DocPull MCP server

DocPull

<!-- project-record: docpull -->

Active open-source project · MIT License

DocPull turns changing public web sources into cited, reproducible context for AI agents and retrieval pipelines. Use it when your application needs to know which sources it used, whether they changed, and how to rebuild the same context later.

<!-- mcp-name: io.github.raintree-technology/docpull -->

Install and sync your first source

pip install docpull
docpull init stripe-docs
docpull add https://docs.stripe.com
docpull sync
docpull diff
docpull export context-pack --target cursor

The project stores declared sources in docpull.yaml and resolved inputs in .docpull/context.lock.json. Later syncs produce a hash-based diff while preserving source URLs, content hashes, run IDs, citations, and export metadata.

No account or paid API is required for this path. Direct fetching, discovery, extraction, indexing, pack analysis, and diffs run locally.

Why use DocPull

source versions produced an answer or artifact.

• Reproduce agent context. Stable IDs, hashes, manifests, and lockfiles show which

feeds, repositories, packages, standards, and local documents.

• Detect source drift. Sync and diff documentation, product pages, policies,

sidecars remain readable without a hosted service.

• Keep evidence inspectable. Markdown, NDJSON, SQLite, citations, and provenance

data workflows, or a versioned context-pack release.

• Choose the downstream surface. Export context for agent clients, vector import,

choice and can be blocked with a zero-dollar budget.

• Keep expensive routes explicit. Browser and cloud rendering require an explicit

How it works

declared sources → local acquisition → versioned evidence → diff and validation → export

DocPull's v3 pack contract separates raw extraction, agent-ready context, and eval-grade evidence. Validate the level a downstream system requires:

docpull pack prepare packs/docs --eval-grade
docpull pack validate packs/docs --level eval
docpull ci --prepare

docpull ci checks freshness, citation coverage, pack quality, rights metadata, and other configured gates. It writes context-ci.report.json and CONTEXT_CI.md, then exits non-zero when a hard gate fails.

Supported surfaces

Common source shapes include static and server-rendered websites, OpenAPI documents, feeds, papers, public GitHub repositories, npm and PyPI packages, standards, datasets, transcripts, Wikimedia pages, product and policy pages, and local PDF or office files. See context-pack workflows for the complete surface.

MCP server

pip install 'docpull[mcp]'
docpull mcp

Claude Code can register the same local server:

Shortened. The full README is on GitHub.