# Renderdoc Analysis

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-dcc-mcp-dcc-mcp-renderdoc-renderdoc-analysis`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [dcc-mcp](https://agentstack.voostack.com/s/dcc-mcp)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [dcc-mcp](https://github.com/dcc-mcp)
- **Source:** https://github.com/dcc-mcp/dcc-mcp-renderdoc/tree/main/src/dcc_mcp_renderdoc/skills/renderdoc-analysis
- **Website:** https://pypi.org/project/dcc-mcp-renderdoc/

## Install

```sh
agentstack add skill-dcc-mcp-dcc-mcp-renderdoc-renderdoc-analysis
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# RenderDoc Analysis

Inspect before exporting. These tools never modify the input `.rdc`; exports require an explicit
destination path and create its parent directory when needed.

Use `export_drawcall_resources` with an exact event ID to export only texture resources that the
pixel shader reports as used at that event. The result records binding, resource name, dimensions,
format, and output file for each PNG.

Inspection reports `draw_dispatch_count`, `frame_work_count`, `present_count`, and
`frame_content_status` so a structurally readable capture with no rendering work is not mistaken
for a usable frame.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [dcc-mcp](https://github.com/dcc-mcp)
- **Source:** [dcc-mcp/dcc-mcp-renderdoc](https://github.com/dcc-mcp/dcc-mcp-renderdoc)
- **License:** MIT
- **Homepage:** https://pypi.org/project/dcc-mcp-renderdoc/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-dcc-mcp-dcc-mcp-renderdoc-renderdoc-analysis
- Seller: https://agentstack.voostack.com/s/dcc-mcp
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.