# Code Mode > 🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution. - **Type:** MCP server - **Install:** `agentstack add mcp-universal-tool-calling-protocol-code-mode` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [universal-tool-calling-protocol](https://agentstack.voostack.com/s/universal-tool-calling-protocol) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** MPL-2.0 - **Upstream author:** [universal-tool-calling-protocol](https://github.com/universal-tool-calling-protocol) - **Source:** https://github.com/universal-tool-calling-protocol/code-mode ## Install ```sh agentstack add mcp-universal-tool-calling-protocol-code-mode ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About 🤖 Code-Mode Library: First library for tool calls via code execution [](https://www.npmjs.com/package/@utcp/code-mode) > Transform your AI agents from clunky tool callers into efficient code executors — in just 3 lines. ## Why This Changes Everything LLMs excel at writing code but struggle with tool calls. Instead of exposing hundreds of tools directly, give them ONE tool that executes TypeScript code with access to your entire toolkit. [Apple](https://machinelearning.apple.com/research/codeact), [Cloudflare](https://blog.cloudflare.com/code-mode/), and [Anthropic](https://www.anthropic.com/engineering/code-execution-with-mcp) say that Code-Mode is a more efficient way to approach tool calling compared to the traditional dump function information and then extract a JSON for function calling. ## Benchmarks Independent [Python benchmark study](https://github.com/imran31415/codemode_python_benchmark) validates the performance claims with **$9,536/year cost savings** at 1,000 scenarios/day: | Scenario Complexity | Traditional | Code Mode | **Improvement** | |---------------------|-------------|-----------|----------------| | **Simple (2-3 tools)** | 3 iterations | 1 execution | **67% faster** | | **Medium (4-7 tools)** | 8 iterations | 1 execution | **75% faster** | | **Complex (8+ tools)** | 16 iterations | 1 execution | **88% faster** | ### **Why Code Mode Dominates:** **Batching Advantage** - Single code block replaces multiple API calls **Cognitive Efficiency** - LLMs excel at code generation vs. tool orchestration **Computational Efficiency** - No context re-processing between operations # Getting Started [ ](https://www.youtube.com/watch?v=zsMjkPzmqhA) ## Get Started in 3 Lines ```typescript import { CodeModeUtcpClient } from '@utcp/code-mode'; const client = await CodeModeUtcpClient.create(); // 1. Initialize await client.registerManual({ name: 'github', /* MCP config */ }); // 2. Add tools const { result } = await client.callToolChain(`/* TypeScript */`); // 3. Execute code ``` That's it. Your AI agent can now execute complex workflows in a single request instead of dozens. ## What You Get ### **Progressive Tool Discovery** ```typescript // Agent discovers tools dynamically, loads only what it needs const tools = await client.searchTools('github pull request'); // Instead of 500 tool definitions → 3 relevant tools ``` ### **Natural Code Execution** ```typescript const { result, logs } = await client.callToolChain(` // Chain multiple operations in one request const pr = await github.get_pull_request({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); const comments = await github.get_pull_request_comments({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); const reviews = await github.get_pull_request_reviews({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); // Process data efficiently in-sandbox return { title: pr.title, commentCount: comments.length, approvals: reviews.filter(r => r.state === 'APPROVED').length }; `); // Single API call replaces 15+ traditional tool calls ``` ### **Auto-Generated TypeScript Interfaces** ```typescript namespace github { interface get_pull_requestInput { /** Repository owner */ owner: string; /** Repository name */ repo: string; /** Pull request number */ pull_number: number; } } ``` ## Enterprise-Ready - **Secure VM Sandboxing** – Node.js isolates prevent unauthorized access - **Timeout Protection** – Configurable execution