ClipGrab MCP server
✓ VerifiedSaves images from the system clipboard to PNG or JPG files so AI agents can access them.
Also known as ulebule/ClipGrab, clipgrab-mcp
- Stars
- 0
- Tools
- 2
- Downloads, 30 days
- 74
- Latest version
- 0.1.0
- Last commit
- Jun 21, 2026
- License
- MIT
What is ClipGrab MCP?
ClipGrab saves images from the system clipboard to PNG or JPG files so AI agents can access them. It exposes 2 tools, such as save_clipboard_image, clipboard_has_image.
Summary generated from the project's README
About ClipGrab MCP server
Converting screenshots or copied images into files for AI agents to process is the primary function of ClipGrab. Because many AI models can read image files but lack direct access to the system clipboard, this server acts as a bridge by saving clipboard contents to the local disk. It works on Windows, macOS, and Linux, though Linux users require wl-clipboard or xclip for clipboard access.
Developers can use this tool via any MCP client by pointing to the PyPI package using uvx or by installing it through pip. It provides two specific tools: clipboard_has_image to check for content and save_clipboard_image to write the data. When saving, you can specify a directory, a custom filename, and choose between PNG or JPG formats. By default, files are stored in the current working directory with a timestamped name.
Users can also integrate this through a dedicated VS Code extension that manages the Python virtual environment and dependencies automatically. This setup allows agents in chat mode to immediately access visual data that was previously trapped in the system clipboard.
What you can do with it
- 1Convert screenshots for AI analysisAsk an AI agent to take an image from your clipboard and save it as a file so it can see it.
- 2Organize captured imagesInstruct an agent to save a copied image into a specific folder with a custom filename and JPG format.
Written from the project's README. Every use case is checked against a quote from it.
How to install ClipGrab MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ClipGrab MCP in Claude Code
$ claude mcp add clipgrab -- uvx clipgrab-mcpInstall ClipGrab MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"clipgrab": {
"command": "uvx",
"args": [
"clipgrab-mcp"
]
}
}
}Install ClipGrab MCP in VS Code
.vscode/mcp.json
{
"servers": {
"clipgrab": {
"type": "stdio",
"command": "uvx",
"args": [
"clipgrab-mcp"
]
}
}
}Install ClipGrab MCP in VS Code CLI
$ code --add-mcp '{"name":"clipgrab","type":"stdio","command":"uvx","args":["clipgrab-mcp"]}'Install ClipGrab MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"clipgrab": {
"command": "uvx",
"args": [
"clipgrab-mcp"
]
}
}
}Install ClipGrab MCP in Codex
$ codex mcp add clipgrab -- uvx clipgrab-mcpInstall ClipGrab MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.clipgrab] command = "uvx" args = ["clipgrab-mcp"]
Install ClipGrab MCP in Gemini CLI
$ gemini mcp add -s user clipgrab uvx -- clipgrab-mcpInstall ClipGrab MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"clipgrab": {
"command": "uvx",
"args": [
"clipgrab-mcp"
]
}
}
}ClipGrab MCP tools 2
Detected from the READMEsave_clipboard_imageclipboard_has_image
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableulebule/clipgrab is public and reachablegithub.com/ulebule/clipgrab ↗Pass
- Package names this repository as its sourceclipgrab-mcp names ulebule/clipgrab as sourcepypi.org/project/clipgrab-mcp/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-06-21github.com/ulebule/clipgrab ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from clipgrab-mcpPass
- No critical advisory in the package or its dependencies38 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model2 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubClipGrab
mcp-name: io.github.ulebule/clipgrab
An MCP server that saves the image currently on the system clipboard to a file (PNG or JPG).
Why
Many AI agents can read image files but cannot access the system clipboard. ClipGrab bridges that gap: copy an image (e.g. a screenshot), call the tool, and get back a path to a saved image on disk that the agent can open.
By default the image is saved to the current working directory — the folder the agent runs from.
Requirements
- Python 3.10+
- Python packages (see
requirements.txt):Pillow,mcp[cli] - Linux only:
wl-clipboard(wl-paste) orxclipfor the clipboard fallback.
Install from PyPI
Run directly with uv (no install step):
uvx clipgrab-mcp
Or install with pip:
pip install clipgrab-mcp
clipgrab-mcp
Setup from source
python3 -m venv .venv
./.venv/bin/pip install -r requirements.txt
Tools
save_clipboard_image(directory?, filename?, image_format?)→ saves the clipboard image and returns the absolute path.directory— defaults to the current working directory (created if missing). Can also be set via theCLIPGRAB_DEFAULT_DIRenvironment variable.filename— defaults to a timestamped name (clipboard-YYYYMMDD-HHMMSS).image_format—"png"(default) or"jpg".
clipboard_has_image()→ returnstrue/false.
Run manually (stdio)
./.venv/bin/python mcp_server.py
Install as a VS Code extension
ClipGrab ships as a VS Code extension that registers the MCP server
automatically — it then appears under Extensions view → MCP Servers and
starts on demand. On first use the extension creates its own Python virtual
environment and installs the dependencies, so you only need Python 3.10+ on your
PATH (configurable via the clipgrab.pythonPath setting).
Develop / try it:
- Open this folder in VS Code and press
F5to launch the Extension Development Host. - In that window, open Chat (agent mode); the
ClipGrabMCP server and itssave_clipboard_imagetool are available.
Package a .vsix for sharing:
npm install -g @vscode/vsce
vsce package
VS Code configuration (without the extension)
A ready-to-use config lives in .vscode/mcp.json:
{
"servers": {
"clipgrab": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/mcp_server.py"],
"cwd": "${workspaceFolder}"
}
}
}
Then open .vscode/mcp.json and start the clipgrab server (or use the Command
Palette → "MCP: List Servers").
Use with an MCP client
Point any MCP client at the published PyPI package over stdio:
{
"servers": {
"clipgrab": {
"command": "uvx",
"args": ["clipgrab-mcp"]
}
}
}
ClipGrab is described for registries by server.json and is
published to the official MCP registry
under the name io.github.ulebule/clipgrab.
Technical notes
- Cross-platform image grab: Pillow
ImageGrab.grabclipboard()(Windows / macOS, and Linux with a recent Pillow). On Linux it falls back towl-paste/xclip.
License
MIT
ClipGrab MCP questions
How do I add ClipGrab MCP to Claude Code?
Run claude mcp add clipgrab -- uvx clipgrab-mcp in your terminal. Add --scope user to make it available in every project.
How do I add ClipGrab MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does ClipGrab MCP provide?
It exposes 2 tools, including save_clipboard_image, clipboard_has_image.
Where are the images saved by default?
Images are saved to the current working directory, which is the folder the agent is running from.
What operating systems are supported?
The server works on Windows, macOS, and Linux. On Linux, it requires wl-clipboard or xclip for clipboard fallback.