Medplum MCP
Securely access and manage FHIR healthcare data stored in Medplum.
Finds slow pandas code, checks rewrites give identical results on your data, measures speedups.
作者提供的原文
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 12/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 pandas-doctor。按照 https://mcp.popnx.com/i/furqan-khan07-pandas-doctor.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月20日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server pandas-doctor,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "pandas-doctor": { "command": "uvx", "args": [ "pandas-doctor", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 pandas-doctor 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"pandas-doctor": {
"command": "uvx",
"args": [
"pandas-doctor",
"mcp"
]
}
}
}用 pandas-doctor 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 pandas-doctor,或回答中出现 pandas-doctor 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 pandas-doctor
pandas-doctor 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 pandas-doctor 的应用
B · 诊所与健康 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server pandas-doctor,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user pandas-doctor -- uvx pandas-doctor mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 pandas-doctor 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user pandas-doctor -- uvx pandas-doctor mcp应能看到 pandas-doctor 在列表中并显示已连接
用 pandas-doctor 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 pandas-doctor,或回答中出现 pandas-doctor 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server pandas-doctor,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "pandas-doctor": { "command": "uvx", "args": [ "pandas-doctor", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 pandas-doctor 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
用 pandas-doctor 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 pandas-doctor,或回答中出现 pandas-doctor 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server pandas-doctor,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "pandas-doctor": { "type": "stdio", "command": "uvx", "args": [ "pandas-doctor", "mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 pandas-doctor 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
用 pandas-doctor 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 pandas-doctor,或回答中出现 pandas-doctor 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user pandas-doctor -- uvx pandas-doctor mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"pandas-doctor": {
"command": "uvx",
"args": [
"pandas-doctor",
"mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"pandas-doctor": {
"command": "uvx",
"args": [
"pandas-doctor",
"mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"pandas-doctor": {
"type": "stdio",
"command": "uvx",
"args": [
"pandas-doctor",
"mcp"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 furqan-khan07 验证,该账户拥有此仓库
代码最后更新于昨天
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
OSV.dev 中没有 pandas-doctor@0.1.2 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月16日
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/furqan-khan07-pandas-doctor)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于昨天,最新版本(0.1.2)于8天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Medplum MCP, Mirobody, Codescene MCP Server, Marrow, WHOOP — MissingMCP
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Securely access and manage FHIR healthcare data stored in Medplum.
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
An MCP server that provides CodeScene Code Health analysis tools.
Marrow Health: your Apple Health data over MCP, from the free iOS app. Reads, and writes on demand.
WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.
| 本项 pandas-doctor | Medplum MCP | Mirobody | Codescene MCP Server | Marrow | WHOOP — MissingMCP | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 需要安装在电脑上 | 需要安装在电脑上 | 需要安装在电脑上 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 3/3 | 2/3 | 3/3 | 2/4 |
| 许可证 | MIT | Apache-2.0 | Apache-2.0 | NOASSERTION | MIT | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
pandas-doctor finds the slow pandas lines in your code, rewrites them, and checks on your own data that the result is exactly the same. Then it tells you how much faster the rewrite was, measured, not guessed.
That's a real run on real data: examples/taxi/features.py on January 2024 of the NYC TLC yellow taxi trips (2.96 million rows), with the kind of loops a lot of notebooks have. The script took 96.6 s (M4 Pro, pandas 3.1.0 with pyarrow). pandas-doctor checked 5 rewrites on the script's own data, all identical and faster. After --fix the whole script runs in 1.64 s and prints exactly the same output. Full report in docs/taxi-run-full.txt.
No download needed for examples/hero/features.py, the same script on 1M seeded synthetic trips: 27.9 s before, 1.01 s after (report).
pip install pandas-doctor
pandas-doctor run your_script.py
Or try it in your browser first, nothing to install:
run executes your script normally. Wherever it spots a slow pattern, it copies that code's inputs, lets your code run as usual, then runs the rewrite on the copies and compares the outputs. --diff shows the verified rewrites as a patch, and --fix writes them into the file.
