"Improving Cursor Efficiency and Smart Features" matching MCP servers:

Provides Claude with persistent memory and learning capabilities through 10 automatic agents that capture decisions, errors, solutions, and patterns across conversations. Features an anti-compaction system to prevent context loss and enables infinite conversation continuity.

An MCP server that lets Claude spawn Cursor subagents as async, bounded workers, enabling non-blocking task delegation with asynchronous completion notifications.

Enables delegating coding tasks to Cursor Cloud Agents from Claude Code, Codex, or Grok, with scoped repository access, progress monitoring, follow-ups, and result reporting.

Monitors your Cursor usage and provides a conserve flag to the agent, helping you manage request quota by batching questions, preferring defaults, and cutting unnecessary confirmations.

Enables an orchestrator like Claude Code to hand coding work off to Cursor SDK agents, run as detached background jobs that survive the session and can be listed, inspected, steered, resumed, or stopped. Agents are asynchronous and reusable across follow-up turns, letting expensive frontier models delegate cheaply without blocking or paying to read the results.

Enables MCP clients to delegate bounded tasks to an explicitly selected Cursor model with durable, restart-safe run state, idempotent runs, and fail-closed security defaults.

Enables delegating coding tasks to the local cursor-agent CLI synchronously, blocking until completion and returning a compact report with diff, status, and session ID.

A sophisticated MCP server that provides a multi-dimensional, adaptive reasoning framework for AI assistants, replacing linear reasoning with a graph-based architecture for more nuanced cognitive processes.

Enables Claude Code to delegate tasks to Cursor's headless agent, run adversarial reviews, and verify findings with prosecutor/advocate roles.

Enables two-way delegation between Codex and Cursor agents with background jobs, handoff plans, and isolated worktrees, allowing either editor to offload investigation, review, planning, or implementation to the other and continue the same native session later.

Token-efficient browser automation for AI agents, filtering the DOM to only interactive elements and grouping them by page section, reducing token usage by 3-13x compared to Playwright MCP.

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.

Allows AI assistants to access and analyze your Cursor conversation history, enabling personalized coding assistance based on your actual development patterns.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables AI assistants and MCP clients to launch and manage Cursor Cloud Agents on repositories or without one, select models, follow up mid-run, retrieve or cancel results, and check usage and cost.

Enables users to control the cursor in Figma through verbal commands using an agentic AI agent, streamlining the design process with a new interaction method.

Wraps the cursor-agent CLI to provide cost-effective tools for repository analysis, code search, planning, and editing. Offloads heavy thinking tasks from the host AI to reduce token usage while maintaining precise, scoped workspace operations.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

Enables orchestrator models to delegate code creation and editing to Cursor's Composer 2 or Grok 4.5 agents, keeping the orchestrator's context free and shifting bulk code generation to cheaper agents.

A single MCP server that fronts many downstream MCP servers and Skills, exposing only four tools (search, call_tool, use_skill, admin) so that an agent's context window only ever sees search results on demand.