"How to invoke Claude code or API" matching MCP servers:

MCP server that pushes Feishu (Lark) messages to Claude Code sessions and allows Claude to reply directly in Feishu.

Enables MCP clients to turn Make blueprints and Zapier exports into n8n workflow files, with a per-step report of what converted, what to review, and what must be finished by hand. Also lists zaps, explains how individual steps are handled, checks workflow files for broken links or placeholders, and can upload the result to an n8n instance as an inactive workflow.

Enables AI clients like Claude to read and manage Microsoft To Do task lists and tasks via the Microsoft Graph API, running locally over stdio with secure token storage.

MCP server for Microsoft To Do via Microsoft Graph. MSAL device code flow, no client secret needed.

Enables managing Microsoft To Do lists and tasks through MCP, including creating, updating, completing, deleting, searching, and checklist operations via Microsoft Graph.

Enables to manage to-do items through natural language, with tools for creating, reading, updating, and deleting tasks.

Enables AI-powered project management by connecting Claude to Planka kanban boards via 75+ MCP tools for creating, updating, and managing projects, boards, lists, and cards.

Enables Claude to manage Apple Reminders on macOS, providing full CRUD operations such as listing, searching, creating, updating, and deleting reminders.

Enables Claude to manage local markdown notes and todos, search notes, and perform text utilities like word/character counting and slug generation. All data is stored locally without external APIs or accounts.

A Model Context Protocol (MCP) server that enables AI assistants like Claude and Cursor to interact with Microsoft To Do via the Microsoft Graph API.

Enables Claude Code to read and write Google Sheets, including cell operations, row appending, sheet creation, formatting, and batch updates via the Google Sheets API.

Enables users to run Claude Code from Telegram with voice notes both ways, persistent memory, live tool-call progress, and 24/7 daemon supervision. It also adds scheduled messages, Google Calendar integration, inline buttons, and session/subagent monitoring.

Enables Claude to read, rewrite, generate, and summarize LibreOffice Writer documents with preview-then-apply editing through MCP tools, authenticating via Claude Code login.

Enables Claude Code to interact with Slack via MCP tools, allowing thinking steps, text streaming, status updates, and stream closure in Slack threads.

Enables driving a Claude Code session from a personal or business chat account, with bidirectional messaging, full media support, local voice transcription, per-group personalities, emoji-reaction tool approval, and pairing-code access control. Runs over either a linked-device connection or Meta's official Cloud API, with no API keys or Docker required.

Enables a weekly review of Todoist tasks by listing overdue tasks with key signals (days overdue, priority, times postponed) and letting Claude propose fixes per task, which you approve or veto in chat before any changes are applied.

Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.

Render PDFs and images from HTML templates (Jinja2, Liquid, Handlebars) or Word and PowerPoint files through the Formfeed API, check data against a template's schema before rendering, and convert Office documents to PDF.

Generate professional AI-powered presentations from a topic, raw text, or document file. Export to PPTX, PDF, image, or shareable link.

Search, document and execute authenticated API calls across all your apps (Gmail, Slack, Stripe, Notion, GitHub, and more) through 4 universal tools whose context footprint stays constant no matter how many connections you add. Hosted remote server with OAuth at https://mcp.withone.ai/mcp, or run locally via npx @withone/mcp.