In a notebook:
%load_ext pandas_doctor
%%doctor
for i, row in df.iterrows(): df.at[i, "total"] = row["price"] * row["qty"]
%%doctor --rewrite drops the verified version into a new cell below.
Two results count as identical only when they have:
numpy.float64 is not float)Every check ends in one of four verdicts:
| Verdict | What it means | Does run apply it? |
|---|---|---|
| identical | everything above matches | yes |
| equal values, different scalar types | every value is exactly equal, but some are numpy scalars where the original had Python ones, or the other way round. The report names the types. | yes, and the report says so. --strict-types turns this off. |
| equal within tolerance | floats differ by at most --rtol, usually from summing in a different order. The largest difference is shown. | only with --rtol |
| different | anything else, with the first place it differs | no |
That's stricter than it sounds, and it catches real differences:
iterrows hands you each row as a Series, so an int column turns into floats when the frame also has float columns. The obvious rewrite keeps the ints, and the dtype changes: *different*.row["x"] * 2 into a list gives numpy floats; the same thing via .tolist() gives Python floats: *equal values, different scalar types*. That rarely matters, but it can: json.dumps can't handle a numpy.int64.When the plain rewrite isn't accepted, pandas-doctor tries a few more faithful versions: the row dtype iterrows used, numpy scalars, the same summation order. It keeps the plainest one that's accepted, and between equally plain ones it prefers identical. If none is accepted, it tells you why and changes nothing.
A rewrite that is identical but not faster isn't recommended either. That happens: on python-backed strings, .str.lower() can be slower than .apply(lambda x: x.lower()).
"Verified" always means *on this data*. It's a strong check, not a proof for every possible input.
An assistant can suggest the same rewrites, but it can't tell you whether they give the same result on your data, and as the examples above show, they often don't. pandas-doctor runs both versions and compares them. If you do use an assistant, it can call pandas-doctor to check its own edits (see AI assistants).
| Command | What it does | Runs your code? |
|---|---|---|
pandas-doctor check PATH | Finds slow patterns in .py files and notebooks, prints suggested rewrites. Fast, for CI and pre-commit. | No |
pandas-doctor run script.py | Runs the script, checks each rewrite on its data, times both versions, and can apply the verified ones. | Yes, that's the point |
pandas-doctor verify | Bring your own rewrite: give it the original, the candidate and setup code that builds the inputs. | Only those snippets |
pandas-doctor verify --setup setup.py --original slow.py --candidate fast.py
verify exits 0 when the rewrite is identical or equal up to scalar types, unless you pass --strict-types; --accept-tolerance also lets *equal within tolerance* pass. With --format json (and run --json), the verdict is one of identical, scalar_types, within_tolerance or different, with the details next to it.
| Rule | Slow pattern | Rewrite | Measured, 100k rows | Result |
|---|---|---|---|---|
| PDD001 | for i, row in df.iterrows(): ... | column expression, .sum(), .extend(...) | 1.13 s → 79 µs (14,239x) | identical |
| PDD002 | df.apply(f, axis=1) with column maths | column expression or np.where | 192 ms → 92 µs (2,091x) | identical |
| PDD003 | X = pd.concat([X, part]) in a loop | collect parts, one pd.concat (unsafe fix) | 65.5 ms → 2.3 ms (29x) | identical |
| PDD004 | s.apply(lambda x: ...), .map(lambda ...) | .str / .dt / arithmetic | 27.8 ms → 403 µs (69x) | identical |
| PDD005 | groupby(...).apply(lambda g: g[c].count()) | groupby(...)[c].count() | 4.2 ms → 479 µs (8.8x) | identical |
| PDD006 | per-column astype loop (run only) | one astype call | 102 ms → 111 ms (1.1x slower) | identical |
| PDD007 | df.at[i, c] = ... in a loop over the index | whole-column assignment | 844 ms → 64 µs (13,283x) | identical |
| PDD008 | text columns with few distinct values (run only) | category | memory: 52.8 MB → 1.0 MB on 1M rows | suggestion only |
Measured with benchmarks/ on an Apple M4 Pro, Python 3.13.5, pandas 3.1.0, numpy 2.5.4 (full results for pandas 2.2.3 and with pyarrow are in benchmarks/results/). Each row is one example of the pattern; your speedup depends on your data and what the loop does.
