# powerplan (pypi · powerplan-mcp)

MCP server that makes PLAN.md the operational backbone of agentic development

- Trust score: 67/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `powerplan-mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/cynacons-powerplan/powerplan-mcp.md), [page](https://verifymcp.io/servers/cynacons-powerplan/powerplan-mcp)

## Channel facts

- Registry: `pypi`
- Package: `powerplan-mcp`
- Version: `0.8.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it.
  - 0 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2588 tokens (~107/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 97/100
  - Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 68% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "remove_task" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the powerplan MCP server?

powerplan runs locally as a PyPI package, launched with uvx powerplan-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add cynacons-powerplan -- uvx powerplan-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "cynacons-powerplan": {
      "command": "uvx",
      "args": [
        "powerplan-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cynacons-powerplan": {
      "command": "uvx",
      "args": [
        "powerplan-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cynacons-powerplan -- uvx powerplan-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cynacons-powerplan": {
      "type": "local",
      "command": [
        "uvx",
        "powerplan-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cynacons-powerplan --command uvx --arg powerplan-mcp
```

### Hermes

```yaml
mcp_servers:
  cynacons-powerplan:
    command: "uvx"
    args: ["powerplan-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "cynacons-powerplan": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "powerplan-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cynacons-powerplan -t stdio -c uvx -a powerplan-mcp
```

### Other

```json
{
  "mcpServers": {
    "cynacons-powerplan": {
      "command": "uvx",
      "args": [
        "powerplan-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 66, 0)

- [functional] Package version: 0.7.0 → 0.8.0

### 2026-09-18 (score 66, +1)

- [functional regression] Security disclosure: unverified → fail

### 2026-09-17 (score 65, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-09-16 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 63, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-12 (score 78, +16)

- [security improvement] Malware scan: unverified → pass

## MCP tools (24)

### `get_current_iteration` (~64 tokens)

JSON for the *current* iteration (what to work on now). Preferred agent entry — avoids reading all of PLAN.md.

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

### `get_iteration` (~58 tokens)

JSON for one iteration by version (goal, tasks, progress).

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `version` (string, required)

### `list_iterations` (~55 tokens)

List iterations filtered by open | complete | all.

Input parameters:

- `filter` (string)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

### `find_task` (~53 tokens)

Locate tasks by substring match (JSON).

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `text` (string, required)

### `get_backlog` (~46 tokens)

Backlog section items (JSON).

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

### `show_miniplan` (~137 tokens)

Raw PLAN.md snippet: the current (or named) iteration byte-for-byte under its major header, with the neighbouring iterations collapsed to their header lines. The plan's own format is the view — start every session here instead of reading the whole file.

Input parameters:

- `after` (integer): Following iterations shown as header lines only.
- `before` (integer): Preceding iterations shown as header lines only.
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `version` (string): Iteration to show; default = the current iteration.

### `show_current_iteration` (~52 tokens)

ASCII view of the resolved current iteration (humans/logs).

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

### `show_plan` (~62 tokens)

Compact index: counts + current iteration. Agents should prefer get_current_iteration / get_iteration over this or full PLAN.md.

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

### `check_plan` (~52 tokens)

Structure lint: duplicates, multiple current, complete-with-open-tasks.

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.

### `create_plan` (~127 tokens)

Bootstrap a new PLAN.md when none exists (powernote-style skeleton). Default path: ./PLAN.md in cwd. Refuses overwrite unless force=true.

Input parameters:

- `force` (boolean): Overwrite existing file if true.
- `goal` (string)
- `philosophy` (string)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `seed_major` (boolean): Include v0.1 / v0.1.0 starter shell (default true).
- `title` (string, required)

### `create_major` (~69 tokens)

Create ## vX.Y — Title major section.

Input parameters:

- `description` (string)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `title` (string, required)
- `version` (string, required)

### `create_iteration` (~111 tokens)

Create ### vX.Y.Z — Title iteration.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `description` (string)
- `goal` (string)
- `major` (string)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `status` (string)
- `title` (string, required)
- `version` (string, required)

### `set_iteration_goal` (~63 tokens)

Set/replace **Goal:** on an iteration.

Input parameters:

- `goal` (string, required)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `version` (string, required)

### `add_task` (~88 tokens)

Append a checkbox task to an iteration.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `done` (boolean)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `text` (string, required)
- `version` (string, required)

### `add_tasks` (~119 tokens)

Append several checkbox tasks in one write. Prefer this over repeated add_task. Shared done/agent apply to every item.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `done` (boolean): Mark every added task done (default false).
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `tasks` (array, required): Task texts to append, in order.
- `version` (string, required)

### `complete_task` (~222 tokens)

Tick one or many tasks in one write. For several, pass indexes (preferred after get_iteration) or tasks. For exactly one, index or task still work.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `expect` (string): Optional guard for a single task: current text must match or the edit is refused. Ignored/rejected with tasks/indexes. Agent tags are ignored in the comparison.
- `index` (integer): One 1-based position. One addressing mode.
- `indexes` (array): Several 1-based positions. Prefer this after get_iteration. One write. One addressing mode.
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `task` (string): One task (exact, else unique substring). One addressing mode.
- `tasks` (array): Several task texts (exact, else unique substring). One write. One addressing mode.
- `version` (string, required)

### `reopen_task` (~217 tokens)

Untick one or many tasks in one write. For several, pass indexes or tasks. For exactly one, index or task still work.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `expect` (string): Optional guard for a single task: current text must match or the edit is refused. Ignored/rejected with tasks/indexes. Agent tags are ignored in the comparison.
- `index` (integer): One 1-based position. One addressing mode.
- `indexes` (array): Several 1-based positions. Prefer this after get_iteration. One write. One addressing mode.
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `task` (string): One task (exact, else unique substring). One addressing mode.
- `tasks` (array): Several task texts (exact, else unique substring). One write. One addressing mode.
- `version` (string, required)

### `update_task` (~257 tokens)

Rewrite task text, preserving done state. One task: text + index/task. Several: changes[{text, index|task, expect?}].

