JIT Tool Synthesis
Enables on-demand generation of TypeScript tools using an LLM with human-in-the-loop approval and safe sandboxed execution. It allows users to create and persist custom functionality through natural language requests.
README
JIT Tool Synthesis v2
LLM-powered on-demand tool generation with human-in-the-loop approval and safe execution.
Overview
This system generates TypeScript tools dynamically using an LLM, requires human approval before execution, and runs them in a sandboxed environment.
Architecture
┌─────────────┐ ┌──────────────┐ ┌─────────────┐
│ Synthesizer │────▶│ Approval │────▶│ Sandbox │
│ (LLM) │ │ (Human Gate) │ │ (Execution) │
└─────────────┘ └──────────────┘ └─────────────┘
│ │ │
▼ ▼ ▼
Generates TS Waits for Runs in
tool code human approval isolated env
Components
| File | Purpose |
|---|---|
synthesizer.ts |
Generates TypeScript code using OpenRouter LLM |
approval.ts |
Human-in-the-loop gate — requires approval before execution |
sandbox.ts |
Safe execution environment for generated code |
registry.ts |
Tool persistence and storage |
server.ts |
MCP server integration |
Setup
# Install dependencies
npm install
# Copy environment template
cp .env.example .env
# Add your OpenRouter API key to .env
OPENROUTER_API_KEY=your_key_here
Usage
Start the MCP Server
npm run dev
Claude Desktop Integration
Import the config:
# Copy Claude Desktop config
cat claude-desktop-config.json
Add the JSON to your Claude Desktop settings under mcpServers.
CLI Commands
# Generate and approve a tool
npm run cli -- synthesize "Create a weather tool that fetches from wttr.in"
# List available tools
npm run cli -- list
# Execute a tool
npm run cli -- execute <tool-id>
Workflow
- Request — User asks for a tool (e.g., "create a weather fetcher")
- Synthesize — LLM generates TypeScript code
- Approve — Human reviews and approves the code
- Execute — Tool runs in sandboxed environment
- Store — Approved tools persist in registry
Environment Variables
| Variable | Description |
|---|---|
OPENROUTER_API_KEY |
API key for LLM tool generation |
PORT |
Server port (default: 3000) |
Status
In Progress — MVP complete, end-to-end testing in progress.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.