Skip to main content

MCP server for Ascend Profiler (msprof) analysis

Project description

msprof mcp

简介

msprof mcp 是一个基于 Model Context Protocol (MCP) 的服务器,旨在为大语言模型 (LLM) 提供分析 Ascend PyTorch Profiler 采集性能数据的能力。通过一系列内置工具,它可以帮助用户快速定位性能瓶颈、分析算子耗时、查看通信开销以及进行 Trace 数据的深度查询。

目录结构

msprof_mcp/
├── pyproject.toml            # 项目配置文件 (build-system, dependencies)
├── src/
│   └── msprof_mcp/
│       ├── __init__.py
│       ├── server.py                 # MCP 服务器入口
│       └── tools/                    # 工具包
│           ├── msprof_analyze_cmd.py
│           ├── csv_analyze.py
│           ├── json_analyze.py
│           └── trace_view/
└── README.md

MCP 能力说明

本服务提供以下核心能力,支持多维度性能数据分析。您可以直接在对话中使用自然语言(如示例 Prompt)来调用这些工具。

1. 总体分析 (msprof-analyze)

工具名称 描述 示例 Prompt
msprof_analyze_advisor 调用 msprof-analyze advisor 提供全方位性能建议(计算/调度瓶颈)。 "分析 /path/to/data 目录下的性能数据,找出主要瓶颈。"

2. TimeLine 分析 (trace_view)

工具名称 描述 示例 Prompt
analyze_overlap 分析计算、通信与调度的重叠情况,判断负载特征(计算/通信密集型)。 "分析 /path/to/trace_view.json 的计算和通信重叠情况。"
find_slices 搜索 Trace 中的特定 Slice(算子/函数),支持模糊匹配和时间范围过滤。 "在 /path/to/trace_view.json 中查找所有 'MatMul' 算子。"
execute_sql_query 执行自定义 SQL 查询,支持 Slice/Thread/Process 等表的深度分析。 "对 /path/to/trace_view.json 执行 SQL 查询,统计耗时超过 1ms 的 Slice 数量。"

3. 算子性能分析 (CSV)

工具名称 描述 示例 Prompt
analyze_kernel_details 分析 kernel_details.csv,提供耗时分布、Top N 算子、设备分布等。 "分析 /path/to/kernel_details.csv,列出耗时最长的 10 个算子。"
get_operator_details 查询特定算子(按名称或类型)的详细执行信息。 "从 /path/to/kernel_details.csv 中获取 'FlashAttention' 算子的详细信息。"
analyze_op_statistic 分析 op_statistic.csv,提供调用次数、总耗时及 Core 类型分布。 "统计 /path/to/op_statistic.csv 中的算子调用次数和总耗时。"
get_op_type_details 查询特定类型算子或 Core 类型算子的详细统计数据。 "查看 /path/to/op_statistic.csv 中所有 'AI_CORE' 类型的算子统计。"
search_csv_by_field 通用 CSV 字段搜索工具,支持按列值过滤。 "在 /path/to/file.csv 的 'Name' 列中搜索包含 'Conv' 的行。"

4. 通信性能分析 (JSON)

工具名称 描述 示例 Prompt
analyze_communication 分析 communication_matrix.json,识别 P2P/集合通信瓶颈及慢链路。 "分析 /path/to/communication_matrix.json,找出带宽利用率低的链路。"
analyze_communication_trace 分析 communication.json,提供通信操作的时间分解(Transit, Wait)和带宽详情。 "分析 /path/to/communication.json,查看通信操作的等待时间分布。"

5. 配置信息查询

工具名称 描述 示例 Prompt
get_profiler_config 获取 profiler_info.json 中的配置信息(版本、软硬件环境)。 "读取 /path/to/profiler_info.json,查看 Profiler 配置版本。"

6. SQL执行

工具名称 描述 示例 Prompt
execute_sql 执行只读 SQL 并返回结果,当结果行数/返回字符数超阈值时会返回失败并提示收敛查询。 "对 /path/to/ascend_pytorch_profiler.db 执行 SQL:SELECT name, SUM(total_time) AS total FROM COMPUTE_TASK_INFO GROUP BY name LIMIT 20。"
execute_sql_to_csv 执行只读 SQL 并将全量结果保存为 CSV,只返回导出状态、路径和行数,不返回查询结果内容。 "将 /path/to/ascend_pytorch_profiler.dbSELECT * FROM TASK WHERE taskType='AI_CORE' 的结果导出到 /tmp/op_statistic_ai_core.csv。"

快速开始

方式一:直接运行 (PyPI)

如果您已安装 uv,可以直接运行以下命令启动服务:

uvx msprof-mcp

方式二:本地开发运行

# 1. 克隆代码仓库
git clone <repository_url>
cd msprof_mcp

# 2. 运行服务
uv run msprof-mcp

集成方法

集成到 Cherry Studio / Claude Desktop

在 MCP 配置 JSON 中添加如下配置。建议优先使用 PyPI 版本。

1. 使用 PyPI 版本 (推荐)

{
  "mcpServers": {
    "msprof-mcp": {
      "name": "msprof_mcp",
      "description": "msprof mcp server",
      "command": "uvx",
      "args": [
        "msprof-mcp"
      ],
      "env": {},
      "isActive": true,
      "type": "stdio"
    }
  }
}

2. 使用本地源码 (开发调试)

{
  "mcpServers": {
    "msprof-mcp-local": {
      "name": "msprof_mcp_local",
      "description": "msprof mcp server (local)",
      "command": "uv",
      "args": [
        "run",
        "msprof-mcp"
      ],
      "cwd": "/absolute/path/to/msprof_mcp", 
      "env": {},
      "isActive": true,
      "type": "stdio"
    }
  }
}

