MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Messy CSV, JSON, Excel, SPSS/Stata/SAS and PDF tables to typed Parquet; inspect, query, join.
教 AI 做这类工作的 Skill,可与本项一起使用
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
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 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 20/100 |
质量: 基础检查通过 5/5 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 AImart Parquet。按照 https://mcp.popnx.com/i/balogvn-aimart-parquet.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 5/5 项检查 · 你的提问会经过开发者的服务器(balogvn--aimart-parquet.us-east.modal.run) · ✓ 命令已检查 2026年11月18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 · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
AImart Parquethttps://balogvn--aimart-parquet.us-east.modal.run/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsAImart Parquet
用 AImart Parquet 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 AImart Parquet,或回答中出现 AImart Parquet 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
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
AImart Parquethttps://balogvn--aimart-parquet.us-east.modal.run/mcp开启新聊天,输入前先从插件列表中选择 AImart Parquet
用 AImart Parquet 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 AImart Parquet,或回答中出现 AImart Parquet 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 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user aimart-parquet https://balogvn--aimart-parquet.us-east.modal.run/mcp应能看到 AImart Parquet 在列表中并显示已连接
用 AImart Parquet 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 AImart Parquet,或回答中出现 AImart Parquet 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 · 约 2 分钟
不需要密钥,不用安装程序
用 AImart Parquet 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 AImart Parquet,或回答中出现 AImart Parquet 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 · 约 2 分钟
不需要密钥,不用安装程序
用 AImart Parquet 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 AImart Parquet,或回答中出现 AImart Parquet 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
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://balogvn--aimart-parquet.us-east.modal.run/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user aimart-parquet https://balogvn--aimart-parquet.us-east.modal.run/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"aimart-parquet": {
"url": "https://balogvn--aimart-parquet.us-east.modal.run/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"aimart-parquet": {
"type": "http",
"url": "https://balogvn--aimart-parquet.us-east.modal.run/mcp"
}
}
}Claude Code
claude mcp add --scope user aimart-parquet -- uvx aimart-parquet mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"aimart-parquet": {
"command": "uvx",
"args": [
"aimart-parquet",
"mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"aimart-parquet": {
"command": "uvx",
"args": [
"aimart-parquet",
"mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"aimart-parquet": {
"type": "stdio",
"command": "uvx",
"args": [
"aimart-parquet",
"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。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
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
工具名称和描述与服务器在 2026年11月17日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
convert_to_parquetConvert a messy data file into clean, typed, zstd-compressed Parquet. Use this first for any CSV/TSV, JSON/NDJSON, Excel, SPSS, Stata or SAS file, or a digital PDF with tables. It detects the format, encoding and delimiter; skips title rows; repairs broken JSON; pulls tables out
inspect_parquetDescribe a Parquet file from its footer without reading rows: row count, columns, types, null counts, min/max per column, and SPSS/Stata/SAS labels. The cheapest way to understand a dataset before querying it. Input: artifact_id from convert_to_parquet, or a url to a .parquet fil
preview_parquetReturn a slice of rows from a Parquet file (default 20, max 500), optionally only some columns, as JSON rows, a Markdown table, or CSV. Use to eyeball data; use query_parquet to filter or aggregate. Long cells are truncated. Price: $0.002 USDC per successful call, paid via x402.
query_parquetRun one read-only DuckDB SELECT over a Parquet file, available as table `data`; join more files by passing `tables` ({name: artifact_id}, up to 7 besides data), e.g. a GL against a bank statement. Supports aggregates, window functions, CTEs, DESCRIBE data and SUMMARIZE data. Up t
verify_provenanceFree. Check that a file this service produced is authentic and unaltered: verifies the post-quantum ML-DSA-65 (NIST FIPS 204) signature in an artifact's `provenance`, and with artifact_id also re-checks the stored file's hash and size against the signed manifest.
