Skip to main content
Glama
claude-sandbox-config.json•2.78 kB
{ "name": "egw-research-compilation", "description": "Claude Code sandbox for automated EGW research compilation", "dockerFile": "FROM node:18-alpine\n\n# Install system dependencies\nRUN apk add --no-cache git python3 make g++ sqlite\n\n# Install pnpm\nRUN npm install -g pnpm\n\n# Set working directory\nWORKDIR /workspace\n\n# Install Claude Code (this would be mounted or installed)\n# RUN npm install -g @anthropic/claude-code\n\n# Copy EGW packages (these would be pre-built)\n# COPY packages/ ./packages/\n# COPY apps/ ./apps/\n\n# Install dependencies\n# RUN pnpm install\n\n# Default command\nCMD [\"bash\"]", "environment": { "NODE_ENV": "development", "EGW_DATABASE_PATH": "/workspace/data/egw.db", "CLAUDE_API_KEY": "${CLAUDE_API_KEY}", "RESEARCH_OUTPUT_DIR": "/workspace/output" }, "mounts": [ { "source": "./data", "target": "/workspace/data", "type": "bind", "readonly": true }, { "source": "./output", "target": "/workspace/output", "type": "bind" } ], "setupCommands": [ "echo 'Setting up EGW Research environment...'", "mkdir -p /workspace/output", "npm install -g @surgbc/egw-writings-shared @surgbc/egw-pdf-generator", "echo 'EGW Research sandbox ready for automated compilation'" ], "initialPrompt": "You are in an EGW Research compilation environment. Your task is to:\n\n1. Take a research topic as input\n2. Use the EGW database tools to search for relevant passages\n3. Organize findings by book, topic, or chronological order\n4. Generate a professional PDF compilation with proper citations\n5. Save the output to /workspace/output/\n\nAvailable tools:\n- @surgbc/egw-writings-shared: Database search and content retrieval\n- @surgbc/egw-pdf-generator: Professional PDF generation\n- EGW database at /workspace/data/egw.db\n\nExample workflow:\n```bash\n# Search for topic\negw-search 'salvation by faith' --limit 50\n\n# Generate research compilation\negw-pdf-generator research \\\n --query 'salvation by faith' \\\n --output /workspace/output/salvation-research.pdf \\\n --group-by book \\\n --citation-style academic\n```\n\nWhat research topic would you like me to compile?", "autoCommit": true, "branchPrefix": "research-compilation", "tools": { "bash": { "enabled": true, "timeout": 300000 }, "file_operations": { "enabled": true, "allowedPaths": ["/workspace"] }, "git": { "enabled": true, "autoCommit": true } }, "security": { "networkAccess": "limited", "allowedHosts": [ "api.anthropic.com", "github.com", "registry.npmjs.org" ], "resourceLimits": { "memory": "2GB", "cpu": "2", "disk": "10GB" } } }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pythondev-pro/egw_writings_mcp_server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server