Happy slice of mcp pizzaMCP.pizza
docpull

docpull

MCP.Pizza Chef: raintree-technology

DocPull lets you gather, version, and cite information from websites and documents on your own computer. It helps keep your AI assistant’s knowledge current by syncing changes and exporting organized context packs usable in apps like Claude Desktop and Cursor. You don’t need an online account or browser, but setup requires some developer steps like installing Python packages and running commands. It supports many document types including PDFs with optional setup.

Files/PDF
Other
Web/Research

Use This MCP server To

Collect and version web pages for AI context Sync and update documentation automatically Export cited context packs for AI assistants Track changes in web content over time Parse local PDFs into AI-readable context Audit and review context quality before use Integrate updated context into Claude Desktop or Cursor

README

DocPull

docpull

Context dependencies for AI agents. Browser-free by default.

Python 3.10+ PyPI version PyPI downloads GitHub stars License: MIT

DocPull is a local-first dependency manager for AI context. Define the public web sources an agent depends on, sync them into cited context packs, diff what changed, and export reproducible context for Cursor, Claude, OpenAI, LlamaIndex, LangChain, MCP clients, and RAG pipelines.

Architecturally, DocPull is the evidence and acquisition engine: it acquires, versions, cites, hashes, and replays evidence. Downstream products own scheduling, review, approved claims, legal conclusions, and notifications. See the architecture decision.

The core workflow is a docpull.yaml plus a .docpull/context.lock.json, similar in spirit to code dependency manifests and lockfiles:

docpull init my-agent-context
docpull add stripe react postgres
docpull install
docpull deps
docpull sync
docpull diff
docpull export context-pack --target openai

Bundled aliases such as stripe, react, postgres, openai, and apple-hig expand to normal HTTPS sources in docpull.yaml. Runs stay reproducible through the lockfile: source URLs, discovered URLs, content hashes, run IDs, aliases, and export metadata are recorded without storing secrets. Use docpull sources list to inspect the bundled alias catalog and docpull install to validate or recreate the local dependency lock. Use docpull deps to see the current dependency, lockfile, latest run, and export status.

Projects can also track typed known-source specs such as pypi:requests, rfc:9110, wiki:Web_scraping, or a local dataset path. Those sources sync through their typed lanes and do not use discovery.

The original docpull URL ... workflow still works: fetch public or explicitly authorized static/server-rendered web pages and write clean Markdown, NDJSON, SQLite, or Open Knowledge Format (OKF) outputs. OKF is a portable bundle format that keeps content, indexes, and manifests together for reuse across tools. Project mode adds the persistent evidence lifecycle on top: sources, runs, diffs, exports, evals, accounting, and local auditability.

DocPull is local-first: direct fetching, sitemap/link discovery, extraction, indexing, pack intelligence, and opt-in agent-browser rendering can run with no external account and no required API spend. Cloud rendering is explicit and budget-guarded.

DocPull aligns core workflows across CLI, Python SDK, and MCP, with each surface optimized for its user. The Surface Contract defines how those surfaces align and where they intentionally differ. For the context dependency workflow, see Context Dependencies.

Web-source ingestion is the core workflow. Documentation is one high-value lane, not the product boundary. It works best on static or server-rendered pages such as blogs, API references, OpenAPI specs, changelogs, vendor pages, product pages, filings, docs sites, and other pages where the useful content is available in HTML or embedded page data.

docpull FAQ

Can I use docpull to gather and version web and document content for AI context?
Yes — docpull helps you collect, track changes, and package web pages and documents as context for AI assistants like Claude Desktop and Cursor.
Does docpull require an API key or online account to use?
No — docpull works locally without needing any external accounts or API keys by default.
Which apps support docpull as a context source?
It works with Claude Desktop and Cursor, and can export context for OpenAI and other MCP clients.
How hard is it to set up docpull?
It requires developer-level setup, including installing via pip and running CLI commands.
Can I use docpull to keep my AI assistant’s knowledge up to date from websites?
Yes — docpull syncs and diffs web sources so your AI has current, cited information.
Does docpull handle PDFs and other document types?
Yes, with optional local PDF parsing enabled by installing extra packages.
Is docpull browser-based?
No — it works without a browser by default, fetching static or server-rendered pages locally.