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `changes` (array): Several rewrites in one write. Do not mix with the singular text + index/task shape.
- `expect` (string): Optional guard for a single task: current text must match or the edit is refused. Ignored/rejected with tasks/indexes. Agent tags are ignored in the comparison.
- `index` (integer): One 1-based position. One addressing mode.
- `indexes` (array): Several 1-based positions. Prefer this after get_iteration. One write. One addressing mode.
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `task` (string): One task (exact, else unique substring). One addressing mode.
- `tasks` (array): Several task texts (exact, else unique substring). One write. One addressing mode.
- `text` (string): New text for a single task.
- `version` (string, required)

### `remove_task` (~195 tokens)

Delete one or many tasks in one write. For several, pass indexes or tasks. Resolve-all then drop (indexes do not shift).

Input parameters:

- `expect` (string): Optional guard for a single task: current text must match or the edit is refused. Ignored/rejected with tasks/indexes. Agent tags are ignored in the comparison.
- `index` (integer): One 1-based position. One addressing mode.
- `indexes` (array): Several 1-based positions. Prefer this after get_iteration. One write. One addressing mode.
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `task` (string): One task (exact, else unique substring). One addressing mode.
- `tasks` (array): Several task texts (exact, else unique substring). One write. One addressing mode.
- `version` (string, required)

### `defer_task` (~233 tokens)

Move one or many tasks to the backlog in one write. For several, pass indexes or tasks. Shared reason/agent apply to every item.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `expect` (string): Optional guard for a single task: current text must match or the edit is refused. Ignored/rejected with tasks/indexes. Agent tags are ignored in the comparison.
- `index` (integer): One 1-based position. One addressing mode.
- `indexes` (array): Several 1-based positions. Prefer this after get_iteration. One write. One addressing mode.
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `reason` (string): Optional why, appended to the backlog entry.
- `task` (string): One task (exact, else unique substring). One addressing mode.
- `tasks` (array): Several task texts (exact, else unique substring). One write. One addressing mode.
- `version` (string, required)

### `add_to_backlog` (~115 tokens)

Append one (text) or many (texts) items to Future (Backlog) in one write.

Input parameters:

- `agent` (string): Optional agent id tag written as [agent: id] on touched lines.
- `checkbox` (boolean)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `text` (string): One backlog item.
- `texts` (array): Several backlog items, in order. One write.

### `append_prose` (~54 tokens)

Append freeform markdown at top level.

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `text` (string, required)

### `start_iteration` (~56 tokens)

Mark iteration ACTIVE / current; clears other current markers.

Input parameters:

- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `version` (string, required)

### `close_iteration` (~83 tokens)

Mark iteration COMPLETE. Requires force=true if open tasks remain. Optional stamp (e.g. date) appended to title.

Input parameters:

- `force` (boolean)
- `plan_path` (string): Optional path to PLAN.md (relative to cwd or absolute). Default: walk up from cwd to nearest PLAN.md.
- `stamp` (string)
- `version` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/cynacons-powerplan/powerplan-mcp#diagnostics

## Score history

- 2026-09-20: 67
- 2026-09-19: 66
- 2026-09-18: 66
- 2026-09-17: 65
- 2026-09-16: 65
- 2026-09-15: 64
- 2026-09-14: 64
- 2026-09-13: 63
- 2026-09-12: 78
- 2026-09-11: 62
- 2026-09-10: 62
- 2026-09-09: 61
- 2026-09-08: 61
- 2026-09-07: 60
- 2026-09-06: 75
- 2026-09-05: 60
- 2026-09-04: 74
- 2026-09-03: 59
- 2026-09-02: 58
- 2026-09-01: 73
- 2026-08-31: 57
- 2026-08-30: 72
- 2026-08-29: 71
- 2026-08-28: 71
- 2026-08-27: 70
- 2026-08-26: 55
- 2026-08-25: 68
- 2026-08-24: 53
- 2026-08-23: 68
- 2026-08-22: 68

## Common questions

### What is the powerplan MCP server?

powerplan is an MCP server listed in the public MCP registry as io.github.CynaCons/powerplan. MCP server that makes PLAN.md the operational backbone of agentic development. This page covers its PyPI package (powerplan-mcp).

### Is the powerplan MCP server safe to use?

powerplan scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the powerplan MCP server expose?

powerplan exposes 24 tools: get_current_iteration, get_iteration, list_iterations, find_task, get_backlog, and 19 more. Their descriptions and schemas cost roughly 2,588 tokens of context every time the server is loaded.

### Is the powerplan MCP server still maintained?

powerplan is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the powerplan MCP server under?

powerplan declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/powerplan-mcp/
- Socket report: https://socket.dev/pypi/package/powerplan-mcp
- Repository: https://github.com/CynaCons/powerplan
- Website: https://cynacons.github.io/powerplan/
- Changelog RSS feed: https://verifymcp.io/servers/cynacons-powerplan/powerplan-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/cynacons-powerplan/powerplan-mcp.json
- HTML version of this page: https://verifymcp.io/servers/cynacons-powerplan/powerplan-mcp