Skip to main content
Glama

pdf-chart-parser (Soapbox deployment)

This repository is the Corresponding Source, under the GNU Affero General Public License v3.0 (section 13), of the pdf-chart-parser MCP service Soapbox runs. If you reached that service over a network, this is the source of the version you used.

It is published automatically. Do not send changes here; they would be overwritten.

What is here

  • upstream/ is pdf-chart-parser by its upstream author, https://github.com/haoxinm/pdf-chart-parser, at commit a07f3be1791be5211531cf99745f57580c5c080b, unmodified. It is licensed AGPL-3.0-or-later; see upstream/LICENSE and upstream/README.md. Only the files needed to build and test the program are included.

  • auth_app.py is Soapbox's modification: it requires a bearer token on every MCP request, and advertises this repository in a Link: rel="source" header and at GET /source.

  • strict_tool_arguments.py is Soapbox's modification: applied by auth_app.py, it makes every upstream tool refuse, by name, an argument its signature does not declare, instead of silently dropping it.

  • Dockerfile, requirements.in, requirements.lock, requirements.txt, pytest.ini, .dockerignore and tests/ are the build and tests of the deployed image. The Dockerfile fetches upstream at the same commit as upstream/.

Soapbox's modifications are licensed under the same terms, AGPL-3.0-or-later; see LICENSE.

Related MCP server: flint-slating

Version

SOURCE_REVISION names the Soapbox source revision this tree was built from and the upstream commit. The deployed service's image is built from exactly these files.

Build

docker build -t pdf-chart-parser .
docker run -e MCP_AUTH_TOKEN=<at least 32 characters> -p 8080:8080 pdf-chart-parser

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    A comprehensive tool server for reading, merging, and extracting content from PDF files via local paths or direct URLs. It enables metadata retrieval, regex searching, and page-specific text extraction with built-in caching and workspace-restricted security.
    9
    5,320 PyPI
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    MCP server that reads PDFs and exposes them as structured Markdown, metadata, outlines, images, and tables to LLM consumers via tools like pdf_read_markdown and pdf_info.
    Apache 2.0
  • F
    license
    A
    quality
    B
    maintenance
    Document-engineering MCP tool server providing tools for PDF, Office, Images, and Archives extraction and conversion. It never mutates source files and requires local tesseract for OCR.
    12
    -
  • A
    license
    A
    quality
    A
    maintenance
    Full-stack PDF intelligence MCP server for extracting, manipulating, annotating, converting, validating, and RAG-searching PDFs through a unified tool surface and React workbench.
    16
    1
    MIT