注意:使用本地源码时,请将 cwd 修改为您的实际项目路径。

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

msprof_mcp-0.1.4.tar.gz (26.8 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

msprof_mcp-0.1.4-py3-none-win_amd64.whl (4.6 MB view details)

Uploaded Python 3Windows x86-64

msprof_mcp-0.1.4-py3-none-manylinux_2_34_x86_64.whl (4.7 MB view details)

Uploaded Python 3manylinux: glibc 2.34+ x86-64

msprof_mcp-0.1.4-py3-none-manylinux_2_23_aarch64.whl (4.5 MB view details)

Uploaded Python 3manylinux: glibc 2.23+ ARM64

msprof_mcp-0.1.4-py3-none-macosx_15_0_x86_64.whl (4.6 MB view details)

Uploaded Python 3macOS 15.0+ x86-64

msprof_mcp-0.1.4-py3-none-macosx_15_0_arm64.whl (4.2 MB view details)

Uploaded Python 3macOS 15.0+ ARM64

File details

Details for the file msprof_mcp-0.1.4.tar.gz.

File metadata

  • Download URL: msprof_mcp-0.1.4.tar.gz
  • Upload date:
  • Size: 26.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for msprof_mcp-0.1.4.tar.gz
Algorithm Hash digest
SHA256 4a96d756aed8518aaa0c9b88da9d1e47d4ac1495d2587695db91c1613c02a307
MD5 e39d5159939d03658e00238f55441b04
BLAKE2b-256 7d665abb1b9838b34a4d9af417023ac33a055e97810874007172235442099819

See more details on using hashes here.

Provenance

The following attestation bundles were made for msprof_mcp-0.1.4.tar.gz:

Publisher: publish-release.yml on kali20gakki/msprof-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file msprof_mcp-0.1.4-py3-none-win_amd64.whl.

File metadata

  • Download URL: msprof_mcp-0.1.4-py3-none-win_amd64.whl
  • Upload date:
  • Size: 4.6 MB
  • Tags: Python 3, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for msprof_mcp-0.1.4-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 86659ded14ab2ec5be86a68faa2346069c16e2e11b47b23a9a81f64ab1997a4f
MD5 f5e44c5b6e4c118e61d64dddad4d4d49
BLAKE2b-256 309b3e930b337daef12ef58d610319a640bdf86635e2bdf3242c4c180adca3ae

See more details on using hashes here.

Provenance

The following attestation bundles were made for msprof_mcp-0.1.4-py3-none-win_amd64.whl:

Publisher: publish-release.yml on kali20gakki/msprof-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file msprof_mcp-0.1.4-py3-none-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for msprof_mcp-0.1.4-py3-none-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 dd4e0fe49a3826e7c27de741aea0c5e1d0855cef94d1437834bf068789ff1e3d
MD5 4956e9bf853b60cbe58438fa95e366c4
BLAKE2b-256 bca0096addeffa60100ca726a34a61a4f18d9c4f7d474ade5865ce90f471818b

See more details on using hashes here.

Provenance

The following attestation bundles were made for msprof_mcp-0.1.4-py3-none-manylinux_2_34_x86_64.whl:

Publisher: publish-release.yml on kali20gakki/msprof-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file msprof_mcp-0.1.4-py3-none-manylinux_2_23_aarch64.whl.

File metadata

File hashes

Hashes for msprof_mcp-0.1.4-py3-none-manylinux_2_23_aarch64.whl
Algorithm Hash digest
SHA256 ceae6db8febe08dcfb7ad2ee83e1448795503b91b866eefc9c26d31d64058db6
MD5 b8bd5b4864fc2a215b339daca52a1c0d
BLAKE2b-256 64a1d3aa2fde0d22be188299332d6e16787820237206a19058e5a5882ea1df1d

See more details on using hashes here.

Provenance

The following attestation bundles were made for msprof_mcp-0.1.4-py3-none-manylinux_2_23_aarch64.whl:

Publisher: publish-release.yml on kali20gakki/msprof-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file msprof_mcp-0.1.4-py3-none-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for msprof_mcp-0.1.4-py3-none-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 b16ddc9bb4b609f2e879531de9155b07ee1f3b2c527822e7f33b899920d2865e
MD5 9d283ab464af91f8ee7610d646fa6c34
BLAKE2b-256 5a38400c70d08d6483534d0f30ffd90ab0e0e6fe8cefb22ee561e6d6991dd97c

See more details on using hashes here.

Provenance

The following attestation bundles were made for msprof_mcp-0.1.4-py3-none-macosx_15_0_x86_64.whl:

Publisher: publish-release.yml on kali20gakki/msprof-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file msprof_mcp-0.1.4-py3-none-macosx_15_0_arm64.whl.

File metadata

File hashes

Hashes for msprof_mcp-0.1.4-py3-none-macosx_15_0_arm64.whl
Algorithm Hash digest
SHA256 4654615d96ba5584125f804514f17ec76ba74911f966fa7033b80c84f1971b28
MD5 58b61f7acf16ca914560dcc2362a04b4
BLAKE2b-256 21088978e84181868942f09e4c1704fe3ca17403e3693f090e614033a2d7dd3a

See more details on using hashes here.

Provenance

The following attestation bundles were made for msprof_mcp-0.1.4-py3-none-macosx_15_0_arm64.whl:

Publisher: publish-release.yml on kali20gakki/msprof-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page