request_capabilityFree. If none of these tools does what you need — a file type we reject, an output we do not produce, a missing operation — describe the task, the formats involved, and the most you would pay per call. The operator reads these to decide what to build next. Do not include personal
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19日
注册名称已通过 GitHub 账户 balogvn 验证,该账户拥有此仓库
代码最后更新于昨天
使用 Apache-2.0
在 280 毫秒内响应(HTTP 200)
无需登录
已读取 6 个工具描述,未发现针对 AI 的隐藏指令
尚未检查
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/balogvn-aimart-parquet)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 5 项适用的基础检查中通过了 5 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。
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于昨天,最新版本(0.1.3)于昨天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:Puter MCP, XcodeBuildMCP, Vexa, Atlassian Rovo MCP Server, Anki MCP Server
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
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.
| 本项 AImart Parquet | Puter MCP | XcodeBuildMCP | Vexa | Atlassian Rovo MCP Server | Anki MCP Server | |
|---|---|---|---|---|---|---|
| 运行位置 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 |
| 需要密钥 | 否 | 否 | 否 | 是 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 是 | 否 |
| 基础检查 | 5/5 | 4/4 | 3/3 | 2/4 | 4/4 | 3/3 |
| 许可证 | Apache-2.0 | AGPL-3.0 | MIT | Apache-2.0 | Apache-2.0 | 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。
Messy data in, clean Parquet out, paid per call by AI agents.
AImart Parquet is an MCP server and REST API that turns messy CSV/TSV, JSON/NDJSON, Excel, SPSS, Stata and SAS files, and tables in digital PDFs, into clean, typed, zstd-compressed Parquet. You can then inspect the result (footer only), preview rows, and query it with sandboxed, read-only DuckDB SQL, including joins across several files. Agents pay per call in USDC with x402 v2. There is no signup and no API key.
Predictable for agents: each operation has a fixed price, so an agent's spend cap is exact, and a call that fails is not charged. Every paid call returns a receipt naming its on-chain transaction (the PAYMENT-RESPONSE header, or x402/payment-response over MCP), and every file the hosted service produces carries a signed provenance record (ML-DSA-65) that proves it came unaltered from the service (how to verify).
Live: the hosted service is at https://balogvn--aimart-parquet.us-east.modal.run and takes USDC on Base mainnet. Its MCP endpoint is https://balogvn--aimart-parquet.us-east.modal.run/mcp. Prices, limits and data handling, as that service applies them, are at /pricing and /llms.txt. The package is on PyPI (uvx aimart-parquet mcp runs the free local server), and the server is in the official MCP Registry as io.github.balogvn/aimart-parquet.
Your data: inputs are deleted when the call ends. Converted files become unreachable after 60 minutes and are deleted by a cleanup that runs when the service starts and once a minute while it runs. The hosted service stops when idle, so one that expires while it is stopped stays stored, unreachable, until it next starts: normally within a day. A deployment that keeps outputs in Cloud Storage has a worst case of about a day (the bucket's 1-day lifecycle rule). File contents are never logged or used for training. Details: docs/privacy.md.
Why it exists: an agent that reads a 100,000-row CSV as text spends a large share of its context on raw rows. With this service it reads a compact schema report and then asks targeted SQL questions. Every conversion reports two rough numbers so you can judge the trade-off for your own data: estimated_tokens_raw (input text bytes / 4) and estimated_tokens_schema (a column digest of name, type and null count, / 4). The ratio depends on rows × columns, so there is no fixed saving:
input (measured with aimart-parquet convert) | estimated_tokens_raw | estimated_tokens_schema |
|---|---|---|
| 3-row, 2-column CSV | 9 | 18 |
| 100,000-row, 6-column synthetic CSV (4.2 MB → 0.6 MB Parquet) | 1,044,271 | 59 |
For tiny files the report costs more than the file, so just read those directly. The schema estimate covers only the column digest. The full JSON response is larger: it adds per-column notes and, on the hosted service, a provenance block with a 3,309-byte ML-DSA-65 signature (4,412 base64 characters).
