经 AI Skill Hub 精选评估,Cartog 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
Cartog 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Cartog 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/jrollin/cartog
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"cartog": {
"command": "npx",
"args": ["-y", "cartog"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Cartog 执行以下任务... Claude: [自动调用 Cartog MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"cartog": {
"command": "npx",
"args": ["-y", "cartog"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Map your codebase. Navigate by graph, not grep.
~280 tokens per query, 97% recall, 8 us to 20 ms latency, 10 languages.
Single binary. Microsecond queries. 100% local by default.
Cartog pre-computes a code graph — symbols, calls, imports, inheritance — and lets you query it instantly. Use it from the CLI for day-to-day navigation, as an MCP server for AI agents, or both. No Python, no pip, no Docker. One binary, one SQLite file, zero cloud dependencies.
Documentation site

curl -fsSL https://jrollin.github.io/cartog/install.sh | sh
Detects your OS + architecture, downloads the matching binary from the latest GitHub Release, verifies its SHA-256, and installs to /usr/local/bin (or ~/.local/bin if non-root). Override with CARTOG_INSTALL_DIR; pin a version with CARTOG_VERSION=<version> (e.g. the tag from Releases). Audit the script: scripts/install.sh.
Fastest path: let cartog write the right config for your editor.
cartog ide # all installed clients, all scopes
cartog ide --client cursor # one client
cartog ide --client claude-desktop --dry-run # preview without writing
Idempotent. Existing servers in each file are preserved.
Prefer the brew/npm shape? cartog install takes editors as positional args and is always non-interactive — safer than cartog ide for scripts and agents:
cartog install cursor # one editor
cartog install cursor vscode codex # several at once
cartog install # all detected editors
cartog install cursor --dry-run # preview
Prefer to wire it yourself? Pick your client below.
<details> <summary><strong>Claude Code</strong> — project-scoped <code>.mcp.json</code> or user settings</summary>
One-shot:
cartog ide --client claude-code # writes .mcp.json + user settings
claude mcp add cartog -- cartog serve --watch # user scope
claude mcp add --scope project cartog -- cartog serve --watch
Manual (<repo>/.mcp.json):
{
"mcpServers": {
"cartog": { "command": "cartog", "args": ["serve", "--watch"] }
}
}
Only Claude Code gets--watchby default — the others ship plain["serve"]. Agent-driven flows churn files faster than human-driven editor flows, so the in-process file watcher pays off. Drop--watchwithcartog ide --no-watchif you don't want it. </details>
<details> <summary><strong>Cursor</strong> — project <code>.cursor/mcp.json</code> or user settings</summary>
One-shot:
cartog ide --client cursor
Manual:
{
"mcpServers": {
"cartog": { "command": "cartog", "args": ["serve"] }
}
} </details>
<details> <summary><strong>Codex CLI</strong> — user-only TOML at <code>~/.codex/config.toml</code></summary>
One-shot:
cartog ide --client codex
Manual:
[mcp_servers.cartog]
command = "cartog"
args = ["serve"]
Codex is user-global only. If you use cartog on multiple projects, cartog ide auto-names each section cartog-<slug>-<hash8> so they coexist. </details>
<details> <summary><strong>Windsurf</strong> — <code>~/.codeium/windsurf/mcp_config.json</code></summary>
cartog ide --client windsurf
{
"mcpServers": {
"cartog": { "command": "cartog", "args": ["serve"] }
}
} </details>
<details> <summary><strong>VS Code (GitHub Copilot)</strong> — project <code>.vscode/mcp.json</code></summary>
cartog ide --client vscode
Note: VS Code's top-level key is servers (no mcp prefix):
{
"servers": {
"cartog": { "type": "stdio", "command": "cartog", "args": ["serve"] }
}
} </details>
<details> <summary><strong>Zed</strong> — <code>~/.config/zed/settings.json</code></summary>
cartog ide --client zed
{
"context_servers": {
"cartog": { "command": "cartog", "args": ["serve"] }
}
} </details>
<details> <summary><strong>OpenCode</strong> — <code>~/.config/opencode/opencode.json</code></summary>
cartog ide --client opencode
{
"mcp": {
"cartog": {
"type": "local",
"command": ["cartog", "serve"],
"enabled": true
}
}
} </details>
<details> <summary><strong>Gemini CLI</strong> — <code>~/.gemini/settings.json</code></summary>
cartog ide --client gemini
{
"mcpServers": {
"cartog": { "command": "cartog", "args": ["serve"] }
}
} </details>
<details> <summary><strong>Claude Desktop</strong> — <code>claude_desktop_config.json</code></summary>
cartog ide --client claude-desktop
Manual (macOS: ~/Library/Application Support/Claude/; Windows: %APPDATA%\Claude\):
{
"mcpServers": {
"cartog": { "command": "cartog", "args": ["serve"] }
}
}
Restart Claude Desktop after editing. </details>
See docs/mcp-setup.md for the canonical long-form reference, including the path-naming scheme for Codex's multi-project setup, and docs/usage.md for all cartog ide flags.
