otask-mcp-server
MCP server and HTTP proxy for O!task API that enables managing tasks (get, update) through natural language.
README
otask-mcp-server
MCP-сервер для O!task API.
Режимы запуска
| Режим | Команда | Клиент |
|---|---|---|
| MCP stdio | bun start |
Cursor / OpenCode |
| MCP Streamable HTTP | bun run start:http |
n8n MCP Client Tool |
Аутентификация HTTP (/mcp)
Всегда через заголовок Authorization: Bearer … от HTTP-клиента. Два сценария:
1. Gateway (серверные credentials в env)
Сервер сам ходит в O!task API. Endpoint нельзя оставлять открытым.
OTASK_AUTH_KEY=... # или OTASK_EMAIL + OTASK_PASSWORD
MCP_AUTH_TOKEN=... # обязателен в gateway-режиме
Клиент (n8n):
Authorization: Bearer <MCP_AUTH_TOKEN>
2. Passthrough (без OTASK_* в env)
Сервер не хранит credentials O!task. Bearer клиента пробрасывается в api.otask.ru.
# OTASK_* не заданы
Клиент (n8n):
Authorization: Bearer <O!task token>
Тот же токен, что для прямых вызовов O!task API.
Stdio (локально)
Только gateway-логика через env (без MCP_AUTH_TOKEN):
OTASK_AUTH_KEY=...
# или OTASK_EMAIL + OTASK_PASSWORD
MCP HTTP endpoint
| URL | https://otask-mcp.grigoreo.dev/mcp |
| Health | GET /health → { ok, authMode: "gateway" | "passthrough" } |
| Порт | 3847 |
n8n MCP Client Tool
- URL:
https://otask-mcp.grigoreo.dev/mcp - Transport: HTTP Streamable
- Gateway: credential с
MCP_AUTH_TOKEN - Passthrough: credential с O!task Bearer (как в workflow 009)
Tools: otask_get_task, otask_update_task.
Добавление нового tool
src/services/api.ts— низкоуровневый fetch (если нужен новый endpoint)src/services/client.ts— метод наOtaskClient(bind auth уже внутри)src/schemas/— Zod-схема входных параметровsrc/tools/my-tool.ts— фабрикаcreateMyTool({ api })→ToolDefinitionsrc/tools/registry.ts— одна строка в массивtoolFactories
Пример скелета:
// src/tools/my-tool.ts
import { MyInputSchema, type MyInput } from "../schemas/my.js";
import { jsonToolResult, toolError } from "./helpers.js";
import type { ToolDefinition, ToolDeps } from "./types.js";
export function createMyTool({ api }: ToolDeps): ToolDefinition<MyInput> {
return {
name: "otask_my_tool",
config: {
title: "...",
description: "...",
inputSchema: MyInputSchema,
annotations: { readOnlyHint: true },
},
handler: async (input) => {
try {
const data = await api.myMethod(input);
return jsonToolResult(data);
} catch (error) {
return toolError(error);
}
},
};
}
server.ts и register.ts трогать не нужно — регистрация централизована.
Разработка
bun install && bun run build
bun start # stdio
bun run dev:http # HTTP hot reload
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.