"Improving Cursor Functionality with Structured Plans and Multi-Step Tasks" matching MCP servers:

Enables agents to run constrained optimization loops on local source files, using Step-5-Preview to propose changes while measuring candidates and returning verified patches.

Enables automated export, compression, and cloud upload of Figma design assets by simply providing Figma links. Supports batch processing of nodes and children, returning structured data with publicly accessible image URLs.

An enhanced MCP server that enables users to interact with NotebookLM while ensuring strict source fidelity and citation accuracy through client-side prompt structuring. It guides Claude to transform user queries into structured prompts that prevent the addition of external knowledge during document analysis.

Enables an LLM to maintain and query durable layered context across sessions, retrieving standing rules, current state, open loops, compiled pages, historical facts, and hard records with explicit conflict handling and abstention when nothing matches.

Enables LLMs to read and write local user data, generate fake users via sampling, and interact with structured prompts and resources.

A fully autonomous patent data marketplace for AI agents, providing highly structured JSON datasets with strategic insights. Supports instant M2M transactions via ROSE on the Oasis Network.

Enables progress-triggered text-to-speech in Cursor Agent, with speak and stop controls and voice matching the system UI language.

A FastMCP server for Cursor platform APIs enabling spend guardrails, cloud agent monitoring, and inter-agent inbox messaging.

Enables AI coding agents to read Microsoft Planner and To Do tasks across multiple M365 tenants with proper authentication, and supports optional write operations limited to tasks the agent created.

An MCP server that exposes ISO 20022 postal-address classification, assessment, and remediation tools for AI agents, enabling them to prepare debtor/creditor addresses for the November 2026 structured-address cutover.

An MCP server and CLI tool that transforms codebases into AI-ready context through semantic search, call graph analysis, and incremental indexing. It enables AI assistants to perform hybrid vector and keyword searches to understand complex repository structures and cross-file relationships.

Enables interactive feedback with image support in Cursor, allowing users to paste images for visual context and feedback.

A flexible proxy server that aggregates multiple backend MCP servers into a single interface using STDIO or SSE transports. It supports dynamic server management via an HTTP API and utilizes namespacing to prevent tool conflicts across connected services.

Enables managing Obsidian Kanban boards and their task notes through the Local REST API, supporting operations like creating, moving, updating tasks and subtasks, and auditing board consistency.

Relays a result screenshot to Slack so you can review a coding agent's output without opening the app.

MCP server for managing multiple SSH servers via AI assistants, offering tools for remote command execution, file operations, and system monitoring.

Enables async-first working practices by providing tools to draft decision docs, convert meetings to async artifacts, score status updates, and triage sync vs async tasks. It also offers reference tools for the Open and Async book's principles and coaching prompts.

Enables AI assistants and other MCP clients to launch and steer Cursor Cloud Agents on repositories or as repo-less research tasks, including model selection, mid-run follow-ups, cancellation, result retrieval, and run listing. Also exposes authentication checks and per-agent or per-run token usage and cost reporting.

Local MCP server that lets Claude Code delegate bounded, read-only tasks to external AI models (Codex, Grok, local OpenAI-compatible servers) via CLIProxyAPI.

An MCP server that exposes tools for sub-agent style reasoning across multiple LLM providers, enabling delegation of prompts to various models and running critique loops, debates, red-teaming, and answer ranking.