What PDF capabilities does parseflow-mcp-server support?

The server extracts text, metadata, images, and table of contents from PDFs. It also supports full-text search across PDF documents to locate specific terms and their page positions.

How do I install and run parseflow-mcp-server?

Install via npm with `npx parseflow-mcp-server@1.0.2`. The server runs over stdio transport, so it integrates directly with MCP clients that support standard input/output communication.

Can I search within PDFs using this server?

Yes, the server includes search functionality that lets you find text within PDFs and returns matching page numbers and positions, useful for building document search features.

What file formats does parseflow support?

The server is specifically designed for PDF parsing. Check the documentation or GitHub repository for details on supported PDF versions and any format limitations.

How do I extract images from PDFs with this server?

The server has built-in image extraction capabilities that identify and extract images embedded in PDFs. Refer to the MCP resource/tool definitions for the exact image output format and metadata available.

MCP ServerSTDIOOfficialv1.0.2

Libres Coder Parseflow MCP Server

Extract text, metadata, images, and table of contents from PDF files via MCP. For developers building document processing pipelines, search tools, or content extraction workflows.

io.github.Libres-coder/parseflow

Try MCP with AI models View source

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the Libres Coder Parseflow MCP server does

How models use it and what it is built for.

Extract text, metadata, images, and table of contents from PDF files via MCP. For developers building document processing pipelines, search tools, or content extraction workflows.

Connect to Libres Coder Parseflow

Local install — runs as a subprocess.

npx parseflow-mcp-server@1.0.2

Resources

Where to find authoritative docs and source for Libres Coder Parseflow.

Source repository

Example prompts for Libres Coder Parseflow

Paste any of these into Agent Studio after connecting Libres Coder Parseflow.

Extract all text from this PDF and return it as structured markdown
Search for occurrences of 'invoice' in the PDF and return page numbers
Get the table of contents structure from this PDF document
Extract all images from the PDF and list their locations by page

Libres Coder Parseflow MCP server — FAQ

Common questions about connecting and running Libres Coder Parseflow.

What PDF capabilities does parseflow-mcp-server support?
The server extracts text, metadata, images, and table of contents from PDFs. It also supports full-text search across PDF documents to locate specific terms and their page positions.
How do I install and run parseflow-mcp-server?
Install via npm with `npx parseflow-mcp-server@1.0.2`. The server runs over stdio transport, so it integrates directly with MCP clients that support standard input/output communication.
Can I search within PDFs using this server?
Yes, the server includes search functionality that lets you find text within PDFs and returns matching page numbers and positions, useful for building document search features.
What file formats does parseflow support?
The server is specifically designed for PDF parsing. Check the documentation or GitHub repository for details on supported PDF versions and any format limitations.
How do I extract images from PDFs with this server?
The server has built-in image extraction capabilities that identify and extract images embedded in PDFs. Refer to the MCP resource/tool definitions for the exact image output format and metadata available.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio