convez.ai
MCP ServerIntegração & APIsIntermediário
ParkviewLab

Flint-Slating MCP Server

ParkviewLab/flint-slating

Converte PDFs em Markdown estruturado com metadados e assets extraídos

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server para leitura de PDFs com conversão estruturada para Markdown, extração de metadados, tabelas e imagens. Projetado para integração com sistemas de wiki e pipelines de processamento documental via Claude ou outras aplicações LLM.

Instalação

$npx convez-ai ParkviewLab/flint-slating

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
62%
Último commit
há 1 mês
Versão
v0.1.9
Issues abertas
0
Contribuidores
2

Casos de uso

  • Extração automática de conteúdo de PDFs para bases de conhecimento
  • Pipeline de processamento documental com agentes Claude
  • Integração com sistemas de wiki e anotações frontmattered
  • Análise e estruturação de documentos técnicos e científicos

Veredito

MCP server robusto e bem arquitetado para processamento de PDFs sem dependências copyleft. Suporta transports HTTP e stdio, com toolset completo para leitura, extração de metadados, tabulação e imagens — excelente para pipelines de knowledge management integrados com LLMs.

README

A tradução para o português deste README ainda está na fila.

flint-slating

MCP server that reads PDFs and exposes them to LLM consumers as structured Markdown, plus the usual ancillaries: metadata, outline, images, tables.

Designed to pair with a separate "wiki" MCP server that handles the writing side — an agent calls flint-slating to read PDFs and another MCP to persist notes about them into a frontmattered-markdown knowledge base.

What it does

Built on a permissive-license PDF stack:

LibraryLicenseRole
DoclingMITPDF → Markdown with heading hierarchy, multi-column reading order, and Markdown tables
pypdfBSD-3metadata, TOC, page count, encryption checks, image enumeration
pdfplumberMITper-page table extraction

There is no PyMuPDF, no MuPDF, no AGPL or GPL anywhere in the dependency tree. A CI license-check job rejects PRs that pull in copyleft transitive deps.

Transports

Two transports off the same MCP server, selected via --transport:

TransportRun viaUse case
Streamable-HTTP (default)uvx flint-slating or --transport httpLong-lived local daemon, container, or shared service.
stdiouvx flint-slating --transport stdioThe standard MCP integration shape — drop into claude_desktop_config.json or any mcp.json.

Run

As an HTTP daemon (default)

uvx flint-slating                    # listens on PORT (default 35833)
curl http://127.0.0.1:35833/health

Or pin it:

uv tool install flint-slating
flint-slating

As a stdio MCP server

uvx flint-slating --transport stdio

Wire into Claude Code's MCP config:

{
  "mcpServers": {
    "flint-slating": {
      "command": "uvx",
      "args": ["flint-slating", "--transport", "stdio"]
    }
  }
}

Docker

docker run --rm \
  -p 35833:35833 \
  -v $(pwd)/pdfs:/pdfs:ro \
  -v flint-slating-data:/data \
  ghcr.io/parkviewlab/flint-slating:latest

Or use docker-compose.yml for a persistent stack.

MCP tools

All PDF tools take a source argument with one of:

  • {"path": "/abs/path/to/file.pdf"} — local file
  • {"url": "https://..."} — streamed to a content-addressed cache
  • {"bytes_b64": "...", "filename": "x.pdf"} — base64 upload (size-capped)
ToolWhat it does
pdf_info{page_count, metadata, is_encrypted, sha256}
pdf_tocflat outline [{level, title, page}]
pdf_read_textplain text by page range (fast — pypdf, no ML)
pdf_read_markdownhigh-quality Markdown via Docling (hybrid sync/async — see below)
pdf_read_chunksper-page Markdown chunks with tables/images/toc_items (hybrid sync/async)
pdf_list_imagesenumerate images: [{page, index, name, width, height, ext}]
pdf_extract_imagebase64 bytes of one image
pdf_find_tablesper-page Markdown tables via pdfplumber
get_job_statuspoll a background job
get_job_resultfetch a finished job's artifact
cancel_jobcancel a running job

Hybrid sync/async

pdf_read_markdown and pdf_read_chunks run inline when page_count <= SYNC_PAGE_THRESHOLD (default 20). For larger PDFs they queue a background job and return a job_id — poll get_job_status until state=="done", then call get_job_result (or, in HTTP mode, fetch output_url directly).

stdio mode transparently waits for the job inline — there's no HTTP server to download from, so the originating tool call blocks until the result is ready and returns it directly.

