pi-cursor-sdk — MCP Server by fitchmultz

by fitchmultz · MCP Server · ★ 208

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

About pi-cursor-sdk

pi-cursor-sdk A pi provider extension that lets pi use Cursor models through the local agent runtime. Use this extension if you primarily use Cursor models inside pi and want Cursor's local SDK agent loop preserved while pi adds native model selection, auth, thinking/context controls, session behavior, replay UI, and optional pi tool bridging. Why use this instead of an OpenAI-compatible Cursor endpoint? Use when you primarily want to use Cursor models inside pi. This extension runs Cursor models through the local agent runtime and keeps Cursor's agent loop intact. pi integrates around that loop: model discovery, model selection, context-window variants, thinking controls where Cursor exposes them, fast/slow aliases, Cursor mode, session handling, native replay cards, and the optional pi tool bridge. OpenAI-compatible Cursor proxies are useful when you want a generic or endpoint for many clients such as curl, the OpenAI SDK, OpenCode, or other tools. That compatibility comes from translating Cursor behavior into OpenAI-shaped requests, responses, and tool calls. For pi users, that translation is usually the wrong abstraction.

aicursorcursor-sdknpm-packagepipi-extensionpi-packageprovidertypescript

Quick Facts

Stars208
Forks12
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score73.7197504187805/100
Last Updated2026-06-29
Created2026-05-04
Platformsmcp, node
Est. Tokens~24k

Compatible Skills

These tools work well together with pi-cursor-sdk for enhanced workflows:

  • pi-rtk-optimizer — semantic(0.47)+complementary+rare_topics+same_lang+similar_pop+shared_platform (75%)

pi-cursor-sdk alternative? Top 6 similar tools

Looking for a pi-cursor-sdk alternative? If you're comparing pi-cursor-sdk with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • memory-forge-rs by voidcraft-dev · ⭐ 362

    Stop resetting satisfying AI chats — edit the memory instead. Local session manager for Claude Code, Codex & O

  • pi-tool-display by MasuRii · ⭐ 203

    Compact tool call rendering, diff visualization, and output truncation extension for Pi coding agent. Hides, c

  • pi-rtk-optimizer by MasuRii · ⭐ 171

    Pi extension that optimizes RTK command rewriting and tool output compaction for the coding agent.

  • kasetto by pivoshenko · ⭐ 114

    📼 A declarative AI agent environment manager, written in Rust

  • vscode-mcp by tjx666 · ⭐ 86

    MCP server for Claude Code/VSCode/Cursor/Windsurf to use editor self functionality. ⚡ Get real-time LSP diagno

  • pi-dynamic-workflows by QuintinShaw · ⭐ 73

    Claude Code–style dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is pi-cursor-sdk?

pi-cursor-sdk is Run Cursor's agent loop inside the pi coding agent via local Cursor SDK agents, with native model selection, thinking controls, fast/plan modes, image input, and MCP-bridged pi tools.. It is categorized as a MCP Server with 208 GitHub stars.

What programming language is pi-cursor-sdk written in?

pi-cursor-sdk is primarily written in TypeScript. It covers topics such as ai, cursor, cursor-sdk.

How do I install or use pi-cursor-sdk?

You can find installation instructions and usage details in the pi-cursor-sdk GitHub repository at github.com/fitchmultz/pi-cursor-sdk. The project has 208 stars and 12 forks, indicating an active community.

What license does pi-cursor-sdk use?

pi-cursor-sdk is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to pi-cursor-sdk?

The top alternatives to pi-cursor-sdk on Agent Skills Hub include memory-forge-rs, pi-tool-display, pi-rtk-optimizer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools