GroupDocs.Redaction MCP Server
OfficialEnables GitHub Copilot (in VS Code and other editors) to apply redaction tools on documents, including text redaction, metadata erasure, annotation removal, and image area redaction.
Integrates with JetBrains Rider, allowing AI agents to redact documents directly from the IDE using tools like text redaction, metadata cleanup, annotation deletion, and image area covering.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GroupDocs.Redaction MCP ServerRedact all email addresses in contract.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GroupDocs.Redaction MCP Server
MCP server that exposes GroupDocs.Redaction as AI-callable tools for Claude, Cursor, GitHub Copilot, and other MCP agents.
Installation
One-click installs pre-fill every supported setting: edit the placeholder documents folder after install (output defaults to the same folder); an empty GROUPDOCS_LICENSE_PATH runs in evaluation mode - point it at your license to lift limits.
More clients - ready-made configs for Claude Code, Codex CLI, Visual Studio 2022, Cursor, Windsurf, Cline, and JetBrains Rider live in
install/generated/.
Requires .NET 10 SDK.
Run directly with dnx (recommended — no install step):
dnx GroupDocs.Redaction.Mcp --yesPulls the latest stable release on every invocation. To pin to a specific
version (recommended for shared configs and CI), append @<version>:
dnx GroupDocs.Redaction.Mcp@26.9.0 --yesOr install as a global dotnet tool:
dotnet tool install -g GroupDocs.Redaction.Mcp
groupdocs-redaction-mcpOr run via Docker:
docker run --rm -i \
-v $(pwd)/documents:/data \
ghcr.io/groupdocs-redaction/redaction-net-mcp:latestRelated MCP server: GroupDocs.Annotation MCP Server
Native prerequisites
The underlying GroupDocs engine uses System.Drawing (GDI+) for image-area
redaction (drawing solid-color boxes over page regions). When you run the server
natively (via dnx or the global dotnet tool) on Linux or macOS, install
the native libgdiplus library first:
Platform | Setup |
Windows | Nothing — GDI+ is built into the OS. |
Linux |
|
macOS |
|
Docker | Nothing — the image already bundles |
Skipping this on Linux/macOS surfaces as DllNotFoundException: libgdiplus in
the tool response. The simplest zero-setup option on Linux/macOS is the
Docker image.
Available MCP Tools
Tool | Description |
| Redact text matching a regex pattern in a document; saves result as |
| Erase document metadata fields (author, title, company, dates, and other properties) |
| Replace or delete annotations and comments in a document |
| Cover a rectangular page region with a solid-color box (pixel coordinates) |
| Return file type, page count, size, and per-page dimensions as JSON (no modification) |
Example prompts
"Redact all occurrences of 'John Smith' in contract.docx"
"Remove all metadata from report.pdf before sharing it externally"
"Delete all comments and annotations from review.docx"
"Cover the signature area on page 1 of agreement.pdf with a black box from (100,200) to (400,300)"
"How many pages does confidential.pdf have?"
Licensing
The MCP server itself is MIT; the underlying GroupDocs.Redaction engine requires a license for production use. Without one the server runs in evaluation mode:
Saved output is watermarked.
A single server process can open at most 1 document in evaluation mode - each redaction needs a fresh server process.
There are two ways to license the server.
License file — point GROUPDOCS_LICENSE_PATH at your GroupDocs.Total.lic. Works offline.
Metered (pay-per-use) — set both GROUPDOCS_METERED_PUBLIC_KEY and
GROUPDOCS_METERED_PRIVATE_KEY. You are billed for what you actually process, which suits AI
agents well because their usage is bursty and hard to predict up front. If both a metered key pair
and a license file are configured, metered wins and the file is ignored.
Metered mode needs outbound connectivity. Usage is reported to GroupDocs servers, so air-gapped or firewalled deployments must allow that egress — or use a license file instead.
Call the get_license_status tool at any time to see which mode is active, and — under
metered — the consumed quantity and remaining credit.