HTTP endpoints (HTTP mode only)

  • GET /health — {ok, version, uptime_seconds}
  • GET /admin/version — package and dependency versions, Docling model status
  • GET /admin/jobs — recent job list
  • GET /outputs/{job_id}/result.md — finished Markdown
  • GET /outputs/{job_id}/result.json — finished chunked output
  • GET /outputs/{job_id}/log.jsonl — append-only job log
  • POST /sse — MCP Streamable-HTTP transport

Configuration

Env varDefault (daemon)Default (container)Purpose
PORT3583335833HTTP bind port
HOST0.0.0.00.0.0.0HTTP bind address
OUTPUT_ROOT./output/data/outputPer-job output dirs
CACHE_ROOT./cache/data/cacheMaterialized URL / base64 PDFs
OUTPUT_EXPIRY_DAYS77Sweep finished jobs older than N days
MAX_INLINE_PDF_BYTES25 MB25 MBCap on base64 upload size
MAX_URL_PDF_BYTES200 MB200 MBCap on URL download size
SYNC_PAGE_THRESHOLD2020Inline-vs-job cutoff for Markdown conversion
DOCLING_ARTIFACTS_PATH~/.cache/docling/opt/docling-modelsDocling layout-model cache
ENABLE_OCRfalsefalseEnable Docling OCR (Tesseract required)
PUBLIC_BASE_URLhttp://localhost:35833http://localhost:35833Used to build output_url

Resource notes

  • Docling downloads a ~200–500 MB layout model on first use. The container image does not pre-fetch it (pre-fetching dominated multi-arch build time under QEMU); the daemon warms it on startup, and the first user-facing call pays the download. Operators can populate DOCLING_ARTIFACTS_PATH (default /opt/docling-models in the container) via volume mount for a hot start.
  • pypdf, pdfplumber, and the URL / base64 paths are fast and have no ML overhead — use pdf_info, pdf_toc, pdf_read_text, and pdf_find_tables whenever Markdown isn't strictly needed.

Releasing

Tag-driven CI publishes to both PyPI (flint-slating) and GHCR (ghcr.io/parkviewlab/flint-slating):

# Bump version in pyproject.toml first, then:
git tag v0.1.0
git push origin v0.1.0

The release workflow refuses tags that don't match pyproject.toml's version, or that aren't on origin/main.

Commit message convention

After the publish jobs, a changelog job generates the new CHANGELOG.md section — an LLM-written "Highlights" paragraph plus a git-cliff categorized commit list — commits it back to main, and creates the GitHub Release with the same content as its body. Categorization uses Conventional Commits prefixes (see cliff.toml):

PrefixSectionNotes
feat:Featuresuser-visible
fix:Bug fixesuser-visible
perf:Performanceuser-visible
refactor:Refactor
docs:Docs
test:Tests
chore: / ci: / build: / style:(dropped)not surfaced in CHANGELOG

Squash-merge PRs use the PR title as the commit subject — so the PR title is what needs the prefix. Commits without a recognised prefix are silently dropped from the CHANGELOG (still in git history). The "Highlights" paragraph requires the ANTHROPIC_API_KEY org-level secret; if the LLM call fails, a placeholder lands and the release still ships.

License

Licensed under either of

at your option. In SPDX terms: MIT OR Apache-2.0.

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in this work by you shall be dual-licensed as above, without any additional terms or conditions. See LICENSING.md.

flint-slating only depends on permissive-licensed libraries; the CI license-check job enforces this on every PR. torch and torchvision are pinned to the CPU-only PyTorch wheel index so the distribution does not bundle NVIDIA's proprietary CUDA libraries. Inference runs on CPU on Linux/Windows and on MPS (Metal) on Apple Silicon. See THIRD_PARTY_LICENSES.md for the per-dependency license breakdown.


© 2026 Gary Frattarola · Licensed under MIT OR Apache-2.0 · part of ParkviewLab

Ver o original no GitHub

Bom para

Relacionados