OneTool MCP

效率与工作流

by beycom

面向开发者的一站式 MCP,集成 100+ 工具,涵盖 Brave、Gemini、Excel、Files、DB 与 DevTools。

什么是 OneTool MCP

面向开发者的一站式 MCP,集成 100+ 工具,涵盖 Brave、Gemini、Excel、Files、DB 与 DevTools。

README

<p align="center"> <!-- mcp-name: io.github.beycom/onetool-mcp --> <a href="https://github.com/beycom/onetool-mcp"> <img src="https://raw.githubusercontent.com/beycom/onetool-mcp/main/docs/assets/logo.svg" alt="OneTool" width="80"> </a> </p> <p align="center"> <strong>🧿 One MCP for developers - No tool tax, no context rot.<br>100+ tools including Brave, Google, Context7, Excalidraw, AWS, Version Checker, Excel, File Ops, Database, Image Vision, Playwright & Chrome DevTools Utils and many more.</strong> </p> <p align="center"> <a href="https://pypi.org/project/onetool-mcp/"><img alt="PyPI" src="https://img.shields.io/pypi/v/onetool-mcp"></a> <a href="https://github.com/beycom/onetool-mcp/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/license-GPLv3-blue"></a> <a href="https://www.python.org/"><img alt="Python" src="https://img.shields.io/badge/python-3.11%2B-blue"></a> <a href="https://github.com/beycom/onetool-mcp/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/beycom/onetool-mcp"></a> </p> <p align="center"> Works with Claude Code or any MCP client </p>

The Problem

Each MCP server consumes 3K-30K tokens per request. Connect 5 servers and you've burned 55K tokens before the conversation starts. Connect 10+ and you're at 100K tokens.

The math is brutal: Claude Opus 4.5 at $5/M input tokens, 20 days × 10 conversations × 10 messages × 3K tokens = $30/month per MCP server - even if you never use the tools.

And then there's context rot - your AI literally gets dumber as you add more tools (Chroma Research, 2025).

The Solution

OneTool is one MCP server that exposes tools as a Python API. Instead of reading tool definitions, your agent writes code:

python
>>> brave.search(query="react docs 2026")

Configure one MCP server. Use unlimited tools.

"Agents scale better by writing code to call tools instead. This reduces the token usage from 150,000 tokens to 2,000 tokens...a cost saving of 98.7%"

Anthropic Engineering

96% fewer tokens. 30× lower cost. No context rot.

📖 Read the full story


Install

Requires uv:

bash
uv tool install 'onetool-mcp[all]'   # everything
onetool init --config ~/.onetool

Add to Claude Code:

bash
claude mcp add onetool -- onetool --config ~/.onetool/onetool.yaml --secrets ~/.onetool/secrets.yaml

Or manually add to ~/.claude/mcp.json:

json
{
  "mcpServers": {
    "onetool": {
      "command": "onetool",
      "args": ["--config", "/Users/yourname/.onetool/onetool.yaml", "--secrets", "/Users/yourname/.onetool/secrets.yaml"]
    }
  }
}

That's it. All 100+ tools work out of the box.

Verify: onetool init validate --config ~/.onetool/onetool.yaml

📖 Full installation guide


Use from the CLI

Works as an MCP server and as a direct CLI — no MCP client needed. Useful for agent harnesses, scripts, and automation:

bash
# Start a persistent execution host (keeps tool state across calls)
onetool direct start --config ~/.onetool/onetool.yaml

# Run any tool — JSON output, pipeable to jq
onetool direct run "ot.packs()" --format json | jq '.[0].name'
onetool direct run "brave.search(query='latest AI news')" --format raw

📖 Direct usage guide


Features

FeatureDescription
96% Token Savings~2K tokens no matter how many tools you add
100+ Built-in ToolsWeb search, AWS, databases, file ops, diagrams, conversions
Explicit ExecutionSee exactly what runs — >>> brave.search(q="AI")
Dynamic AWSProxy all 57+ AWSlabs MCP servers; SSO and credentials handled
Live WhiteboardDraw diagrams with a Mermaid-compatible DSL via Excalidraw
MCP Server ProxyWrap existing MCP servers without the tool tax
Encrypted Secretsage-encrypted secrets.yaml backed by your OS keychain
Forge ToolsBuild new tools as part of the conversation
Image VisionRoutes to a cheaper, better vision model via ot_image (img). Zero host tokens. Supports local files, URLs, clipboard; PNG, JPEG, GIF, WebP, TIFF, HEIC, AVIF, SVG.
Smart Contextot_context (ctx) — SQLite+FTS5 store. Search and navigate large outputs without filling the context window.
Smart ToolsDelegate to cheaper LLMs (10× savings)
Security LayersAST validation, path boundaries, output sanitisation

