GroupDocs.Metadata MCP server
Commit Sep 5, 2026Enables AI agents to read, search, write, and remove metadata from various document types.
Also known as groupdocs-metadata/GroupDocs.Metadata.Mcp
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 26.9.0
- Last commit
- Sep 5, 2026
- License
- MIT
What is GroupDocs.Metadata MCP?
GroupDocs.Metadata enables AI agents to read, search, write, and remove metadata from various document types.
Summary generated from the project's README
About GroupDocs.Metadata MCP server
Managing document properties through AI agents is possible with this server, which connects the GroupDocs.Metadata engine to clients like Claude, Cursor, and GitHub Copilot. It allows developers to automate the reading, searching, writing, and removing of metadata across various file types. Users can interact with files using specific tools such as ReadMetadata to retrieve JSON properties, SearchMetadata to filter for specific details like GPS data, and WriteMetadata to update fields like Author or Title.
This server can be deployed locally using the .NET 10 SDK via dnx or as a global dotnet tool, or it can be run in a Docker container for a zero-setup experience on Linux and macOS. While the MCP server itself is MIT licensed, the underlying engine requires a license for production use. In evaluation mode, the server is limited to opening 15 documents and cannot save metadata changes. Users can provide a license file via GROUPDOCS_LICENSE_PATH or use a metered pay-per-use model with public and private keys.
What you can do with it
- 1Extracting document propertiesAn AI agent can retrieve all metadata properties including author, title, and creation date in a structured JSON format.
- 2Searching for specific metadataYou can ask an AI to find specific information within a document, such as checking if a file contains GPS coordinates.
- 3Cleaning sensitive informationDevelopers can instruct an agent to strip all metadata or specific categories like personal details and comments from a file.
- 4Performing structural file checksAn agent can quickly verify a file's type, size, and encryption status without reading every metadata property.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
GROUPDOCS_LICENSE_PATHGROUPDOCS_MCP_OUTPUT_PATHGROUPDOCS_MCP_STORAGE_PATHGROUPDOCS_METERED_PRIVATE_KEYGROUPDOCS_METERED_PUBLIC_KEY
| Name | Description | |
|---|---|---|
| GROUPDOCS_LICENSE_PATH | — | |
| GROUPDOCS_MCP_OUTPUT_PATH | — | |
| GROUPDOCS_MCP_STORAGE_PATH | — | |
| GROUPDOCS_METERED_PRIVATE_KEY | — | |
| GROUPDOCS_METERED_PUBLIC_KEY | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablegroupdocs-metadata/groupdocs.metadata.mcp is public and reachablegithub.com/groupdocs-metadata/groupdocs.metadata.mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-05github.com/groupdocs-metadata/groupdocs.metadata.mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubGroupDocs.Metadata MCP Server
MCP server that exposes GroupDocs.Metadata 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.Metadata.Mcp --yes
Pulls the latest stable release on every invocation. To pin to a specific
version (recommended for shared configs and CI), append @<version>:
dnx GroupDocs.Metadata.Mcp@26.9.0 --yes
Or install as a global dotnet tool:
dotnet tool install -g GroupDocs.Metadata.Mcp
groupdocs-metadata-mcp
Or run via Docker:
docker run --rm -i \
-v $(pwd)/documents:/data \
ghcr.io/groupdocs-metadata/metadata-net-mcp:latest
Native prerequisites
The underlying GroupDocs engine uses System.Drawing (GDI+) for some
operations. 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 | sudo apt-get install -y libgdiplus libfontconfig1 |
| macOS | brew install mono-libgdiplus |
| Docker | Nothing — the image already bundles libgdiplus. |
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 |
|---|---|
ReadMetadata |
Reads all metadata properties (author, title, creation date, custom properties) and returns them as JSON |
SearchMetadata |
Searches within one document and returns only matching properties (filter by category, name, or value) — e.g. "show me the author", "does this have GPS?" |
WriteMetadata |
Sets, changes, or adds a property (Author, Title, Subject, Keywords, Comments, Copyright, Company, Manager) and saves the updated file |
RemoveMetadata |
Removes metadata and saves a cleaned file. Strips everything by default, or only specific categories (gps, author, comments, company, dates, software, copyright, keywords, personal) |
GetDocumentInfo |
Returns the file type, MIME type, page count, byte size, and encryption status as JSON — a lightweight structural check that does not enumerate metadata properties |
Licensing
The MCP server itself is MIT; the underlying GroupDocs.Metadata engine requires a license for production use. Without one the server runs in evaluation mode:
- A single server process can open at most 15 documents; further calls fail with an evaluation-cap error until the server restarts.