Two results worth knowing:
.apply(lambda x: x.strip().lower()) → .str.strip().str.lower() was 5.6 ms → 8.7 ms (1.5x slower) without pyarrow, but 8.0 ms → 1.9 ms (4.2x) with pyarrow installed. pandas-doctor measures before recommending it.groupby.apply(lambda g: g[c].sum()) → groupby[c].sum() is 5.7 ms → 613 µs (9.3x), but pandas' built-in sum uses compensated summation, so the result matches only to within a relative 2.2e-16. pandas-doctor reports that and only applies it with --rtol.PDD006 and PDD008 need the data, so only run reports them. PDD006 shows up only when one astype call really is faster; on today's pandas releases it usually isn't.
Findings come at two levels:
check exits 1 when it finds one (--exit-zero to only report).iterrows loop that no vectorised rewrite matches, usually one that plots, prints or calls something for each row. All 99 iterrows findings in the corpus check below were like that. Info findings are listed (as notices in the GitHub Action) and never fail check.check --fix never changes behaviour on its own. The concat rewrite (PDD003) is identical only when every part has the same columns and dtypes; the property tests found frames where it isn't. So it's an unsafe fix that needs --unsafe-fixes, and run checks it on your data.
Before release, check was run over 8,419 files from 13 public repos (pandas, statsmodels, Kaggle courses, popular notebook collections) to hunt for false positives. The results and fixes are in docs/corpus.md. Slow lines it found in well-known teaching notebooks, re-measured, are in the speedup gallery.
Fixes found with pandas-doctor and merged into other projects:
| project | change | measured |
|---|---|---|
| pandapower | iterrows + per-row .loc in the different_voltage_levels_connected diagnostic replaced with one vectorised comparison | 2.28 s → 0.9 ms for that check on a 13,797-line grid (case9241pegase); a full pandapower.diagnostic(net) also runs power flows, so the whole call gets a few seconds faster, not thousands of times |
| pandapower | invalid_values diagnostic re-ran iterrows() once per checked column (up to 27 times per table); now builds the rows once per table | 1.77 s → 0.68 s for that check on case9241pegase; the full diagnostic went from 4.1 s to 3.1 s |
| datacompy | row-wise apply in the array-like column comparator replaced with a list comprehension | PandasCompare plus its report on 500k rows: 2.52 s → 0.72 s |
| fairlearn | row-wise apply in BoundedGroupLoss signed weights replaced with Series.map | ExponentiatedGradient fit on 100k rows: 15.1 s → 1.06 s |
pre-commit:
- repo: https://github.com/furqan-khan07/pandas-doctor
rev: v0.1.0 hooks:
GitHub Action. It annotates the diff and keeps one summary comment on the PR:
- uses: furqan-khan07/pandas-doctor@v0.1.0
with: paths: src notebooks
The comment needs permissions: pull-requests: write. check --format json works with anything else.
pandas-doctor mcp serves three tools over MCP: check_code, verify_rewrite and list_rules. Install it with pip install "pandas-doctor[mcp]", or let uvx fetch it. In Claude Code:
claude mcp add pandas-doctor -- uvx --from "pandas-doctor[mcp]" pandas-doctor mcp
In Cursor, Claude Desktop or any other client that takes an mcpServers config:
{
"mcpServers": { "pandas-doctor": { "command": "uvx", "args": ["--from", "pandas-doctor[mcp]", "pandas-doctor", "mcp"] } } }
It's also in the MCP Registry as io.github.furqan-khan07/pandas-doctor.
For Claude Code there's also a plugin with a skill that tells the assistant to verify before claiming a speedup (it uses the CLI through uvx, or the MCP server above if you added it):
/plugin marketplace add furqan-khan07/pandas-doctor
/plugin install pandas-doctor@pandas-doctor
run executes your script once, as python script.py would. Flagged blocks that are plain computation (no files, network or randomness) are re-run on copies to get a stable median. Slower blocks are timed once, during your run, and the report says so.