The examples below call the hosted service, so a paid one spends real USDC (two cents for a
conversion). An unpaid call costs nothing and shows the price. If you run your own deployment
(hosting), use its URL instead.
The typical flow is: convert_to_parquet returns an artifact_id and a schema report. Then inspect_parquet or preview_parquet lets you look, and query_parquet answers questions with SQL. Pass the artifact_id between calls instead of re-sending the file. Inputs are a public url (best for large files), content_base64 plus filename (under about 3 MB), or the artifact_id of a file converted earlier (convert takes one too, to convert it again with new options). Over MCP only convert_to_parquet takes content_base64; on REST, convert, inspect, preview and query take all three.
An unpaid call returns HTTP 402 with an empty body. The quote is in the base64 PAYMENT-REQUIRED header:
URL=https://balogvn--aimart-parquet.us-east.modal.run # the hosted service
curl -s -D - -o /dev/null -X POST "$URL/v1/convert" \ -H 'content-type: application/json' \ -d '{"url": "https://raw.githubusercontent.com/balogvn/aimart/main/docs/examples/sales.csv"}' \ | awk 'tolower($1) == "payment-required:" {print $2}' | tr -d '\r' | base64 --decode | jq .
{
"x402Version": 2, "error": "Payment required", "resource": {"url": "https://balogvn--aimart-parquet.us-east.modal.run/v1/convert", "mimeType": "application/json", "...": "..."}, "accepts": [{ "scheme": "exact", "network": "eip155:8453", "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913", "amount": "20000", "payTo": "0x…", "maxTimeoutSeconds": 300, "extra": {"name": "USD Coin", "version": "2"} }] }
network is Base mainnet and asset is USDC there. amount is in USDC atomic units (6 decimals): 20000 is $0.02. curl cannot sign. An x402 client signs the quote with your wallet and retries with a PAYMENT-SIGNATURE header. The settlement comes back in PAYMENT-RESPONSE. The payer needs USDC on Base and nothing else: the facilitator pays the network fee. With the x402 Python SDK (pip install "x402[evm,httpx]"), this spends $0.025 of real USDC, two cents to convert and half a cent to query:
import os
import anyio import httpx from eth_account import Account from x402 import max_amount, x402Client from x402.http.clients.httpx import x402AsyncTransport from x402.mechanisms.evm import EthAccountSigner from x402.mechanisms.evm.exact import ExactEvmClientScheme
URL = "https://balogvn--aimart-parquet.us-east.modal.run" # the hosted service, on Base mainnet KEY = os.environ["PAYER_PRIVATE_KEY"] # a wallet holding a little USDC on Base; stays on your side
payer = x402Client() payer.register("eip155:8453", ExactEvmClientScheme(EthAccountSigner(Account.from_key(KEY)))) payer.register_policy(max_amount(20_000)) # never pay more than $0.02 per call
async def main() -> None: transport = x402AsyncTransport(payer, httpx.AsyncHTTPTransport()) async with httpx.AsyncClient(base_url=URL, transport=transport, timeout=180) as http:
sample = "https://raw.githubusercontent.com/balogvn/aimart/main/docs/examples/sales.csv" r = await http.post("/v1/convert", json={"url": sample}) artifact_id = r.json()"artifact" r = await http.post( "/v1/query", json={ "artifact_id": artifact_id, "sql": "SELECT region, sum(units) FROM data GROUP BY 1", }, ) print(r.json()["rows"])
anyio.run(main)
A complete, tested script for REST, MCP and provenance checks is in docs/examples/agent_pays.py. The step-by-step guide is in docs/agents-guide.md. If a paid retry still returns 402, the body is again {} and the reason is in the PAYMENT-REQUIRED header's error field.