limits prevent runaway code - **Complete Observability** – Full console output capture and error handling - **Zero External Dependencies** – Tools only accessible through registered UTCP/MCP servers - **Runtime Introspection** – Dynamic interface discovery for adaptive workflows If you're working at an enterprise, and need support, book a consultation [here](https://bevel.neetocal.com/meeting-with-ali). ## Universal Protocol Support Works with **any tool ecosystem:** | Protocol | Description | Usage | |----------|-------------|-------| | **MCP** | Model Context Protocol servers | `call_template_type: 'mcp'` | | **HTTP** | REST APIs with auto-discovery | `call_template_type: 'http'` | | **File** | Local JSON/YAML configurations | `call_template_type: 'file'` | | **CLI** | Command-line tool execution | `call_template_type: 'cli'` | ## Installation ```bash npm install @utcp/code-mode ``` ## Recommended for shell agents: the `utcp` CLI **If your agent can run shell commands** (Claude Code, Cursor, Codex, Claude Cowork, etc.), the [`utcp` CLI](./code-mode-cli) is the **preferred** way to use Code Mode — no MCP server, no client config, no env vars. The agent self-configures by writing a `.utcp_config.json` and drives everything from the shell. Just point the agent at the built-in guide: ```bash npx -y @utcp/code-mode-cli prompt ``` Hand it a description of the API to use — a UTCP call template, an **OpenAPI spec**, or a **plain-English description** — and it writes the config, discovers tools, runs tool-chains, and even completes **interactive OAuth logins** (e.g. Notion), all from the shell: ```bash npx -y @utcp/code-mode-cli search "" # discover tools + TS interfaces npx -y @utcp/code-mode-cli run b.title); EOF npx -y @utcp/code-mode-cli login # interactive OAuth, writes token to .env ``` > **CLI vs MCP:** prefer the **CLI** whenever the agent has shell access (most coding agents) — it's simpler and self-configuring. Use the **MCP server** (below) only for MCP-only clients like Claude Desktop. Both wrap the same `@utcp/code-mode` engine. See [`code-mode-cli/`](./code-mode-cli) for full docs. ## Ready-to-Use MCP Server **On an MCP-only client (e.g. Claude Desktop)?** Use our plug-and-play MCP server. (If your agent has a shell, prefer the [`utcp` CLI](#recommended-for-shell-agents-the-utcp-cli) above.) ```json { "mcpServers": { "code-mode": { "command": "npx", "args": ["@utcp/code-mode-mcp"], "env": { "UTCP_CONFIG_FILE": "/path/to/your/.utcp_config.json" } } } } ``` **That's it!** No installation, no Node.js knowledge required. The [Code Mode MCP Server](https://github.com/universal-tool-calling-protocol/code-mode/tree/main/code-mode-mcp) automatically: - Downloads and runs the latest version via `npx` - Loads your tool configurations from JSON - Provides code execution capabilities to Claude Desktop - Gives you `call_tool_chain` as an MCP tool for TypeScript execution **Perfect for non-developers** who want Code Mode power in Claude Desktop! ## Direct TypeScript Usage ### 1. **MCP Server Integration** Connect to any Model Context Protocol server: > Each `call_template_type` is a separate plugin package. Install and import the > package once at startup so it can register itself with the client; the plugin > registers as a side effect of being imported. For `mcp`, that's `@utcp/mcp`. > The same pattern applies to other transports: `@utcp/http`, `@utcp/text`, etc. > > ```bash > npm install @utcp/mcp > ``` ```typescript import '@utcp/mcp'; // registers the 'mcp' call template import { CodeModeUtcpClient } from '@utcp/code-mode'; const client = await CodeModeUtcpClient.create(); // Connect to GitHub MCP server await client.registerManual({ name: 'github', call_template_type: 'mcp', config: { mcpServers: { github: { transport: 'stdio', // required by @utcp/mcp command: 'docker', args: ['run', '-i', '--rm', '-e', 'GITHUB_PERSONAL_ACCESS_TOKEN', 'mcp/github'], env: { GITHUB_PERSONAL_ACCESS_TOKEN: process.env.GITHUB_TOKEN } } } } }); ``` ### 2. **Execute Multi-Step Workflows** Replace 15+ tool calls with a single code execution: ```typescript const { result, logs } = await client.callToolChain(` // Traditional: 4 separate API round trips → Code Mode: 1 execution const pr = await github.get_pull_request({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); const comments = await github.get_pull_request_comments({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); const reviews = await github.get_pull_request_reviews({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); const files = await github.get_pull_request_files({ owner: 'microsoft', repo: 'vscode', pull_number: 1234 }); // Process data in-sandbox (no token overhead) const summary = { title: pr.title, state: pr.state, author: pr.user.login, stats: { comments: comments.length, reviews: reviews.length, filesChanged: files.length, approvals: reviews.filter(r => r.state === 'APPROVED').length }, topDiscussion: comments.slice(0, 3).map(c => ({ author: c.user.login, preview: c.body.substring(0, 100) + '...' })) }; console.log(\`PR "\${pr.title}" analysis complete\`); return summary; `); console.log('Analysis Result:', result); // console output: 'PR "Fix memory leak in hooks" analysis complete' ``` --- ## Advanced Features ### **Multi-Protocol Tool Chains** Mix and match different tool ecosystems in a single execution: ```typescript // Register multiple tool sources await client.registerManual({ name: 'github', call_template_type: 'mcp', /* config */ }); await client.registerManual({ name: 'slack', call_template_type: 'http', /* config */ }); await client.registerManual({ name: 'db', call_template_type: 'file', file_path: './db-tools.json' }); // This loads a UTCP manual from a json file const result = await client.callToolChain(` // Fetch PR data from GitHub (MCP) const pr = await github.get_pull_request({ owner: 'company', repo: 'api', pull_number: 42 }); // Query deployment status from database (File) const deployment = await db.get_deployment_status({ pr_id: pr.id }); // Send notification to Slack (HTTP) await slack.post_message({ channel: '#releases', text: \`PR #42 "\${pr.title}" deployed to \${deployment.environment}\` }); return { pr: pr.title, environment: deployment.environment }; `); ``` ### **Runtime Interface Introspection** Tools can dynamically discover and adapt to available interfaces: ```typescript const result = await client.callToolChain(` // Discover available tools at runtime console.log('Available interfaces:', __interfaces); // Get specific tool interface for validation const prInterface = __getToolInterface('github.get_pull_request'); console.log('PR tool expects:', prInterface); // Use interface info for dynamic workflows const hasSlackTools = __interfaces.includes('namespace slack'); if (hasSlackTools) { await slack.post_message({ channel: '#dev', text: 'Analysis complete' }); } return { toolsAvailable: hasSlackTools }; `); ``` ### **Context-Efficient Data Processing** Process large datasets without bloating the model's context: ```typescript const result = await client.callToolChain(` // Fetch large dataset const allIssues = await github.list_repository_issues({ owner: 'facebook', repo: 'react' }); console.log('Fetched', allIssues.length, 'total issues'); // Process efficiently in-sandbox const criticalBugs = allIssues .filter(issue => issue.labels.some(l => l.name === 'bug')) .filter(issue => issue.labels.some(l => l.name === 'high priority')) .map(issue => ({ number: issue.number, title: issue.title, author: issue.user.login, daysOld: Math.floor((Date.now() - new Date(issue.created_at)) / (1000 * 60 * 60 * 24)) })) .sort((a, b) => b.daysOld - a.daysOld); // Only return processed summary (not 10,000 raw issues) return { totalIssues: allIssues.length, criticalBugs: criticalBugs.slice(0, 10), // Top 10 oldest critical bugs summary: \`Found \${criticalBugs.length} critical bugs, oldest is \${criticalBugs[0]?.daysOld} days old\` }; `); ``` ### **Error Handling & Observability** Built-in error handling with complete execution transparency: ```typescript const { result, logs } = await client.callToolChain(` try { console.log('Starting multi-step workflow...'); const data = await external_api.fetch_data({ id: 'user-123' }); console.log('Data fetched successfully'); const processed = await data_processor.transform(data); console.warn('Processing completed with', processed.warnings.length, 'warnings'); return processed; } catch (error) { console.error('Workflow failed:', error.message); throw error; // Propagates to outer error handling } `, 30000); // 30-second timeout // Complete observability console.log('Result:', result); console.log('Execution logs:', logs); // ['Starting multi-step workflow...', 'Data fetched successfully', '[WARN] Processing completed with 2 warnings'] ``` ### **Custom Timeouts** Configure execution limits for different workload types: ```typescript // Quick operations (5 seconds) const quickResult = await client.callToolChain(`return await ping.check();`, 5000); // Heavy data processing (2 minutes) const heavyResult = await client.callToolChain(` const bigData = await database.export_full_dataset(); return await analytics.process_dataset(bigData); `, 120000); ``` --- ## AI Agent Integration Plug-and-play with any AI framework. The built-in prompt template handles all the complexity: ```typescript import { CodeModeUtcpClient } from '@utcp/code-mode'; const systemPrompt = ` You are an AI assistant with access to tools via UTCP CodeMode. ${CodeModeUtcpClient.AGENT_PROMPT_TEMPLATE} Additional instructions... `; // Works with any AI library const response = await openai.chat.completions.create({ model: 'gpt-4', messages: [ { role: 'system', content: systemPrompt }, { role: 'user', content: 'Analyze the latest PR in microsoft/vscode' } ] }); ``` **The template provides comprehensive guidance on:** - Tool discovery workflow (`searchTools` → `__interfaces` → `callToolChain`) - Hierarchical access patterns (`manual.tool()` syntax) - Interface introspection (`__getToolInterface()`) - Error handling and best practices --- ## API Reference ### **Core Methods** #### `callToolChain(code: string, timeout?: number)` Execute TypeScript code with full tool access and observability. - **Returns**: `{result: any, logs: string[]}` with execution result and captured console output - **Default timeout**: 30 seconds #### `getAllToolsTypeScriptInterfaces()` Generate complete TypeScript interfaces for IDE integration. - **Returns**: String containing all interface definitions with namespaces #### `searchTools(query: string)` *(from UtcpClient)* Discover tools using natural language queries. - **Returns**: Array of relevant tools with descriptions and interfaces ### **Static Methods** #### `CodeModeUtcpClient.create(root_dir?, config?)` Create a new client instance with optional configuration. #### `CodeModeUtcpClient.AGENT_PROMPT_TEMPLATE` Production-ready prompt template for AI agents. --- ## Security & Performance ### **Secure by Design** - **Node.js VM sandboxing** – Isolated execution context - **No filesystem access** – Tools only through registered servers - **Timeout protection** – Configurable execution limits - **Zero network access** – No external dependencies or API keys exposed ### **Performance Optimized** - **Minimal memory footprint** – VM contexts are lightweight - **Efficient tool caching** – TypeScript interfaces cached automatically - **Streaming console output** – Real-time log capture without buffering - **Identifier sanitization** – Handles invalid TypeScript identifiers gracefully --- ## Development Experience ### **IDE Integration** Generate TypeScript definitions for full IntelliSense support: ```bash # Generate tool interfaces const interfaces = await client.getAllToolsTypeScriptInterfaces(); await fs.writeFile( … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [universal-tool-calling-protocol](https://github.com/universal-tool-calling-protocol) - **Source:** [universal-tool-calling-protocol/code-mode](https://github.com/universal-tool-calling-protocol/code-mode) - **License:** MPL-2.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** yes - **Shell / process execution:** no - **Environment & secrets:** yes - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-universal-tool-calling-protocol-code-mode - Seller: https://agentstack.voostack.com/s/universal-tool-calling-protocol - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.