mcp-toolkit-ts
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
🟦 mcp-toolkit-ts
Production-ready Model Context Protocol (MCP) server toolkit for autonomous AI agents with typed schemas and safety guardrails.
⚡ Highlights
🔒 Strongly Typed Tools: Define agent tools with parameter schemas and auto-generated JSON Schema manifests.
🤖 Agent Client Compatible: Out-of-the-box support for Claude Desktop, Cursor, Antigravity, and OpenAI assistants.
🛡️ Parameter Validation: Enforces parameter requirements, type safety, and error feedback before tool invocation.
🚀 Zero Bloat: Minimal runtime footprint designed for fast cold starts.
Related MCP server: mcp-agent-kit
📦 Installation
npm install mcp-toolkit-ts💻 Quick Start
import { MCPServer, ToolDefinition } from 'mcp-toolkit-ts';
const server = new MCPServer('my-agent-tools', '1.0.0');
// Register a custom typed tool
server.registry.register({
name: 'calculate_growth',
description: 'Calculate compounded interest rate for financial simulations',
parameters: {
principal: { type: 'number', description: 'Initial balance', required: true },
rate: { type: 'number', description: 'Annual interest rate percentage', required: true },
years: { type: 'number', description: 'Simulation duration in years', required: true },
},
handler: async ({ principal, rate, years }) => {
return principal * Math.pow(1 + rate / 100, years);
},
});
// Handle incoming MCP JSON-RPC call
const response = await server.handleRequest({
method: 'tools/call',
params: {
name: 'calculate_growth',
arguments: { principal: 1000, rate: 5, years: 3 }
}
});
console.log('Result:', response); // 1157.625📄 License
MIT License © 2026 Ismeet Pandey.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Convert, lint and generate LLM tool schemas for OpenAI, Anthropic, Gemini and MCP
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTurns any ML model into an MCP tool with auto-inferred schemas, input/output validation, and structured error handling.1MIT
- AlicenseAqualityBmaintenanceEnables building and running zero-dependency MCP servers with automatic JSON Schema generation, exposing Python tools to Claude Desktop, Cursor, and autonomous agent fleets.2Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants and MCP-enabled clients to discover and call application capabilities exposed as structured, schema-defined tools, with input validation, error handling, and API/database integration. It also ships a sample client that demonstrates secure tool execution and seamless AI-agent interoperability.-
- AlicenseNot gradedqualityBmaintenanceEnables developers to expose a single set of tool definitions as MCP server tools over stdio or Streamable HTTP, so Claude Code, Codex, Claude Desktop and Cursor can call them with risk-based annotations, human-approved irreversible writes, typed structured results and long-running job handling built in. It also ships the same tools as a CLI from one source, keeping both surfaces in parity.594 npmApache 2.0