M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
X

Xberg

Official
Polyglot document intelligence engine for extracting text, tables, metadata, and structured data from 101 formats and code from 371 languages.
How to install ↓ Compare GitHub source repository ↗
Category
Filesystem #12 of 24
Stars
★ 9.4k Very popular
Transport
stdio (local process)
Runtime
Prebuilt binary · Docker · Rust
Credentials
No credential needed
License
MIT
Last commit
Tools
9
58FMRS · C

Suitable for users who need to extract information from diverse documents and code, offering rich features and multiple integration options.

Strongest · Maintenance 16/20 Weakest · Reliability 8/20

Reliability
8/20
Security and permissions
12/20
Maintenance
16/20
Documentation
12/20
Setup experience
10/20
Why each score
Reliability 8/20
The manifest provides a clear OCI container (ghcr.io/xberg-io/xberg-cli:5.0.0-rc.10) with stdio transport arguments, and README lists 9 tools, 3 prompts, and 4 resources, but static analysis found no CI workflows or committed tests as execution evidence. Thus reliability is capped at 12; based on static evidence (clear package definition and declared consistency) a score of 8 is given, deducting for lack of verified tool behavior.
Security and permissions 12/20
No red flags such as malware or credential theft were found, but the tools allow local file extraction, potentially handling sensitive data; no explicit confirmation mechanism for dangerous operations is observed, and least privilege is not clearly demonstrated. Therefore security is scored 12, deducting for insufficient disclosure of data flow and permission scope.
Maintenance 16/20
The repository is active with 8925 stars, 18 open issues, MIT license, and version 5.0.0-rc.10; README shows multiple packages and bindings. Maintenance scores 16, deducting for insufficient evidence of a security response channel and dependency update policy.
Documentation 12/20
README details CLI commands, MCP server usage, configuration examples (Claude Desktop), and links to external docs. However, it lacks per-tool parameter details, troubleshooting guides, and cost information, so documentation scores 12.
Setup experience 10/20
Installation steps are clear: via brew or Docker pull, with config examples directly provided. But no CI-verified installation process is given, and the MCP server requires a local CLI install; platform compatibility is not fully verified, so setup scores 10.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesUses the network

Best for

  • Developers and data engineers who need to process diverse document formats and extract structured data.
  • AI agents that need document processing capabilities within an MCP environment.
  • RAG pipelines that require extracting semantic information from codebases.

Not for

  • General MCP scenarios that do not require document extraction or OCR.
  • Users needing real-time collaborative document editing, as Xberg focuses on extraction.
  • Simple text conversion with low performance requirements.

Required permissions

  • Read access to the local file system to access documents for extraction.
  • May access network to fetch URLs or call remote OCR/LLM APIs if configured.
  • Write access to cache directories to store extracted results.

Risks and side effects

  • Potential security risk when processing malicious files; it is recommended to limit file sources.
  • OCR or LLM calls may require additional API keys or network connectivity.
  • Large file processing may consume significant memory and CPU resources.

Setup

Before you start

Runtime：Prebuilt binary · Docker · Rust

Install the CLI via Homebrew: brew install xberg-io/tap/xberg, then configure your client. For example, add to your Claude Desktop or Cursor config: { "mcpServers": { "xberg": { "command": "xberg", "args": ["mcp"] } } }.

claude_desktop_config.json 
{
  "mcpServers": {
    "xberg": {
      "command": "xberg",
      "args": [
        "mcp"
      ]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "xberg": {
      "command": "xberg",
      "args": [
        "mcp"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add xberg -- xberg mcp

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

The client's tool list should show the 9 tools including extract, extract_batch, detect_mime_type, cache_stats, and list_formats; calling get_version should report version 5.0.0-rc.10.

Troubleshooting

  1. Ensure the xberg CLI is correctly installed and in PATH.
  2. Verify the command path in your configuration file.
  3. Run `xberg doctor` to check backend dependencies (like Tesseract) are available.
  4. Check logs for detailed error messages.

Things to try

Once connected, you can ask your AI assistant things like:

  • Extract the text from /tmp/report.pdf and return it as Markdown
  • Detect the MIME type of file.dat
  • Batch extract text from all files in /docs
  • List all formats supported by xberg

Tools 9

extract read-only
Extract text, tables, metadata, and images from a single document.
extract_batch read-only
Extract content from multiple documents in parallel.
detect_mime_type read-only
Detect MIME type of a file.
cache_stats read-only
Show statistics for the extraction cache.
list_formats read-only
List all supported file formats and MIME types.
cache_clear destructive
Clear the extraction cache.
get_version read-only
Get version information for Xberg.
cache_manifest read-only
View the cache manifest.
Show 1 more tools
cache_warm writes
Warm the cache to speed up subsequent extractions.

Use cases

Extract text and tables from PDFs, Office documents, images, etc., for RAG or data processing.
Perform OCR on scanned documents with backends like Tesseract and PaddleOCR.
Extract functions, classes, imports, and other structures from source code for code analysis.
Use local or remote LLMs for schema-driven structured data extraction and document understanding.

Supported clients

Claude Desktop
Cursor

Listed from the project's documentation, not tested by this site.

Overview

Xberg is a Rust-core document intelligence framework supporting extraction of text, tables, metadata, and images from 101 formats (115 file extensions) plus code intelligence for 371 programming languages. It offers 15 language bindings (Rust, Python, Node.js, Go, Java, C#, Ruby, PHP, Elixir, Dart, Swift, Zig, WASM, Kotlin, C FFI) with CLI, REST API, and MCP server interfaces. The MCP server provides 9 tools (extract, extract_batch, detect_mime_type, cache_stats, list_formats, cache_clear, get_version, cache_manifest, cache_warm), 3 prompts (extract_document, extract_with_ocr, semantic_search), and 4 resources (formats, models, OCR languages, embedding presets).

Similar servers

Compare with other MCP servers

Source revision b4bdf0b93461 Data synced 2026-10-12 Read the FMRS scoring method