Mu
News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint.
Code-map tools for AI agents: see a repo's structure first, then edit only what matters.
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-10-09 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 4/5 项(仅展示,不用于排序)
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 Itamos MCP Tools。按照 https://mcp.popnx.com/i/itamos-technologia-itamos-mcp-tools.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 4/5 项检查 · 你的提问会经过开发者的服务器(mcp.itamos-technologia.com) · ✓ 命令已检查 2026年11月13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
Itamos MCP Toolshttps://mcp.itamos-technologia.com/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
+ConnectorsItamos MCP Tools
用 Itamos MCP Tools 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 Itamos MCP Tools,或回答中出现 Itamos MCP Tools 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
Itamos MCP Toolshttps://mcp.itamos-technologia.com/mcp开启新聊天,输入前先从插件列表中选择 Itamos MCP Tools
用 Itamos MCP Tools 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 Itamos MCP Tools,或回答中出现 Itamos MCP Tools 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 itamos-tools https://mcp.itamos-technologia.com/mcp应能看到 Itamos MCP Tools 在列表中并显示已连接
用 Itamos MCP Tools 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 Itamos MCP Tools,或回答中出现 Itamos MCP Tools 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 Itamos MCP Tools 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 Itamos MCP Tools,或回答中出现 Itamos MCP Tools 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 Itamos MCP Tools 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 Itamos MCP Tools,或回答中出现 Itamos MCP Tools 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://mcp.itamos-technologia.com/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user itamos-tools https://mcp.itamos-technologia.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"itamos-tools": {
"url": "https://mcp.itamos-technologia.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"itamos-tools": {
"type": "http",
"url": "https://mcp.itamos-technologia.com/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
服务器要求先登录,才会列出它的工具。
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 itamos-technologia 验证,该账户拥有此仓库
代码最后更新于22天前
GitHub 无法识别许可证类型;请打开文件自行查看
在 319 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
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/itamos-technologia-itamos-mcp-tools)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 4 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。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于22天前,最新版本(1.1.0)于40天前进入注册中心。
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:Mu, Award Travel Finder, Killbottleneck, Whimsical, HasData Google Maps
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
News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint.
Search award flight availability and points pricing across 27 airlines and 23 loyalty programs.
Free-to-self-host goal and process maps for humans and AI agents, with REST API and MCP.
Create and edit flowcharts, mind maps, wireframes, and docs in Whimsical, or search your workspace.
Google Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud.
| 本项 Itamos MCP Tools | Mu | Award Travel Finder | Killbottleneck | Whimsical | HasData Google Maps | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 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 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 是 | 否 | 是 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 是 | 否 |
| 基础检查 | 4/5 | 4/4 | 3/3 | 3/3 | 4/4 | 5/5 |
| 许可证 | NOASSERTION | AGPL-3.0 | MIT | MIT | 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。
Built in Greece, for the world.
Free and open source under AGPL-3.0. Commercial licences for closed-source use.
Every LLM coding assistant faces the same wall: codebases are too large to fit in context. The standard response is to dump files — grep for something promising, cat it, hope for the best. At 50k files this breaks. At 240k files it never worked.
We built four tools that give an LLM structured perception of a codebase instead of raw file access, plus a sandboxed git to bring code in. The result is a model that navigates code the way a senior engineer does — starting from the architecture, narrowing to the module, reading only the segment it needs. One call takes it from the project straight to the lines it needs, and every save is checked before it lands.
Read the full paper: docs/PAPER.md: how each tool works, why it was designed that way, and how the hosted sandbox runs, with diagrams.
| Tool | What it does |
|---|---|
| read_file | The single entry point. With no path it lists your projects; a project name shows its structure with coordinates (no code); a coordinate opens a file map or one segment in a single call. Edits one segment at a time, and every save is verified automatically. |
| master_architect | The engine behind read_file. Indexes the codebase into a graph (files, imports, databases, servers) and keeps it in step with every save. In the sandbox it is not called directly: read_file does it. |
| write_file | Creates new files only and never overwrites; edits go through read_file. Every new file belongs to a project the agent names: an existing one, or a new name to start one. Nothing is placed automatically. |
| git | The original Itamos git tool, sandboxed for security: clone (remote URLs only, depth=1), status, commit. A clone is scanned into a project as soon as it finishes. Everything stays inside the session workspace; push is not available. |
| web_skeleton | LLM-first web perception. 97% token reduction vs raw HTML. Actions: search, skeleton, read, click. |
At least 97% fewer tokens than the usual shell workflow (grep, cat, run_cmd), measured against the best case where the model fixes the bug in one attempt. Real sessions save more, because the failed attempts common with raw shell access aren't counted.
Every client gets an isolated workspace. No shared state, no cross-session leakage. Workspaces are wiped after 10 minutes of inactivity.
read_file() → your projects
read_file(path="itsdangerous") → the structure: folders and files with coordinates, no code read_file(path="itsdangerous", segment="d.a.f") → the map of signer.py, one line per segment read_file(path="itsdangerous", segment="d.a.f.31.17") → the code of verify_signature, nothing else
Coordinates: letters are location (folders and files share one sequence per folder), numbers are what is inside a file. d.a.f.31.17 reads as src → itsdangerous → signer.py → segment 31.17. A folder that has never been scanned is scanned on first read; a cloned repository is scanned as soon as the clone finishes.
Nothing is dumped: a structure or file map over ~3,000 tokens returns an overview and asks for a search term instead. search works on both: file and folder names in a project, segment names in a file. trace=true shows what a file connects to, or a project's data flow.
Files are parsed into named segments. A 5000-line file might have 40 segments; its map is one line per segment, with classes listing their methods. The model reads the map, picks the segment it needs, reads that segment. Total context used is roughly 120 lines instead of 5000.
One edit at a time, and only on segments the model has read since the last change, so it can never change code it has not looked at. Saving verifies the file first:
| Level | Checks | On failure |
|---|---|---|
| L1 | Syntax: tree-sitter plus the language's own checker (py_compile, node --check, php -l, bash -n, gofmt, C/C++ in project context, config parsers) | Not saved; the error names the line |
| L2 | Config files through their service's checker (nginx -t, sshd -t, visudo, systemd-analyze). Linters run too | Config failure: not saved. Linter findings are only reported |
| L3 | Connections: every local import resolves to a project file (Python and JavaScript/TypeScript: any other import must be an installed package, for Python in the project's venv when it has one); SQL is checked against the live database schema | Saved, with what is incomplete and how to see it, so a project's first files can import files that don't exist yet |
L3 checks the content being saved, not an older index, and every save re-indexes the file in every supported language, so the map never lags behind the disk.
Raw HTML of a modern web page runs 50,000 to 200,000 tokens. web_skeleton output is 500 to 3,000 tokens. The model reads the skeleton, picks the section id it needs, reads that section only.
Verified in live use with Claude Opus 5.5 and Claude Sonnet. Any MCP-capable model can use the tools.
Don't take our word for it. Test the tools free in the hosted sandbox with your own model and your own repository, then post your results in Discussions → Benchmarks: model, task, tokens, time.
Found a bug? Open an issue with the steps to reproduce it. Every report makes the tools better.
The sandbox server speaks standard MCP over HTTP POST with SSE support.
Compatible with any MCP client. Used in practice through Claude.ai and through direct API integration (our benchmark harness).
Try it in Claude (free live alpha): copy https://mcp.itamos-technologia.com/mcp, open Claude's connector settings, click Add custom connector, paste the address and click Add. A page opens with one button, Create my sandbox: no account, no email. Switch it on in a chat (+ → Connectors) and ask, for example, *"Go to bbc.com/news and tell me the top stories."* In other MCP clients, add the same address as a remote MCP server. Sandboxes are deleted after 10 minutes of inactivity, so don't use them for sensitive data.
apt install build-essential python3).git clone https://github.com/itamos-technologia/itamos-mcp-tools.git
cd itamos-mcp-tools npm install
One npm install sets up everything, including the tools folder.
On Ubuntu 26.04 you can install the package from Releases instead: sudo apt install ./itamos-mcp-tools_1.1.0_all.deb. It sets up a service user, a systemd service, settings in /etc/itamos-mcp-tools/env and the command itamos-mcp-create-slots, then tells you the next two steps.
Besides the standard tree-sitter grammars (installed by npm install), read_file and the segmenter use extra parsers from the grammars/ folder:
| Files | Parser | Falls back to |
|---|---|---|
.cu .cuh .hip | tree-sitter-cuda-plus | stock tree-sitter-cuda, then C++ |
.metal | tree-sitter-metal-plus | tree-sitter-metal, then C++ |
.cpp .cc .hpp, C++ .h | tree-sitter-cpp-plus | stock tree-sitter-cpp |
.m .mm, .h with @interface | tree-sitter-objc | C / C++ |
The "plus" parsers are the stock grammar plus extra C++ rules, checked to give the identical tree wherever the stock grammar already parses. A parser that is missing or fails to load is skipped, never fatal.
grammars/tree-sitter-*/prebuilds/linux-x64/ (Node-API, any Node 18+, glibc 2.14+), and npm install sets up the rest. cd grammars/tree-sitter-cuda-plus && npx node-gyp rebuild # same for tree-sitter-cpp-plus, -metal-plus, -metal
grammars/tree-sitter-* folder is a self-contained package. Copy one in and the sandbox finds it by name, with no install or symlink. To keep the grammars somewhere else, set SANDBOX_GRAMMARS_DIR.grammars/plus/): grammars/plus/build_plus.sh generates with tree-sitter-cli 0.25.10 (ABI 15), compiles, and publishes into the matching tree-sitter-* folder. Its header shows the arguments.sudo scripts/create-slots.sh tank/sandboxes 500 2G $USER
This creates slot_001 to slot_500 under the ZFS dataset tank/sandboxes (use your own pool name), each with a 2 GB quota and lz4 compression, owned by the user the server runs as. It is safe to run again.
SANDBOX_ROOT=/tank/sandboxes SANDBOX_TOTAL_SLOTS=500 npm start
From the same machine, add http://localhost:4200/mcp as a connector in your MCP client. Local connections are identified by IP address and need no sign-in.
Firewall port 4200 and put an HTTPS reverse proxy (for example nginx) in front of it that sets X-Forwarded-For and X-Forwarded-Proto. Requests that arrive through the proxy use the anonymous one-click sign-in, so users on shared addresses (such as claude.ai) each get their own sandbox. Direct connections to port 4200 skip the sign-in, which is why the port must not be reachable from outside.
read_file and web_skeleton give untitled paragraphs and page sections a short title (5 to 10 words) from a small summarizer model, so the agent can tell parts apart without reading them. Without a summarizer everything still works; those parts are then named by their first line.
Any OpenAI-compatible chat endpoint works, set with ITAMOS_SUMMARIZER_URL (default http://127.0.0.1:8090): a single llama-server, Ollama, or the included router in front of several GPUs. The whole paragraph is always sent, never cut.
The hosted sandbox runs Gemma 4 E4B (Q4_0) as summarizer and EmbeddingGemma 300M as embedder on three GPUs (one 16 GB MI50 and two 8 GB V340 dies), each summarizer started like this:
llama-server -m gemma-4-E4B-it-Q4_0.gguf -ngl 99 --port 8190 \
-np 64 -c 524288 --kv-unified -fa on --cache-type-k q4_0 --cache-type-v q4_0 -rea off
--kv-unified: one shared KV pool, so each request uses only the tokens it needs.--cache-type-k q4_0 --cache-type-v q4_0 (needs -fa on): a 4-bit KV cache, about 4.5 KB per token for this model.-c is the pool in tokens: 524,288 on the MI50, 262,144 on each V340 die (with 32 slots).The router (router/llm-router.js, service itamos-llm-router) listens on 8090 (summarizer) and 8091 (embedder). Before sending a request it counts its tokens with the backend's own tokenizer, sends it to a GPU whose pool has room (preferring faster GPUs by weight), and makes it wait in line when none has. A GPU that fails is skipped for 15 seconds and the request is retried on another. Configure it with ROUTES (in the package: /etc/itamos-mcp-tools/router.env); GET /router/status shows each GPU's pool, reserved