How to generate a PDF or Word report from JSON data in a repository with Claude Code Leave feedback

Your repository already holds the data — a release manifest, a changelog, a contributors list. Run the GroupDocs.Assembly MCP server locally with the repository as its storage folder, and Claude Code (or any coding agent) turns that JSON into a formatted PDF or Word document from a template you version next to the code:

claude mcp add groupdocs-assembly \
  -e GROUPDOCS_MCP_STORAGE_PATH=$(pwd) -- dnx GroupDocs.Assembly.Mcp --yes

Generate the release notes PDF for 4.2.0 from data/release-4.2.0.json, and a contribution certificate for everyone in data/contributors-2026.json.

Note

The commands and config snippets on this page are for the .NET build of the server — the only platform available today. Installation and client setup: MCP server for .NET. Other platforms will expose the same tools with their own launch command; everything else on this page applies unchanged.

• The .NET 10 SDK; the server registered for the project — register in AI clients.
• Templates in the repository (templates/release-notes.docx, templates/certificate.docx) and JSON data (data/*.json).

repo/
  data/release-4.2.0.json        --+
  data/contributors-2026.json    --|--  the data is already in the repo
  templates/release-notes.docx   --|--  the layout is versioned with it
  templates/certificate.docx     --+
        |
  assemble_document    --> release-notes-4.2.0.pdf
  assemble_per_record  --> pnair.pdf  tvarga.pdf  mrossi.pdf
        (recordsPath "contributors", fileNameField "Handle")

Captured from server 26.11.0, with the repository as the storage folder (the evaluation note that opens each response is trimmed):

-> get_template_fields {"template":{"filePath":
     "repo/templates/release-notes.docx"}}
<- { "dataSourceNames": [ "release", "changes" ],
     "fields": [ "release.Product", "release.Version", "release.Date",
                 "changes[].Type", "changes[].Title", "changes[].PullRequest",
                 "changes[].Author" ] }

-> assemble_document {"template":{"filePath":
     "repo/templates/release-notes.docx"},
     "data":{"filePath":"repo/data/release-4.2.0.json"},"format":"pdf",
     "outputName":"release-notes-4.2.0.pdf"}
<- Assembled 'release-notes.docx' with 'release-4.2.0.json' (JSON object)
   as PDF
   Saved to: …/release-notes-4.2.0.pdf

-> assemble_per_record {"template":{"filePath":
     "repo/templates/certificate.docx"},
     "data":{"filePath":"repo/data/contributors-2026.json"},
     "recordsPath":"contributors","fileNameField":"Handle","format":"pdf"}
<- Assembled 3 of 3 document(s) from 'certificate.docx' with
   'contributors-2026.json', one per record (each record as 'contributor'),
   as PDF.
   Saved to:
   …/pnair.pdf
   …/tvarga.pdf
   …/mrossi.pdf

The release-notes template repeats a table row per change and ends with <<[changes.Count()]>> changes from <<[changes.Select(c => c.Author).Distinct().Count()]>> contributors. — the counting is done by the template, not by the model.

release-notes-4.2.0.pdf and one certificate per contributor, generated in the output folder. The JSON stays the source of truth; the next release is the same prompt with a new file.

Generated files are written to the storage folder (or GROUPDOCS_MCP_OUTPUT_PATH). Point the output path at a build folder and ignore it:

# .gitignore
out/

with -e GROUPDOCS_MCP_OUTPUT_PATH=$(pwd)/out on the claude mcp add line.

Can this run in CI? The server is an MCP server for agents; in CI, call the GroupDocs.Assembly library or run the agent. Locally, the agent is the build step.

Are templates code? Treat them so: image and document tags load the paths and URLs their expressions return. Review template changes like code changes.

Can it read YAML or TOML? No — JSON, XML, CSV and document tables. Ask the agent to convert first.

Agents follow project instructions about when to use a tool. Paste this into the instruction file your agent reads (CLAUDE.md, AGENTS.md, .github/copilot-instructions.md, .cursorrules):

Release documents are generated, not written: use the groupdocs-assembly MCP
server with templates/*.docx and data/*.json. Output to out/ (gitignored).
Never edit the generated files; change the template or the data instead.

• Evaluation mode: every generated document starts with an Evaluation Only line, workbooks gain a worksheet, and e-mail templates lose their HTML body. Licensing.
• <<[name]>>, not {{name}}: other engines’ placeholders stay in the output as text.
• Templates are trusted input: image and document tags load the paths and URLs their expressions return.
• Dates: write them as "2026-11-12T00:00:00" and format them in the template; a date-only string can shift by a day on machines east of UTC.

• Generate documents with AI agents
• One document per record (mail merge)
• Reports with tables and charts
• Inspect and fix a template
• From notes or email to a document
• On-premise deployment
• Tools reference · Licensing · Troubleshooting & FAQ
• Questions: Assembly forum

• Your repo already has the data; let the agent make the PDF — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.