AGENT SKILL

cartogopher

Set up CartoGopher AI-native code intelligence. Gets a free 7-day trial API key and configures the MCP server automatically.

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
cartogopher
emoji
🦞
homepage
https://cartogopher.com
metadata
{ "openclaw": { "requires": { "bins": [ "curl", "unzip", "node", "npm" ] }, "primaryEnv": "CARTOGOPHER_API_KEY" } }
description
Set up CartoGopher AI-native code intelligence. Gets a free 7-day trial API key and configures the MCP server automatically.

03 SKILL.md 正文

CartoGopher

Set up CartoGopher — AI-native code intelligence that gives you 30+ tools for navigating codebases with 94% fewer tokens than file reading.

When to Use This Skill

Use this skill when the user wants to:

  • Set up CartoGopher for their project
  • Get a CartoGopher trial API key
  • Configure the CartoGopher MCP server
  • Improve code navigation and understanding with AI-native tooling

What CartoGopher Does

CartoGopher parses a codebase into a compact graph (bake.json) and exposes 30+ MCP tools:

  • Symbol lookup — find functions, types, and their relationships
  • API tracing — trace endpoints from frontend to database
  • Architecture mapping — understand project structure and get placement suggestions
  • AST-aware search — search code semantically, not just text matching
  • Frontend analysis — Vue, React component analysis with props, hooks, store usage

Setup Flow

Step 1: Get a Trial API Key

Ask the user for their email address, then request a 7-day trial key:

curl -s -X POST https://cartogopher.com/api/agent-trial \
  -H 'Content-Type: application/json' \
  -d '{"email":"USER_EMAIL_HERE"}'

The response will contain:

{
  "success": true,
  "api_key": "cg_agent_...",
  "trial_ends_at": "2026-02-27T...",
  "message": "Trial started! Configure your MCP server with this key."
}

Save the api_key value — you'll need it for the next steps.

If the response contains an error:

  • "Disposable email addresses are not allowed" — ask for a real email
  • "A trial already exists for this email" — the user already has a key, ask them to check their email or provide the existing key
  • "Rate limit exceeded" — wait and retry later

Step 2: Verify the Key Works

curl -s -X POST https://cartogopher.com/api/verify-key \
  -H 'Content-Type: application/json' \
  -d '{"api_key":"API_KEY_HERE"}'

Step 3: Install the MCP Server

Download and install the CartoGopher bundle for the user's platform. Each download is a zip containing the binary, MCP server, and dependencies.

Container prerequisite (Linux/Docker only): CartoGopher requires /etc/machine-id to exist. Most Linux desktops have this, but containers often don't:

# Ensure machine-id exists (required in containers)
[ -f /etc/machine-id ] || (cat /proc/sys/kernel/random/uuid | tr -d '-' > /etc/machine-id)

Detect platform and download:

# Detect platform and set download URL
PLATFORM=$(uname -s)-$(uname -m)

case "$PLATFORM" in
  Darwin-arm64)  DOWNLOAD_URL="https://cartogopher.com/downloads/cartogopher/v4/mac/arm64" ;;
  Darwin-x86_64) DOWNLOAD_URL="https://cartogopher.com/downloads/cartogopher/v4/mac/intel" ;;
  Linux-x86_64)  DOWNLOAD_URL="https://cartogopher.com/downloads/cartogopher/v4/linux/amd64" ;;
  Linux-aarch64) DOWNLOAD_URL="https://cartogopher.com/downloads/cartogopher/v4/linux/arm64" ;;
  *) echo "Unsupported platform: $PLATFORM"; exit 1 ;;
esac

# Download, extract, and clean up
curl -sL "$DOWNLOAD_URL" -o cg.zip && unzip cg.zip -d ~/.cartogopher/mcp-server && rm cg.zip

Platform-specific one-liners (if you already know the platform):

  • macOS Apple Silicon (M1/M2/M3/M4):

    curl -sL https://cartogopher.com/downloads/cartogopher/v4/mac/arm64 -o cg.zip && unzip cg.zip -d ~/.cartogopher/mcp-server && rm cg.zip
    
  • macOS Intel:

    curl -sL https://cartogopher.com/downloads/cartogopher/v4/mac/intel -o cg.zip && unzip cg.zip -d ~/.cartogopher/mcp-server && rm cg.zip
    
  • Linux amd64:

    curl -sL https://cartogopher.com/downloads/cartogopher/v4/linux/amd64 -o cg.zip && unzip cg.zip -d ~/.cartogopher/mcp-server && rm cg.zip
    
  • Linux arm64:

    curl -sL https://cartogopher.com/downloads/cartogopher/v4/linux/arm64 -o cg.zip && unzip cg.zip -d ~/.cartogopher/mcp-server && rm cg.zip
    

After extraction, install the MCP server dependencies:

cd ~/.cartogopher/mcp-server
npm install

Step 4: Set the API Key Permanently

The API key MUST be set in the user's shell profile so the MCP server process can access it. Setting it with export in a single session is NOT sufficient — MCP servers run as separate processes.

# Detect shell profile
SHELL_PROFILE="$HOME/.zshrc"
[ -f "$HOME/.bashrc" ] && [ ! -f "$HOME/.zshrc" ] && SHELL_PROFILE="$HOME/.bashrc"

# Add API key to shell profile (only if not already present)
if ! grep -q "CARTOGOPHER_API_KEY" "$SHELL_PROFILE" 2>/dev/null; then
  echo "export CARTOGOPHER_API_KEY=API_KEY_HERE" >> "$SHELL_PROFILE"
fi

source "$SHELL_PROFILE"

Step 5: Configure the MCP Server

The MCP configuration depends on which AI tool the user runs:

For OpenClaw (openclaw.json):

{
  "mcpServers": {
    "cartogopher": {
      "command": "node",
      "args": ["~/.cartogopher/mcp-server/cartogopher-mcp.js"],
      "env": {
        "CURSOR_WORKSPACE": ".",
        "CARTOGOPHER_API_KEY": "API_KEY_HERE"
      }
    }
  }
}

For Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "cartogopher": {
      "command": "node",
      "args": ["~/.cartogopher/mcp-server/cartogopher-mcp.js"],
      "env": {
        "CURSOR_WORKSPACE": "${workspaceFolder}",
        "CARTOGOPHER_API_KEY": "API_KEY_HERE"
      }
    }
  }
}

For Claude Code:

claude mcp add cartogopher node ~/.cartogopher/mcp-server/cartogopher-mcp.js \
  -e CURSOR_WORKSPACE=. \
  -e CARTOGOPHER_API_KEY=API_KEY_HERE

Step 6: Verify Setup

After configuration, test that the MCP tools are working by calling the shake tool on the user's project. If it returns a project overview, setup is complete.

Important Notes

  • Trial keys have a cg_agent_ prefix and last 7 days
  • Trial allows 2 devices simultaneously
  • The MCP server must have CARTOGOPHER_API_KEY explicitly in its env config — it does NOT inherit from the shell
  • After setup, the user must restart their AI tool (Cursor, Claude, etc.) for MCP changes to take effect
  • If the user already has a CartoGopher API key (cg_live_ or cg_trial_), skip the trial step and go straight to MCP configuration

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0