MCPgee
MCPgee
MCPgeeMCPgee

RenderDoc

v1.0.0•Developer Tools•stable

Enables AI assistants to analyze RenderDoc GPU frame captures for graphics debugging and performance analysis through a headless Python API. It provides a comprehensive suite of tools for inspecting pipeline states, shader bindings, and exporting fra

claudecodexgraphics-debuggingmcpopengl
Share:
199
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is RenderDoc?

RenderDoc is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to analyze renderdoc gpu frame captures for graphics debugging and performance analysis through a headless python api. it provides a comprehensive suite of tools for inspecting p...

Enables AI assistants to analyze RenderDoc GPU frame captures for graphics debugging and performance analysis through a headless Python API. It provides a comprehensive suite of tools for inspecting pipeline states, shader bindings, and exporting fra

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables AI assistants to analyze RenderDoc GPU frame capture

Use Cases

Analyze GPU frame captures for graphics debugging and performance tuning.
Inspect pipeline states, shader bindings, and rendering operations.
Export and process graphics data for AI-assisted debugging.
Linkingooo

Maintainer

LicenseMIT
Languagec++
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx renderdoc

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use RenderDoc

RenderDoc MCP connects AI assistants to the RenderDoc GPU frame capture tool via a headless Python API, exposing 42 tools across eight categories for deep graphics debugging. It enables natural-language inspection of draw calls, pipeline states, shader bindings, textures, buffers, and pixel history in captured frames. Graphics engineers and game developers can use it to automate tedious frame analysis tasks — like overdraw estimation, mobile GPU risk assessment, and shader constant inspection — without manually clicking through the RenderDoc UI.

Prerequisites

  • Python 3.10 or higher installed
  • RenderDoc installed on your system (provides renderdoc.pyd on Windows or renderdoc.so on Linux)
  • A valid RenderDoc .rdc frame capture file to analyze
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Clone the repository

Clone the renderdoc-mcp repository from GitHub to your local machine.

git clone https://github.com/Linkingooo/renderdoc-mcp.git
cd renderdoc-mcp
2

Install the package

Install renderdoc-mcp in editable mode using pip so the module is available on your Python path.

pip install -e .
3

Locate your RenderDoc installation path

Find the directory where RenderDoc is installed. On Windows this is typically C:\Program Files\RenderDoc; on Linux it is usually /usr/lib/renderdoc or wherever the shared library lives. This path must contain the renderdoc.pyd or renderdoc.so module.

4

Set the RENDERDOC_MODULE_PATH environment variable

The server requires the RENDERDOC_MODULE_PATH environment variable pointing to your RenderDoc installation directory. Set this in your MCP client config so the server can load the RenderDoc Python module on startup.

5

Add to your MCP client configuration

Register the server in claude_desktop_config.json (Claude Desktop) or .claude/settings.json (Claude Code). Use the python -m renderdoc_mcp invocation and pass the env var.

{
  "mcpServers": {
    "renderdoc": {
      "command": "python",
      "args": ["-m", "renderdoc_mcp"],
      "env": {
        "RENDERDOC_MODULE_PATH": "C:\\Program Files\\RenderDoc"
      }
    }
  }
}
6

Restart your MCP client and verify

Restart Claude Desktop (or reload your MCP client). Open a conversation and ask it to list available RenderDoc tools to confirm the server is connected.

RenderDoc Examples

Client configuration

Claude Desktop config using python -m renderdoc_mcp with the required RENDERDOC_MODULE_PATH env var pointing to your RenderDoc installation.

{
  "mcpServers": {
    "renderdoc": {
      "command": "python",
      "args": ["-m", "renderdoc_mcp"],
      "env": {
        "RENDERDOC_MODULE_PATH": "C:\\Program Files\\RenderDoc"
      }
    }
  }
}

Prompts to try

Example natural-language prompts once connected to a frame capture.

- "Open frame.rdc and give me an overview of what's happening in this frame"
- "List all draw calls and find any that have depth test disabled"
- "Disassemble the vertex shader used in draw call 42"
- "Export the render target texture from the last draw call as PNG"
- "Estimate overdraw for this frame and flag any hotspot events"
- "Check for mobile GPU risks in this capture"

Troubleshooting RenderDoc

Server fails to start with 'Cannot find renderdoc module'

Verify that RENDERDOC_MODULE_PATH points to the directory containing renderdoc.pyd (Windows) or renderdoc.so (Linux), not a subdirectory or the executable itself. On Windows the default is C:\Program Files\RenderDoc.

open_capture returns an error when loading a .rdc file

Ensure the .rdc file path uses the correct separator for your OS and that the file was captured with the same major version of RenderDoc that is installed. RenderDoc captures are not always forward/backward compatible across major versions.

Python import error for renderdoc_mcp after pip install

Make sure you ran pip install -e . inside the cloned repository directory, and that the python command in your MCP config points to the same Python environment where you ran pip. Use python --version to confirm.

Frequently Asked Questions about RenderDoc

What is RenderDoc?

RenderDoc is a Model Context Protocol (MCP) server that enables ai assistants to analyze renderdoc gpu frame captures for graphics debugging and performance analysis through a headless python api. it provides a comprehensive suite of tools for inspecting pipeline states, shader bindings, and exporting fra It connects AI assistants to external tools and data sources through a standardized interface.

How do I install RenderDoc?

Follow the installation instructions on the RenderDoc GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with RenderDoc?

RenderDoc works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is RenderDoc free to use?

Yes, RenderDoc is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

RenderDoc Alternatives — Similar Developer Tools Servers

Looking for alternatives to RenderDoc? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "renderdoc": { "command": "npx", "args": ["-y", "renderdoc"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use RenderDoc?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides