Hono MCP Server
Exposes Hono API endpoints as Model Context Protocol tools, allowing LLMs to interact with your API routes through a dedicated MCP endpoint. It provides helpers to describe routes and includes a codemode for dynamic API interaction via search and execute tools.
README
MCP Server for Hono
Expose your Hono API endpoints as MCP tools.
Usage
import { Hono } from "hono";
import { z } from "zod";
import { mcp, registerTool } from "hono-mcp-server";
const app = new Hono()
.get("/users", registerTool("List all users"), (c) => c.json([{ id: 1, name: "Alice" }]))
.get("/users/:id", registerTool("Get user by ID"), (c) => c.json({ id: c.req.param("id") }))
.post(
"/users",
registerTool({
description: "Create a new user",
inputSchema: {
name: z.string().describe("User's full name"),
email: z.string().email().describe("User's email address"),
},
}),
async (c) => {
const { name } = c.req.valid("json"); // typed!
return c.json({ id: 1, name });
},
);
export default mcp(app, {
name: "Users API",
version: "1.0.0",
});
This adds an /mcp endpoint that exposes your routes as MCP tools.
Input & Output Schemas
Use registerTool() with inputSchema for validated, typed input. Access validated data with c.req.valid('json'):
import { z } from "zod";
import { registerTool } from "hono-mcp-server";
app.post(
"/search",
registerTool({
description: "Search for items",
inputSchema: {
query: z.string().describe("Search query"),
limit: z.number().optional().describe("Max results"),
},
outputSchema: {
results: z.array(z.object({ id: z.string(), title: z.string() })),
},
}),
async (c) => {
const { query, limit } = c.req.valid("json"); // typed!
return c.json({ results: [] });
},
);
When outputSchema is defined, the tool returns structured content that MCP clients can parse.
Options
mcp(app, {
name: "API Name", // required
version: "1.0.0", // required
description: "...", // optional
instructions: "...", // optional
mcpPath: "/mcp", // optional, default: "/mcp"
codemode: false, // optional, see below
});
Codemode
Instead of exposing individual routes as tools, codemode exposes search and execute tools for dynamic API interaction. Requires Cloudflare Worker Loader.
export default mcp(app, {
name: "API",
version: "1.0.0",
codemode: true,
});
// wrangler.jsonc
{
"worker_loaders": [{ "binding": "LOADER" }],
}
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.