- Saving metadata changes (write / remove) is blocked without a license.
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${input:...}). - A literal value in a user-scoped config (for example
~/.claude.json) is acceptable for a single developer. - Never commit a literal key in a project-scoped
.mcp.json.
For Docker, forward the values without writing them into any file:
docker run --rm -i \
-e GROUPDOCS_METERED_PUBLIC_KEY -e GROUPDOCS_METERED_PRIVATE_KEY \
-v /path/to/documents:/data \
ghcr.io/groupdocs-metadata/metadata-net-mcp:latest
To lift the limits with a license file:
Configuration
| Variable | Description | Default |
|---|---|---|
GROUPDOCS_MCP_STORAGE_PATH |
Base folder for input and output files | current directory |
GROUPDOCS_MCP_OUTPUT_PATH |
(Optional) separate folder for output files | GROUPDOCS_MCP_STORAGE_PATH |
GROUPDOCS_LICENSE_PATH |
Path to GroupDocs license file | (evaluation mode) |
GROUPDOCS_METERED_PUBLIC_KEY |
Metered public key. Requires the private key too; takes precedence over the license file | (unset) |
GROUPDOCS_METERED_PRIVATE_KEY |
Metered private key. Secret - see Licensing | (unset) |
Usage with Claude Desktop
{
"mcpServers": {
"groupdocs-metadata": {
"type": "stdio",
"command": "dnx",
"args": ["GroupDocs.Metadata.Mcp", "--yes"],
"env": {
"GROUPDOCS_MCP_STORAGE_PATH": "/path/to/documents"
}
}
}
}
To pin to a specific version, replace
"GroupDocs.Metadata.Mcp"with"GroupDocs.Metadata.Mcp@26.9.0"inargs. Pinning is recommended for shared / committed configs to avoid surprise upgrades.
Usage with VS Code / GitHub Copilot
NuGet.org generates a ready-to-use mcp.json snippet on the package page.
Copy it directly into your .vscode/mcp.json.
Alternatively, add manually to .vscode/mcp.json:
{
"inputs": [
{
"type": "promptString",
"id": "storage_path",
"description": "Base folder for input and output files.",
"password": false
}
],
"servers": {
"groupdocs-metadata": {
"type": "stdio",
"command": "dnx",
"args": ["GroupDocs.Metadata.Mcp", "--yes"],
"env": {
"GROUPDOCS_MCP_STORAGE_PATH": "${input:storage_path}"
}
}
}
}
Same pinning rule as above — swap
"GroupDocs.Metadata.Mcp"for"GroupDocs.Metadata.Mcp@26.9.0"to lock to a specific release.
Usage with Docker Compose
cd docker
docker compose up
Edit 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.Metadata.Mcp.Tests:
- Install from NuGet —
dnx, global tool, pinned vs always-latest - Run via Docker
- Verify on the MCP registry
- Use with Claude Desktop
- Use with VS Code / GitHub Copilot
- Use with Cursor
- Run the integration tests
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
GroupDocs.Metadata MCP questions
Does the server require a license for production use?
Yes, while the MCP server is MIT licensed, the underlying GroupDocs.Metadata engine requires a license for production. Without one, it runs in evaluation mode with a 15-document limit and no write capabilities.
How do I run this on Linux or macOS?
You can run it natively using the .NET SDK, but you must install the native libgdiplus library first. Alternatively, using the Docker image is the simplest zero-setup option.