via vector search (Qdrant).

MCP & Tools / 工具连接器ShellNetworkScanned