NM Hard Tools
OfficialNM Hard Tools
엄격한 추론 평가 및 벤치마킹을 위한 배포 가능한 무상태 MCP 서비스입니다. 이 저장소는 서비스 구현, 컨테이너 이미지, Helm 차트를 관리합니다.
포함된 서비스:
프로파일링된
lm-evaluation-harness컨트롤러 및 워커;vLLM forward-pass 벤치마크 서비스용 제한된 MCP 어댑터;
lm-eval, forward-pass, Nyann, AgentX용 배포 차트.
개발
uv run --extra test pytest
uv run --extra test ruff format --check src tests
uv run --extra test ruff check src tests저장소 거버넌스는 gov/에 저장되며 govctl로 검증됩니다:
cargo install govctl --version 0.19.1 --locked
govctl status
govctl checklm-eval 이미지는 명시적인 Python 기본 이미지로 빌드되어야 합니다:
podman build -f Dockerfile.lm-eval-service \
--build-arg BASE_IMAGE=python:3.12-slim -t inference-hard-lm-eval:dev .Related MCP server: ArmBench MCP Server
라이선스
Apache License, Version 2.0에 따라 라이선스가 부여됩니다. LICENSE를 참조하세요.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Benchmark-first release surface with a read-only MCP endpoint and operator CLI.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceEnables running LLM evaluations, experiments, and custom evaluators through a standardized MCP interface.16Apache 2.0- AlicenseNot gradedqualityDmaintenanceEnables benchmarking and inference of LLMs on Arm64 cloud instances with KleidiAI optimizations, providing an MCP-compatible API for serving results.1MIT

Local AI MCPofficial
AlicenseAqualityCmaintenanceUnified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.1617 npmCreative Commons Attribution Non Commercial No Derivatives 4.0 International- AlicenseNot gradedqualityBmaintenanceEnables benchmarking of local LLM models (performance and quality) and sharing results to a public leaderboard via MCP tools.4 npm8Apache 2.0