
Cursor Delegate
MCP serverHand coding work from Claude Code or Codex to Cursor's CLI agent and review the diff
Runs locally- 1 tool
- Open source
- Developer tools

Hand coding work from Claude Code or Codex to Cursor's CLI agent and review the diff
Runs locally
Hand coding tasks from Claude Code or Cursor to the OpenAI Codex CLI and review the diff
Runs locallySee where your coding agent's tokens and money went, with cache-safe fixes
Runs locally
Hand coding tasks to sandboxed workers and verify each change before it is committed
Runs locallySpawn, read and steer a team of AI coding CLIs running in local tmux windows
Runs locallyShared memory and an email address for your coding agents, via Semantik and Bud
Runs locally
Give coding agents a catalogue of editable React components and complete screens
Not checked yetCatalogue of mini apps your coding agent installs into your own Cloudflare site
Not checked yetLocal MCP server giving coding agents your architectural decisions, plus proposals
Runs locallyShared, human-approved team memory for coding agents and pull request reviews
Not checked yet
Browse TypeScript source mods for SaaS features and prepare a cart for human checkout
Not checked yetFeedback pinned to page elements, readable by coding agents that fix and reply
Not checked yetAccessibility-tree desktop control for coding agents on macOS, Windows and Linux
Runs locallyShared mailbox, handoffs and file-clash warnings for your coding agents
Runs locallyLocal security layer for coding agents: secret redaction, injection checks and MCP proxy
Runs locallyLocal SQLite project memory for AI coding agents, kept across sessions
Runs locallyPersistent requirements, user stories and traceability that coding agents read over MCP
Not checked yetReads any live site in a real browser and gives coding agents its HTML, styles and brand
Not checked yetShared local Markdown memory for coding agents across Copilot, Cursor and Claude Code
Runs locallyGive a coding agent a remote Linux box with Docker, a browser and human takeover
Not checked yetLets a coding agent test your prompts across models and rewrite them, with evidence
Not checked yetPublish an honest build receipt for your project from your coding agent
Not checked yetProduction error tracking your coding agent can search, read and resolve over MCP
Not checked yetTells coding agents what broke since the version they learned, for 60 APIs and SDKs
Not checked yetWaits for a production verdict on each deploy and shows the evidence when a release fails
Runs locallyDecision ledger MCP server that gives coding agents your team's confirmed decisions
Runs locallyLocal-first memory for coding agents that recalls decisions and warns of repeat mistakes
Runs locallyLocal-first memory for coding agents with always-on principles and just-in-time rules
Runs locallyMac key vault where agents get scoped, expiring tokens and never the API keys
Runs locallyReplay reordered responses to find race conditions in a web app, then prove the fix
Runs locally