Arm Code Mcp

io.github.jean-johnson-zwix由 GitHub 帳號 jean-johnson-zwix 發布v0.1.0更新於 Oct 25, 2026

MCP server for Arm64 Linux performance: parse perf output, suggest NEON intrinsics, audit deps.

已驗證STDIO僅桌面開發者工具資料與分析

概覽

AI 產生的概覽

本機 MCP 伺服器,協助助理最佳化 Arm64 上的 Linux 工作負載:解析 perf 輸出、建議 NEON 內建函式、稽核相依清單。

可以做什麼
解析 perf report 輸出,依開銷排序回傳熱點符號清單並附上警告,可依回傳數量與最低開銷門檻篩選。依熱點迴圈的描述,從含 110 筆項目的精選知識庫建議 NEON SIMD 內建函式,並依目標架構篩選。掃描 requirements.txt、pyproject.toml 或 Dockerfile 內容,標記缺少 arm64 wheel 的套件,分為 error、warning、info 三個等級。三個工具皆離線執行並回傳結構化結果。
適用情境
適用於對 Linux 軟體進行效能分析或移植到 Arm64 時,讓助理解讀 perf 報告、為熱點迴圈挑選 NEON 內建函式,或在建置前檢查 Python 相依套件是否有 arm64 wheel。
執行需求
以本機 stdio 程序執行,通常透過已發布的 Docker 映像啟動,因此需要 Docker;還需要相容 MCP 的用戶端,如 Claude Code、GitHub Copilot 或 Codex。無需驗證或 API 金鑰。選用環境變數 ARM_CODE_MCP_LOG_LEVEL、ARM_CODE_MCP_KB_PATH 與 ARM_CODE_MCP_CACHE_DIR;無設定也可使用。
安裝前請注意
這些工具只對你提供的文字做唯讀分析,未提及網路呼叫。貼上的 perf 報告與相依清單可能包含內部符號名稱、路徑或套件清單,請考量與助理分享的內容。NEON 建議來自固定知識庫,檢索分數普通(hit@1 為 0.667),採用前應自行確認。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Arm Code Mcp,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

arm-code-mcp

An MCP server that helps AI assistants optimize Linux workloads on Arm64. It parses perf report output, recommends NEON SIMD intrinsics for hot loops, and audits Python dependency manifests for arm64 wheel availability — all offline, all structured, all callable from Claude Code, GitHub Copilot, and Codex.


What's inside

  • analyze_perf_output — parse perf report --stdio into a ranked list of hot symbols
  • suggest_neon_intrinsic — semantic + keyword search over 110 curated NEON intrinsics
  • check_arm64_deps — flag packages in requirements.txt, pyproject.toml, or Dockerfile that lack arm64 wheels or require special handling

Prerequisites

  • Docker
  • An MCP-compatible AI assistant (Claude Code, GitHub Copilot, Codex)

Quick start

bash
docker pull jeannjohnson/arm-code-mcp:latest

Add to your MCP client config (e.g. ~/.claude/mcp.json):

json
{  "mcpServers": {    "arm-code-mcp": {      "command": "docker",      "args": ["run", "--rm", "-i", "jeannjohnson/arm-code-mcp:latest"]    }  }}

Restart your client. All three tools are now available.


Tools

analyze_perf_output

Parse raw perf report --stdio output and return the top hot symbols, ranked by overhead.

python
analyze_perf_output(    perf_report_text: str,          # raw stdout of `perf report --stdio`    top_n: int = 10,                # max symbols to return    min_overhead_pct: float = 0.5,  # ignore symbols below this %) -> dict

Example response:

json
{  "summary": {    "total_samples": 5432100,    "total_events": null,    "command": "myapp"  },  "hot_symbols": [    {"overhead_pct": 24.17, "samples": 1245, "command": "myapp",     "module": "myapp", "symbol": "process_buffer"},    {"overhead_pct": 12.34, "samples": 636, "command": "myapp",     "module": "libc-2.31.so", "symbol": "__memcpy_avx_unaligned_erms"}  ],  "warnings": []}

suggest_neon_intrinsic

Recommend NEON intrinsics for a hot loop using hybrid semantic + exact-name retrieval over a curated knowledge base of 110 intrinsics.

python
suggest_neon_intrinsic(    operation_description: str,    # e.g. "32-bit float multiply-accumulate"    target_arch: str = "armv8-a",  # "armv8-a" | "armv8.2-a" | "armv9-a"    top_k: int = 5,) -> dict

Example response:

json
{  "matches": [    {      "intrinsic": "vmlaq_f32",      "signature": "float32x4_t vmlaq_f32(float32x4_t a, float32x4_t b, float32x4_t c)",      "header": "<arm_neon.h>",      "min_arch": "armv8-a",      "description": "Multiply-accumulate: a + (b * c), lane-wise, 4x f32.",      "score": 0.9142    }  ],  "notes": "Filtered to armv8-a. KB contains 110 entries (103 compatible)."}

check_arm64_deps

Scan a dependency manifest and flag packages with known arm64 compatibility issues. Fully offline — no network calls, fast, deterministic.

python
check_arm64_deps(    file_content: str,                    # raw text of the manifest    file_type: str = "requirements.txt",  # "requirements.txt" | "pyproject.toml" | "Dockerfile") -> dict

Example response:

json
{  "checked": ["numpy", "tensorflow", "cupy-cuda12x", "faiss-cpu", "requests"],  "issues": [    {"package": "cupy-cuda12x", "severity": "error",     "message": "GPU-only package with no arm64 wheel. Use cupy with ROCm or a CPU fallback."},    {"package": "tensorflow", "severity": "warning",     "message": "Official TensorFlow PyPI wheels are x86-only before 2.10; use tensorflow-aarch64 or build from source."},    {"package": "faiss-cpu", "severity": "warning",     "message": "No official arm64 wheel on PyPI; build from source or use the conda-forge package."},    {"package": "numpy", "severity": "info",     "message": "arm64 wheels available from PyPI since 1.21.0. Ensure version >= 1.21.0."}  ],  "summary": "Checked 5 package(s): 1 error(s), 2 warning(s), 1 info(s)."}

Severity levels:

LevelMeaning
errorNo arm64 wheel exists (e.g. GPU-only packages)
warningWheel exists but requires a workaround or alternative source
infoWheel available; version constraint or system-lib note applies

Configuration

All env vars are optional. The server works with no configuration.

VariableDefaultDescription
ARM_CODE_MCP_LOG_LEVELINFOLog verbosity: DEBUG, INFO, WARNING
ARM_CODE_MCP_KB_PATHbundled JSONLOverride path to neon_intrinsics.jsonl
ARM_CODE_MCP_CACHE_DIR~/.cache/arm-code-mcpEmbedding cache directory

Pass env vars to the container:

bash
docker run --rm -i \  -e ARM_CODE_MCP_LOG_LEVEL=DEBUG \  jeannjohnson/arm-code-mcp:latest

Evaluation

suggest_neon_intrinsic is evaluated against 15 hand-curated (query, expected intrinsic) pairs using the real all-MiniLM-L6-v2 embedding model. Current baseline:

MetricScore
hit@10.667
hit@30.933
hit@51.000
MRR0.817

The regression guard exits non-zero if hit@3 drops below 0.70.

Run the eval harness locally:

bash
uv syncmake eval

See eval/README.md for methodology and known limitations.


Development

bash
git clone https://github.com/jean-johnson-zwix/arm-code-mcpcd arm-code-mcpuv syncmake test    # 78 testsmake lint    # ruff check + formatmake eval    # real model, 15 gold queries

Makefile targets:

TargetDescription
make setupuv sync + pre-commit install
make testRun the full test suite
make lintruff check + ruff format --check
make evalRun the NEON retrieval eval harness
make docker-buildBuild arm-code-mcp:dev locally
make docker-runRun the local dev image over stdio

Multi-arch images (linux/amd64 + linux/arm64) are built and pushed automatically by .github/workflows/release.yml on v*.*.* tags.


Knowledge base maintenance

The NEON intrinsics knowledge base lives in src/arm_code_mcp/kb/data/neon_intrinsics.jsonl (110 entries). To add intrinsics or refresh after a model upgrade, see docs/kb-refresh.md.


Roadmap

Tools

  • parse_flamegraph — extract hot paths from Linux perf flamegraph SVG
  • suggest_sve2_intrinsic — extend retrieval to SVE2 intrinsics (Neoverse V2, Cortex-X4)

Eval

  • Multi-query paraphrase expansion for each gold pair
  • Reranking pass over semantic candidates
  • Larger gold set (50+ queries) for lower metric variance

Demo

Coming soon.


Contributing

Stars, forks, and issues are welcome. Open a PR or file an issue on GitHub.

Good first issues:

  • Add more NEON intrinsic entries to kb/data/neon_intrinsics.jsonl
  • Add gold eval queries for SVE2 intrinsics
  • Add parse_flamegraph tool for Linux perf flamegraph SVG files

License

Apache 2.0 — same as arm/mcp.

來源:README.md,提交 ead6db8

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 40%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。