# Screenplay (npm · agent-screenplay)

Beautiful screen recordings of any website or desktop app, scripted by your agent.

- Trust score: 79/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- npm · `agent-screenplay`: 79/100 (this document), [markdown](https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay.md), [page](https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay)

## Channel facts

- Registry: `npm`
- Package: `agent-screenplay`
- Version: `0.1.7`
- 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 2026-11-06.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 41 of 124 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to gmpetrov/agent-screenplay).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 606 tokens (~151/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

Screenplay runs locally as an npm package, launched with npx -y agent-screenplay 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 gmpetrov-agent-screenplay -- npx -y agent-screenplay mcp
```

### Cursor

```json
{
  "mcpServers": {
    "gmpetrov-agent-screenplay": {
      "command": "npx",
      "args": [
        "-y",
        "agent-screenplay",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "gmpetrov-agent-screenplay": {
      "command": "npx",
      "args": [
        "-y",
        "agent-screenplay",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add gmpetrov-agent-screenplay -- npx -y agent-screenplay mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "gmpetrov-agent-screenplay": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agent-screenplay",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add gmpetrov-agent-screenplay --command npx --arg -y --arg agent-screenplay --arg mcp
```

### Hermes

```yaml
mcp_servers:
  gmpetrov-agent-screenplay:
    command: "npx"
    args: ["-y", "agent-screenplay", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "gmpetrov-agent-screenplay": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "agent-screenplay",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add gmpetrov-agent-screenplay -t stdio -c npx -a -y agent-screenplay mcp
```

### Other

```json
{
  "mcpServers": {
    "gmpetrov-agent-screenplay": {
      "command": "npx",
      "args": [
        "-y",
        "agent-screenplay",
        "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.

### 2026-11-05 (score 79, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-11-04 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 64)

First indexed and scored.

## MCP tools (4)

### `screenplay_guide` (~39 tokens)

How to make a good screen recording

The guide to writing Screenplay scenarios: the loop, targets, steps, style, voice-over and direction tips. Read it before the first recording.

### `screenplay_check` (~128 tokens)

Check a scenario

Play the scenario quickly without filming. Reports each step; for a missing element, lists the visible targets you can use instead, with a screenshot of where it stopped. It really performs the steps in the app (a click on Send sends, a click on Delete deletes): use a demo account or a staging environment.

Input parameters:

- `path` (string, required): Path of the scenario JSON file. Prefer an absolute path; a relative one is resolved from the server's working directory.
- `scenario` (object): Optional scenario object: validated, then written to `path` (overwriting that file), then used.

### `screenplay_record` (~180 tokens)

Film and edit a scenario

Film the scenario and edit the video. Returns the MP4 path and the storyboard (one image per step): look at it and fix framing, bubbles or data before handing the video over. Takes about the length of the video plus a few seconds per 10 seconds of video. It really performs the steps in the app (a click on Send sends, a click on Delete deletes): use a demo account or a staging environment.

Input parameters:

- `gif` (boolean): Also write a GIF.
- `noVoice` (boolean): Skip the voice-over even if the scenario enables it.
- `path` (string, required): Path of the scenario JSON file. Prefer an absolute path; a relative one is resolved from the server's working directory.
- `scenario` (object): Optional scenario object: validated, then written to `path` (overwriting that file), then used.

### `screenplay_render` (~159 tokens)

Edit the last recording again

Re-edit the last recording of this scenario without filming: use it after changing text, narration (say), callouts, style, zoom or output. Changing actions needs screenplay_record. Does not touch the app; writes the video files, and sends new narration text to Cartesia or ElevenLabs when the scenario enables voice-over.

Input parameters:

- `gif` (boolean): Also write a GIF.
- `noVoice` (boolean): Skip the voice-over even if the scenario enables it.
- `path` (string, required): Path of the scenario JSON file. Prefer an absolute path; a relative one is resolved from the server's working directory.
- `scenario` (object): Optional scenario object: validated, then written to `path` (overwriting that file), then used.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay#diagnostics

## Score history

- 2026-11-06: 79
- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 64

## Common questions

### What is the Screenplay MCP server?

Screenplay is an MCP server listed in the public MCP registry as io.github.gmpetrov/agent-screenplay. Beautiful screen recordings of any website or desktop app, scripted by your agent. This page covers its npm package (agent-screenplay).

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

Screenplay scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Screenplay MCP server expose?

Screenplay exposes 4 tools: screenplay_guide, screenplay_check, screenplay_record, screenplay_render. Their descriptions and schemas cost roughly 506 tokens of context every time the server is loaded.

### Is the Screenplay MCP server still maintained?

Screenplay is still listed as active in the MCP registry. We last reached this channel on 6 November 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 Screenplay MCP server under?

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

### What did VerifyMCP test on the Screenplay MCP server?

VerifyMCP ran 14 checks on Screenplay, covering Malware scan, Known CVEs, Install scripts, Dependency health and 10 more. 2 items could not be completed, a gap on our side rather than a finding about Screenplay: Security disclosure and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/agent-screenplay
- Socket report: https://socket.dev/npm/package/agent-screenplay
- Repository: https://github.com/gmpetrov/agent-screenplay
- Changelog RSS feed: https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay.xml
- Changelog JSON feed: https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay.json
- HTML version of this page: https://verifymcp.io/servers/gmpetrov-agent-screenplay/agent-screenplay