Tools

27+ packs, 230+ tools ready to use:

PackToolsExtraDescription
awswhoami, login, start_packs, roles[dev]Dynamic AWS proxy (57+ servers)
bravesearch, news[util]Web and news search
chrome_utilhighlight_element, guide_user[dev]Browser annotations (DevTools)
context7search, doc[dev]Library documentation
convertpdf_to_md, docx_to_md, pptx_to_md[util]Document conversion
dbquery, schema, tables[dev]Database operations
diagramcreate, get_playground_url[dev]Mermaid / Kroki diagrams
excelread, write, query[util]Excel files
fileread, write, grep, slice, toc[util]File operations
groundsearch[util]Google Grounding search
knowledgesearch, ask, write, read, grep[util]RAG knowledge base (FTS5+vector)
memwrite, read, search, grep, ask, inspect, query[util]Persistent memory
ot_forgecreate_ext, validate_ext, install_skillsScaffold new tool packs
ot_context (ctx)write, read, search, grep, slice, tocSmart context store (SQLite+FTS5)
ot_image (img)load, load_batch, ask, summary, list, delete, purge[util]Image vision via dedicated model
ot_llmtransform, transform_fileLLM-powered transforms
ot_secretsinit, encrypt, audit, rotateSecrets encryption
ot_timerstart, elapsed, listNamed timers
othelp, tools, stats, skillsIntrospection
packagenpm, pypi, cargo[dev]Package versions
play_utilhighlight_element, guide_user[dev]Browser annotations (Playwright)
ripgrepsearch, count[dev]Fast code search
tavilysearch, search_batch, research[util]AI-native search
webfetchfetch, fetch_batch[dev]Web fetching
whiteboardopen, draw, screenshot, save[dev]Live Excalidraw canvas

📖 Complete tools reference — full summary table with all 230+ tools


MCP Server Proxy

Wrap any existing MCP server and call it explicitly - simple yaml config without the tool tax:

yaml
# .onetool/onetool.yaml
servers:
  chrome_devtools:
    type: stdio
    command: npx
    args: ["-y", "@anthropic-ai/chrome-devtools-mcp@latest"]
  github:
    type: stdio
    command: npx
    args: ["-y", "@anthropic-ai/github-mcp-server@latest"]
python
>>> mcp.call(server="github", tool="get_file_contents", arguments={"path": "README.md"})

📖 Configuration guide


Extending

Drop a Python file, get a pack. No registration, no config:

python
# .onetool/tools/wiki.py
pack = "wiki"

def summary(*, title: str) -> str:
    """Get Wikipedia article summary."""
    import httpx
    url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{title}"
    return httpx.get(url).json().get("extract", "Not found")
python
>>> wiki.summary(title="Python_(programming_language)")

📖 Creating tools guide


Documentation


References


Telemetry

OneTool sends anonymous startup pings (event type, version, OS). No personal data. Opt out: export DO_NOT_TRACK=1 or set telemetry.enabled: false in onetool.yaml. Details


Issues

Check for existing issues first:

Raise a new issue: github.com/beycom/onetool-mcp/issues/new


Support

If you find OneTool useful:

Ko-fi


License

GPLv3

常见问题

OneTool MCP 是什么?

面向开发者的一站式 MCP,集成 100+ 工具,涵盖 Brave、Gemini、Excel、Files、DB 与 DevTools。

相关 Skills

表格处理

by anthropics

Universal
热门

围绕 .xlsx、.xlsm、.csv、.tsv 做读写、修复、清洗、格式整理、公式计算与格式转换,适合修改现有表格、生成新报表或把杂乱数据整理成交付级电子表格。

做 Excel/CSV 相关任务很省心,能直接读写、修复、清洗和格式转换,尤其擅长把乱七八糟的表格整理成交付级文件。

效率与工作流
未扫描109.6k

PDF处理

by anthropics

Universal
热门

遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。

PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。

效率与工作流
未扫描109.6k

Word文档

by anthropics

Universal
热门

覆盖Word/.docx文档的创建、读取、编辑与重排,适合生成报告、备忘录、信函和模板,也能处理目录、页眉页脚、页码、图片替换、查找替换、修订批注及内容提取整理。

搞定 .docx 的创建、改写与精排版,目录、批量替换、批注修订和图片更新都能自动化,做正式文档尤其省心。

效率与工作流
未扫描109.6k

相关 MCP Server

文件系统

编辑精选

by Anthropic

热门

Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。

这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。

效率与工作流
82.9k

by wonderwhy-er

热门

Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。

这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。

效率与工作流
5.8k

EdgarTools

编辑精选

by dgunning

热门

EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。

这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。

效率与工作流
1.9k

评论