The remote server speaks Streamable HTTP at /mcp. initialize and tools/list are free. Each paid tools/call is charged through x402's MCP transport: an unpaid call returns isError: true with the PaymentRequired object in structuredContent, and the client retries with the signed payload in params._meta["x402/payment"].
Claude Code:
claude mcp add --transport http aimart https://balogvn--aimart-parquet.us-east.modal.run/mcp
Cursor, or any client that takes a remote URL (.cursor/mcp.json or equivalent):
{ "mcpServers": { "aimart": { "url": "https://balogvn--aimart-parquet.us-east.modal.run/mcp" } } }
Free local server over stdio, for files on your machine. It needs no payments, no wallet and no network:
claude mcp add aimart-local -- uvx aimart-parquet mcp
claude mcp add aimart-local -e AIMART_ENABLE_QUANTUM=true -- uvx --from 'aimart-parquet[quantum]' aimart-parquet mcp
{ "mcpServers": { "aimart-local": { "command": "uvx", "args": ["aimart-parquet", "mcp"] } } }
Local mode takes path inputs and writes the output next to the input, or to output_path. If AIMART_HOSTED_URL is set, convert results include a one-line hint that points at the hosted service, which adds signed provenance.
Paying from an MCP host. Today most MCP hosts do not sign x402 payments by themselves.
In those hosts,
tools/listworks and paid tools return the PaymentRequired error result.
To pay over MCP you need an x402-capable MCP client, such as the Python client in
docs/agents-guide.md. The local server never asks for payment.
One query reads up to 8 tables in total: the top-level input is table data, and tables adds up to 7 more by name, for one query price. REST takes an object per table (artifact_id, or url of a Parquet file); the MCP tool takes the artifact_id string itself (a local path in local mode). With sql = SELECT d.*, o.status FROM data d JOIN orders o USING (order_id):
REST POST /v1/query {"artifact_id": "<invoices_id>", "sql": "...", "tables": {"orders": {"artifact_id": "<orders_id>"}}}
MCP query_parquet {"artifact_id": " ", "sql": "...", "tables": {"orders": " "}}
Prices are the Settings defaults, in USDC per successful call. A call that fails (HTTP ≥ 400, or an MCP isError result) is never settled, so you are not charged for errors. A deployment can override each price with AIMART_PRICE_*. Its live list is at GET /pricing.
| operation | REST | MCP tool | price |
|---|---|---|---|
| convert | POST /v1/convert, POST /v1/convert/upload (multipart) | convert_to_parquet | $0.02 |
| inspect (footer only) | POST /v1/inspect | inspect_parquet | $0.002 |
| preview | POST /v1/preview | preview_parquet | $0.002 |
query (one read-only SELECT; up to 8 tables: data plus up to 7 more in tables) | POST /v1/query | query_parquet | $0.005 |
| premium (off by default): quantum-kernel PCA | POST /v1/quantum/compress | quantum_compress_features | $0.50 |
| premium (off by default): QAOA portfolio | POST /v1/quantum/portfolio | quantum_optimize_portfolio | $1.00 |
Free: GET /, /health, /pricing, /llms.txt, /openapi.json, /docs, /.well-known/x402, /.well-known/mcp/server-card.json, /.well-known/aimart-signing-key, POST /v1/verify and the verify_provenance tool, POST /v1/feedback and the request_capability tool (tell us what you needed and would pay for), signed artifact downloads (GET /v1/artifacts/{id}/{filename}?exp&sig), MCP initialize and tools/list, and the whole local stdio server.
The floor is $0.002 because facilitators reject payments below about $0.0011–0.0015, and some charge up to about $0.002 per settlement. Below that floor a call is either unsettleable or loss-making. See docs/economics.md.
Networks: the hosted service takes USDC on Base mainnet (eip155:8453), settled through xpay, with Primer as the fallback. The software's own default is testnet (Base Sepolia eip155:84532, facilitator https://x402.org/facilitator): mainnet (Base via xpa