# AgentTakt (pypi · agenttakt)

Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal

- Trust score: 36/100 (low)
- Change this week: −43
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-23

## Components

- pypi · `agenttakt`: 36/100 (this document), [markdown](https://verifymcp.io/servers/ryoohshima-agenttakt/agenttakt.md), [page](https://verifymcp.io/servers/ryoohshima-agenttakt/agenttakt)

## Channel facts

- Registry: `pypi`
- Package: `agenttakt`
- Version: `0.2.2`
- 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 2026-09-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 1 of 36 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 0/100
  - Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- **Capabilities**: 0/100
  - Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet.

**Unverified: 5 categories.** Categories scored 0 because our sandbox run of this package has not given us the schema these checks need to read. That is a gap on our side rather than a finding about the package, and we only credit what we can confirm, so the score stands at 0 until the capture succeeds. We are working through the fleet, so this normally clears without any action from you.

## Install

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

AgentTakt runs locally as a PyPI package, launched with uvx agenttakt. 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 ryoohshima-agenttakt -- uvx agenttakt
```

### Cursor

```json
{
  "mcpServers": {
    "ryoohshima-agenttakt": {
      "command": "uvx",
      "args": [
        "agenttakt"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ryoohshima-agenttakt": {
      "command": "uvx",
      "args": [
        "agenttakt"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ryoohshima-agenttakt -- uvx agenttakt
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ryoohshima-agenttakt --command uvx --arg agenttakt
```

### Hermes

```yaml
mcp_servers:
  ryoohshima-agenttakt:
    command: "uvx"
    args: ["agenttakt"]
```

### Netclaw

```json
{
  "McpServers": {
    "ryoohshima-agenttakt": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "agenttakt"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ryoohshima-agenttakt -t stdio -c uvx -a agenttakt
```

### Other

```json
{
  "mcpServers": {
    "ryoohshima-agenttakt": {
      "command": "uvx",
      "args": [
        "agenttakt"
      ]
    }
  }
}
```

## 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.

### 2026-09-23 (score 36, −42)

- [security regression] Stability: 0.97 → unverified
- [security regression] Tool safety: pass → unverified
- [security] Stability: 0.97 → pass
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.2.1 → 0.2.2

### 2026-09-21 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 76, −3)

- [functional] Stability: pass → 0.80

### 2026-09-16 (score 79, +1)

- [security] Stability: 0.97 → pass

### 2026-09-15 (score 78, −1)

- [functional] Stability: pass → 0.97

### 2026-09-14 (score 79, +1)

- [security] Stability: 0.97 → pass

### 2026-09-12 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (2)

### `request_approval` (~141 tokens)

Submit a task execution plan for human review in the AgentTakt editor.

Blocks until the human approves or rejects the plan in the TUI. Returns
{"status": "approved" | "rejected", "plan": <edited plan>, "reason": <str | null>}.
The returned plan may differ from the submitted one (the human can edit
nodes, edges and parameters) — always execute the returned plan.

Args:
    plan: Plan JSON with graph_id, nodes[] and edges[] (must be a DAG).
    summary: One-line description shown in the editor header.

Input parameters:

- `plan` (object, required)
- `summary`

### `show_plan` (~148 tokens)

Display a task execution plan in the AgentTakt editor, without blocking.

Call this whenever you have formulated a multi-step plan — in any mode,
not just plan mode — so the human can see it as a node graph. Returns
{"status": "displayed"} as soon as the editor receives the plan; it does
NOT wait for (or report) any human decision. Use request_approval instead
when you need the human's approval before executing.

Args:
    plan: Plan JSON with graph_id, nodes[] and edges[] (must be a DAG).
    summary: One-line description shown in the editor header.

Input parameters:

- `plan` (object, required)
- `summary`

## Diagnostics

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

## Score history

- 2026-09-23: 36
- 2026-09-22: 78
- 2026-09-21: 78
- 2026-09-20: 77
- 2026-09-19: 77
- 2026-09-18: 76
- 2026-09-17: 76
- 2026-09-16: 79
- 2026-09-15: 78
- 2026-09-14: 79
- 2026-09-13: 78
- 2026-09-12: 78
- 2026-09-11: 77
- 2026-09-10: 77
- 2026-09-09: 76
- 2026-09-08: 76
- 2026-09-07: 79
- 2026-09-06: 79
- 2026-09-05: 78
- 2026-09-04: 78
- 2026-09-03: 77
- 2026-09-02: 77
- 2026-09-01: 76
- 2026-08-31: 76
- 2026-08-30: 75
- 2026-08-29: 75
- 2026-08-28: 74
- 2026-08-27: 74
- 2026-08-26: 73
- 2026-08-25: 71

## Common questions

### What is the AgentTakt MCP server?

AgentTakt is an MCP server listed in the public MCP registry as io.github.ryoohshima/agenttakt. Review, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal. This page covers its PyPI package (agenttakt).

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

AgentTakt scores 36 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 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 AgentTakt MCP server expose?

AgentTakt exposes 2 tools: request_approval, show_plan. Their descriptions and schemas cost roughly 289 tokens of context every time the server is loaded.

### Is the AgentTakt MCP server still maintained?

AgentTakt is still listed as active in the MCP registry. We last reached this channel on 23 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/agenttakt/
- Socket report: https://socket.dev/pypi/package/agenttakt
- Repository: https://github.com/ryoohshima/AgentTakt
- Changelog RSS feed: https://verifymcp.io/servers/ryoohshima-agenttakt/agenttakt.xml
- Changelog JSON feed: https://verifymcp.io/servers/ryoohshima-agenttakt/agenttakt.json
- HTML version of this page: https://verifymcp.io/servers/ryoohshima-agenttakt/agenttakt