Keeping the private key out of your config
The metered private key is a secret. MCP client configs are plain files on disk, and a
project-scoped .mcp.json is committed by convention, so prefer, in order:
Set the variables in your OS environment and leave them out of the config entirely. An stdio MCP server inherits its client's environment, so this works in every client. On macOS note that an app launched from Finder does not inherit shell exports — use
launchctl setenv, or launch the client from a terminal.Reference them indirectly if your client supports it (Claude Code expands
${VAR}; VS Code uses${env:VAR}and${input:...}).A literal value in a user-scoped config (for example
~/.claude.json) is acceptable for a single developer.Never commit a literal key in a project-scoped
.mcp.json.
For Docker, forward the values without writing them into any file:
docker run --rm -i \
-e GROUPDOCS_METERED_PUBLIC_KEY -e GROUPDOCS_METERED_PRIVATE_KEY \
-v /path/to/documents:/data \
ghcr.io/groupdocs-redaction/redaction-net-mcp:latestTo lift the limits with a license file:
Configuration
Variable | Description | Default |
| Base folder for input and output files | current directory |
| (Optional) separate folder for output files |
|
| Path to GroupDocs license file | (evaluation mode) |
| Metered public key. Requires the private key too; takes precedence over the license file | (unset) |
| Metered private key. Secret - see Licensing | (unset) |
Usage with Claude Desktop
{
"mcpServers": {
"groupdocs-redaction": {
"type": "stdio",
"command": "dnx",
"args": ["GroupDocs.Redaction.Mcp", "--yes"],
"env": {
"GROUPDOCS_MCP_STORAGE_PATH": "/path/to/documents"
}
}
}
}To pin to a specific version, replace
"GroupDocs.Redaction.Mcp"with"GroupDocs.Redaction.Mcp@26.9.0"inargs. Pinning is recommended for shared / committed configs to avoid surprise upgrades.
Usage with VS Code / GitHub Copilot
NuGet.org generates a ready-to-use mcp.json snippet on the package page.
Copy it directly into your .vscode/mcp.json.
Alternatively, add manually to .vscode/mcp.json:
{
"inputs": [
{
"type": "promptString",
"id": "storage_path",
"description": "Base folder for input and output files.",
"password": false
}
],
"servers": {
"groupdocs-redaction": {
"type": "stdio",
"command": "dnx",
"args": ["GroupDocs.Redaction.Mcp", "--yes"],
"env": {
"GROUPDOCS_MCP_STORAGE_PATH": "${input:storage_path}"
}
}
}
}Same pinning rule as above — swap
"GroupDocs.Redaction.Mcp"for"GroupDocs.Redaction.Mcp@26.9.0"to lock to a specific release.
Usage with Docker Compose
cd docker
docker compose upEdit docker/docker-compose.yml to point volumes at your local documents folder.
Documentation & guides
Step-by-step deployment guides and a published-package integration test suite live in the companion repo GroupDocs.Redaction.Mcp.Tests:
Install from NuGet —
dnx, global tool, pinned vs always-latest
That repo also exercises every advertised tool against the published NuGet artifact on Linux, macOS, and Windows in CI — so the snippets above are verified end-to-end on every release.
License
MIT — see LICENSE
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server that extracts clean text, tables, and structured data from documents, images, code, and audio files, supporting 97 formats with OCR, transcription, and code intelligence.MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that exposes GroupDocs.Annotation as AI-callable tools for Claude, Cursor, GitHub Copilot, and other MCP agents.MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that exposes GroupDocs.Parser as AI-callable tools for extracting text, images, metadata, tables, barcodes, and document info from 50+ document and image formats.MIT
- AlicenseNot gradedqualityAmaintenanceUnified MCP server that exposes GroupDocs.Total document-processing tools (annotation, comparison, conversion, merging, metadata, parsing, redaction, signing, watermarking, and more) as AI-callable tools for MCP agents.MIT