mcpField
P
powerplan

powerplan

Local
cynacons.github.ioProductivity0Updated today

About powerplan

powerplan is an MCP server for coordinators and worker agents that manage project work through PLAN.md. Its scoped tools support status review and structured task or iteration updates while avoiding freeform edits to the plan file.

Key features

  1. 01Create and inspect PLAN.md
  2. 02View current iteration and progress
  3. 03Add, complete, reopen, or defer tasks
  4. 04Manage iteration lifecycle
  5. 05Check plan structure

Use cases

  1. 01Review the current work at session start
  2. 02Update tasks as work changes
  3. 03Track progress across iterations
  4. 04Validate a project plan's structure

MCP support

Exposes PLAN.md reading, navigation, validation, and structured mutation tools to MCP clients. Optional plan_path selects the file, and server instructions recommend showing the current iteration at the end of major turns.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cynacons-powerplan": {
"command": "uvx",
"args": [
"powerplan-mcp"
],
"env": {
"PYTHONUNBUFFERED": "<PYTHONUNBUFFERED>",
"PYTHONIOENCODING": "<PYTHONIOENCODING>"
}
}
}
}
Run commanduvx powerplan-mcp
Environment variables to set
PYTHONUNBUFFEREDUnbuffered stdio so MCP JSON-RPC flushes immediately.
PYTHONIOENCODINGUTF-8 stdio (needed on Windows).

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypipowerplan-mcp0.10.0

Tools

24

Saved tool list · updated today

ParameterTypeRequiredDescription
plan_pathstringNoOptional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

Details

From the project README

powerplan

PLAN.md as the operational backbone of agentic development.

powerplan is an MCP server that gives coordinators and worker agents a human-language API over your project’s PLAN.md: show progress, create iterations, complete tasks, keep the header truthful — without freeform file thrash.

mcp-name: io.github.CynaCons/powerplan

MCP server namepowerplan
PyPIpowerplan-mcp (powerplan is a different, unrelated package)
Registryio.github.CynaCons/powerplan
Statusv0.9.0 — turn-end status view (PLAN.md)
SiteGitHub Pages
Pairs withPowerSpawn (optional)

Install

You need uv (provides uvx) or Python 3.10+.

uvx powerplan-mcp

That is the stdio MCP server. Point your client at it:

Claude Code / Cursor / .mcp.json
{
  "mcpServers": {
    "powerplan": {
      "command": "uvx",
      "args": ["powerplan-mcp"],
      "env": {
        "PYTHONIOENCODING": "utf-8",
        "PYTHONUNBUFFERED": "1"
      }
    }
  }
}
Claude Desktop

Same block in claude_desktop_config.json (mcpServers).

Grok (~/.grok/config.toml or project config)
[mcp_servers.powerplan]
command = "uvx"
args = ["powerplan-mcp"]
env = { PYTHONUNBUFFERED = "1", PYTHONIOENCODING = "utf-8" }
enabled = true
pip (no uv)
pip install powerplan-mcp
{
  "mcpServers": {
    "powerplan": {
      "command": "python",
      "args": ["-m", "powerplan"],
      "env": {
        "PYTHONIOENCODING": "utf-8",
        "PYTHONUNBUFFERED": "1"
      }
    }
  }
}

Agent guide

Prefer scoped tools. Do not read all of PLAN.md to figure out what to do.

  1. If tools fail with “no PLAN.md” → create_plan first.
  2. show_miniplan — what to work on now, in the plan's own format: the current iteration verbatim with the neighbouring headers. Start every session here.
  3. get_current_iteration — the same, as JSON.
  4. get_iteration(version) — one iteration’s tasks and progress.
  5. Mutate with add_task / add_tasks / complete_task (indexes for several) / start_iteration / close_iteration.
  6. show_plan is a human skim, not a dump.
  7. End every major turn (files changed, tasks ticked or added, a check run, an iteration closed) with show_current_iteration pasted verbatim in a code block, so the user sees status and progress at a glance. The server sends this rule to every client in its MCP instructions.

Every tool accepts optional plan_path (relative or absolute). Default: walk up from cwd to the nearest PLAN.md.

Optional agent on mutations writes a trailing [agent: id] tag on the touched line.


Why

Agents often edit PLAN.md by hand. Headers drift, “COMPLETE” gets stamped without proof, and multi-agent swarms step on each other. powerplan is the single writer: tolerant reader, surgical writer, optional [agent: …] tags.


Tools

ToolBehavior
create_planBootstrap ./PLAN.md (or plan_path) when missing; force to overwrite
show_miniplanSession opener — raw PLAN.md snippet: the current (or named) iteration byte-for-byte, neighbours collapsed to header lines (before/after)
get_current_iterationPreferred for agents — scoped JSON for current work
get_iterationJSON for one version (tasks, progress)
list_iterations / find_task / get_backlogNavigate without full-file reads
create_major / create_iteration / add_task / add_tasksSurgical mutations (batch add in one write)
complete_task / reopen_task / remove_task / defer_taskOne or many (indexes / tasks); optional [agent: id]
start_iteration / close_iterationACTIVE/current vs COMPLETE lifecycle
check_planStructure lint
show_current_iterationTurn closer — status view (status, progress count, goal, tasks) to paste at the end of every major turn
show_planCompact human skim (not a full dump)

Managed plan format

ConstructPattern
Major## vX.Y — Title
Iteration### vX.Y.Z — Title
Goal**Goal:** …
Tasks- [ ] / - [x]
Backlog## Backlog

Phase-like headers and other prose are preserved as opaque blocks.


From source

Clone, editable install, or PowerSpawn submodule — for contributors.

git clone https://github.com/CynaCons/powerplan.git
cd powerplan
pip install -e ".[dev]"
python -m powerplan          # same stdio server
# or: powerplan-mcp

PowerSpawn can vendor this repo as a git submodule. Register both MCP servers — they do not merge:

{
  "mcpServers": {
    "powerplan": {
      "command": "uvx",
      "args": ["powerplan-mcp"]
    },
    "powerspawn": {
      "command": "python",
      "args": ["-m", "powerspawn.mcp_server"]
    }
  }
}

Path-only (no install): python /path/to/powerplan/powerplan_server.py

Landing page: cd site && npm ci && npm run dev


Releasing (maintainers)

Full procedure, identities, and failure history: docs/RELEASING.md. Agent checklist: project skill release-powerplan (/release-powerplan).

Short path: bump every version file listed in that guide → pytest -q → tag vX.Y.Z → push the tag. .github/workflows/publish.yml uploads powerplan-mcp to PyPI, then server.json to the MCP Registry as io.github.CynaCons/powerplan.


License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.