convez.ai
MCP Server
achmadya-dev

mcp-core

achmadya-dev/mcp-core

Ver no GitHub
InicialPluginScore · de 0 a 100

Shared MCP server runtime, types, and env helpers for @achmadya-dev MCP packages

Instalação

$npx convez-ai achmadya-dev/mcp-core

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
v0.8.0
Issues abertas
0
Contribuidores
2

README

A tradução para o português deste README ainda está na fila.

@achmadya-dev/mcp-core

Shared MCP SDK wrapper for @achmadya-dev servers: stdio transport, tool registration, JSON-safe responses, and env helpers.

Built on MCP TypeScript SDK v2 (@modelcontextprotocol/server). Tool schemas use Standard Schema — pick any compatible library in your package.

Install

pnpm add @achmadya-dev/mcp-core
# plus a Standard Schema library in your MCP package, e.g. zod, valibot, arktype, …

Installed automatically as a dependency of @achmadya-dev/mcp-*-query servers.

Usage

Pass a Standard Schema object to inputSchema / outputSchema. Examples below use the same tool shape; only the schema library differs.

Zod

pnpm add zod
import * as z from "zod";
import { defineTool, startMcpServer } from "@achmadya-dev/mcp-core";

const myTool = defineTool({
  name: "my_tool",
  description: "Does something",
  inputSchema: z.object({
    name: z.string().describe("Item name"),
  }),
  outputSchema: z.object({ ok: z.boolean() }),
  handler: async ({ name }) => ({ ok: true }),
});

await startMcpServer({ name: "My MCP", version: "1.0.0", tools: [myTool] });

Valibot

pnpm add valibot @valibot/to-json-schema
import * as v from "valibot";
import { toStandardJsonSchema } from "@valibot/to-json-schema";
import { defineTool, startMcpServer } from "@achmadya-dev/mcp-core";

const myTool = defineTool({
  name: "my_tool",
  description: "Does something",
  inputSchema: toStandardJsonSchema(
    v.object({ name: v.pipe(v.string(), v.description("Item name")) })
  ),
  outputSchema: toStandardJsonSchema(v.object({ ok: v.boolean() })),
  handler: async ({ name }) => ({ ok: true }),
});

await startMcpServer({ name: "My MCP", version: "1.0.0", tools: [myTool] });

Other (ArkType, JSON Schema, …)

ArkType — Standard Schema native:

pnpm add arktype
import { type } from "arktype";
import { defineTool, startMcpServer } from "@achmadya-dev/mcp-core";

defineTool({
  name: "my_tool",
  description: "Does something",
  inputSchema: type({ name: "string" }),
  outputSchema: type({ ok: "boolean" }),
  handler: async ({ name }) => ({ ok: true }),
});

Raw JSON Schema — via MCP SDK adapter:

import { fromJsonSchema } from "@modelcontextprotocol/server";
import { defineTool } from "@achmadya-dev/mcp-core";

defineTool({
  name: "my_tool",
  description: "Does something",
  inputSchema: fromJsonSchema({
    type: "object",
    properties: { name: { type: "string", description: "Item name" } },
    required: ["name"],
  }),
  handler: async ({ name }) => ({ ok: true }),
});

Tools with no parameters: use an empty object schema from your library (e.g. z.object({}), toStandardJsonSchema(v.object({})), type({})).

Exports

  • Server, defineTool, ToolError, startMcpServer
  • envStr, envInt, envBool
  • Types: ToolDefinition, ToolInput, JsonValue, RegisterableTool, ServerConfig, StandardSchemaWithJSON, …

Schema builders and runtime validation stay in each @achmadya-dev/mcp-* package.

Release

Uses Changesets — same flow as achmadya-dev/mcp.

  1. Add a changeset when you ship user-facing changes:

    pnpm changeset
    
  2. Push to main. GitHub Actions opens a Version packages PR (version bump + CHANGELOG.md).

  3. Merge that PR. Next push to main publishes to npm (@achmadya-dev/mcp-core).

Remote prerequisites: GitHub secret NPM_TOKEN (npm automation token with bypass 2FA for @achmadya-dev).

Ver o original no GitHub

Relacionados