Plan Wright MCP Server

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. Its 30 documented tools cover planwright, objective, context, initiative. It is available as a remote MCP endpoint.

Teams that want a hosted coding agent endpoint instead of running a local process.

VERIFIED ACTIVE

LAST COMMIT 2026-07-04 · ★ 7 · #176 OF 194 MAINTAINED CODING AGENT · VERIFIED 2026-08-25

NOASSERTION · how we verify → /methodology

01 · Install Plan Wright

Claude Code

claude mcp add planwright-planwright --transport http https://mcp.planwright.tools/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "planwright-planwright": {
      "url": "https://mcp.planwright.tools/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://mcp.planwright.tools/mcp

transport: streamable-http

endpoint alive - authentication required · probed 2026-08-25

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as remote - your agent's requests go to mcp.planwright.tools

endpoint auth requires authentication - rejected our unauthenticated MCP initialize

repo age created 2026-06-30 - young repo, little track record yet

license no standard license detected - usage rights unclear; check the repo before commercial use

registry vendor namespace tools.planwright - domain-verified with the official MCP registry

03 · What Plan Wright can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can set active project for the session (by GitHub repo or project ID), list workspaces you have access to, list projects with IDs and linked GitHub repos, and read a specific context file.

The 30 tools it gives your agent

Extracted from the project's README - what PlanWright lets an agent do.

planwright_set_repo: - Set active project for the session (by GitHub repo or project ID)
planwright_list_workspaces: - List workspaces you have access to
planwright_list_projects: - List projects with IDs and linked GitHub repos
planwright_list_context_files: - List CLAUDE.md, specs, architecture docs for the project
planwright_get_context_file: - Read a specific context file
planwright_push_context_file: - Upload or update a context file
planwright_get_doc_suggestions: - Get pending documentation gap suggestions
planwright_dismiss_doc_suggestion: - Dismiss a doc suggestion
planwright_get_board_url: - Get the Planwright board URL
planwright_list_initiatives: - List initiatives (milestones) for the workspace
planwright_create_initiative: - Create a new initiative
planwright_update_initiative: - Update initiative metadata

show all 30 tools

planwright_delete_initiative: - Delete an initiative
planwright_list_objectives: - List objectives by lane (backlog, scheduled, in_progress, acceptance, done)
planwright_get_objective: - Get full objective details including agent run history
planwright_create_objective: - Create a new objective with acceptance criteria
planwright_update_objective: - Update objective metadata
planwright_schedule_objective: - Move objective from backlog to scheduled
planwright_claim_objective: - Claim a scheduled objective and start an agent run
planwright_append_plan: - Post the agent's decomposition plan
planwright_check_alignment: - Verify work aligns with claimed objective (drift detection)
planwright_record_diff: - Record diff summary and test results
planwright_submit_test_run: - Submit acceptance criteria verification results
planwright_request_acceptance: - Move objective to acceptance lane for human review
planwright_append_note: - Record task completion in the agent run log
planwright_flag_clarity: - Flag objective as having clarity concerns
planwright_override_clarity: - Human override for clarity flags
planwright_list_unenriched: - List objectives/initiatives missing intent summaries
planwright_list_unclassified: - List objectives missing strategic classification
planwright_list_my_bugs: - List bugs for this project

04 · Who maintains Plan Wright

PlanWright is maintained by planwright. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

repository: github.com/planwright/planwright
category: coding agent - ranked #176 of 194 actively-maintained coding agent servers as of 2026-08-25.
registry: tools.planwright/planwright (active, first published 2026-06-30 · 3 versions)

06 · Plan Wright FAQ

Is Plan Wright still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-04. We re-verify nightly.

What can Plan Wright do?

How do I install Plan Wright?

Run `claude mcp add planwright-planwright --transport http https://mcp.planwright.tools/mcp`. You can also paste the ready-made client config above.

Does Plan Wright require authentication?

Yes - when we probed the endpoint on 2026-08-25, it rejected an unauthenticated MCP initialize; you'll need credentials to connect.

07 · Alternatives to Plan Wright

Alternatives to Plan Wright

Maintained coding agent servers if Plan Wright isn't the fit.

Pairs well with

Servers that cover what Plan Wright doesn't - only shown when the pairing reason fits the companion.

More coding agent MCP servers · Pocketlantern · Logbook · Pibox · Java Lens