PlanWright
Objective-native planning board for agent-led development
Ads
Overview
Control plane for autonomous software labor. Planwright is the objective-native planning board for agent-led software development. Humans define outcomes at the Objective layer; coding agents (Claude Code, Cursor, Codex, and others) claim work, decompose tasks, execute, and report back via native MCP—with every state change captured in a hash-chained, Ed25519-signed audit trail. Your browser opens for GitHub login. That's it. See the full agent setup guides for Cursor, Codex, Claude Desktop, and generic MCP clients.
Installation
claude mcp add planwright https://mcp.planwright.tools/mcp
Configuration
Configuration example is not available yet.
Capabilities
- Create and manage objectives
Use `planwright_create_objective` to define outcomes with acceptance criteria, then `planwright_schedule_objective` to queue them for agents.
- Claim and execute agent work
Agents call `planwright_claim_objective` to start a run, `planwright_append_plan` to post a decomposition, and `planwright_request_acceptance` when ready for review.
- Record diffs and test results
Submit code changes via `planwright_record_diff` and verify acceptance criteria with `planwright_submit_test_run`.
- Check for drift during execution
Use `planwright_check_alignment` to confirm the agent's work still matches the claimed objective.
- Surface documentation gaps
Call `planwright_get_doc_suggestions` to find missing context files, then `planwright_push_context_file` to fill them.
- List bugs and enrichment gaps
Query `planwright_list_my_bugs` for known issues and `planwright_list_unenriched` for objectives lacking intent summaries.
Tags
- project-management
- task-management
- development
- ai-agent
Related MCP servers
Context7 MCP
OfficialOfficial Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Chrome DevTools MCP
OfficialOfficial Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Mastra/mcp
OfficialClient implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
GitHub MCP Server
OfficialConnect your AI assistant to GitHub repositories, issues, pull requests, and search.