cargo install cartog # or download a binary from GitHub Releases
cd your-project
cartog init # 1. scaffold .cartog.toml
cartog index # 2. build the code graph
That's it for CLI use. Two commands.
If you want MCP wired into your editor (Cursor, VS Code, Claude Desktop, Codex CLI, Gemini CLI, OpenCode, Windsurf, Zed), add one more:
cartog ide # optional — only if you want editor integration
All three commands are idempotent.
Now query:
cartog search validate # find symbols by name (sub-ms)
cartog refs validate_token # who calls this? (< 500 us)
cartog impact validate_token # what breaks if I change it? (< 20 ms)
cartog outline src/auth.py # file structure, no cat (< 15 us)
cartog rag setup # download models (~1.2 GB, one-time)
cartog rag index . # embed symbols + docs into sqlite-vec
cartog rag search "authentication token validation"
Three-tier hybrid pipeline: FTS5 keyword + vector KNN + cross-encoder re-ranking. Indexes both code (functions, classes, methods) and Markdown documents. Models run locally via ONNX Runtime — no API keys, no network calls.
Prefer Ollama? Setprovider = "ollama"in.cartog.toml. See Configuration.
Database path is resolved automatically — no config needed for standard use:
--db flag / CARTOG_DB env var (highest priority).cartog.toml at git root.cartog/db.sqlite; legacy .cartog.db still read with a warning).cartog/db.sqlite in current directory.cartog.toml (optional):
[database]
path = "~/.local/share/cartog/myproject.db"
[embedding]
provider = "ollama" # "local" (default) or "ollama"
model = "nomic-embed-text"
[embedding.ollama]
base_url = "http://localhost:11434"
[reranker]
provider = "none" # "local" (default) or "none"
Three setup paths for agents and editors. Pick the one that matches your stack — they are alternatives, not steps.
| Path | Use it when | What you get |
|---|---|---|
cartog ide | You want MCP wired into one or more editors (Cursor, VS Code, Codex CLI, Gemini CLI, Claude Desktop, OpenCode, Windsurf, Zed). | MCP entries written to the right files; interactive picker if you run it without flags. |
| Claude Code plugin | You are on Claude Code and want install + skill + MCP wired in one step. | Bundled: binary install, behavioural skill, MCP server, all preconfigured. |
| Agent skill | You use an agent that follows the skills protocol (Cursor, Copilot, others) and only need the behavioural rules, not MCP. | Skill files installed into the agent's skill directory; works alongside any install method. |
Run these two commands one at a time in Claude Code:
/plugin marketplace add jrollin/cartog
/plugin install cartog@cartog-plugins
First session: if the cartog binary is not already on your PATH, the plugin starts a background install and prints a one-line notice. The cartog MCP server cannot start in this first session because the binary lands after Claude Code has already tried to spawn it.
Second session: restart Claude Code. The MCP server starts, code-graph tools become available, and the SessionStart hook keeps the index fresh on every subsequent session.
Repair or upgrade: type /cartog-install at any time to install the binary synchronously (e.g. to retry a failed background install), or to upgrade an existing install to match the plugin's pinned version. The skill at skills/cartog-install/ handles both cases.
Offline / vetted install: the manual fallback is the same one used by the curl one-liner at the top of this section: download scripts/install.sh (mirrored at https://jrollin.github.io/cartog/install.sh), inspect it, then run it.
高质量的MCP工具,支持树形查询
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Cartog 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | cartog |
| 原始描述 | 开源MCP工具:claude code with treesitter and query capability (RLM, RAG, MCP, LSP)。⭐9 · Rust |
| Topics | claudeclilspmcprust |
| GitHub | https://github.com/jrollin/cartog |
| License | MIT |
| 语言 | Rust |
收录时间:2026-05-28 · 更新时间:2026-05-28 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端