okra-public-docsQuery pre-extracted public documents via OkraPDF MCP — arxiv AI papers, SEC 10-K/10-Q filings, and more. Read, ask questions, extract structured data. No upl...
Install via ClawdBot CLI:
clawdbot install steventsao/okra-public-docsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://api.okrapdf.com/mcpUses known external API (expected, informational)
arxiv.orgAudited Apr 18, 2026 · audit v1.0
Generated May 10, 2026
A researcher queries pre-parsed arxiv papers to get answers about recent AI advancements, compare results across multiple papers, and extract structured benchmark data without manual reading.
A financial analyst browses pre-extracted SEC 10-K and 10-Q filings for major companies, asks questions about revenue segments, risk factors, and compares R&D spending across competitors to inform investment decisions.
An analyst uses the SEC filing channel to compare AI strategies, gross margins, or debt obligations across up to 10 tickers in a single query, enabling rapid competitive benchmarking.
A data scientist extracts tabular benchmark results from arxiv papers by providing a JSON schema, getting structured numbers for models, datasets, and scores without manual copy-pasting.
Arxiv papers channel requires a free API key for access, while SEC filings remain completely open. This model attracts users with zero-auth SEC features and upsells them to the authenticated arxiv service.
OkraPDF provides pre-extracted, structured document corpora (research papers and financial filings) accessible via API. Users pay indirectly through API key usage or future subscription plans for high-volume access.
By integrating as MCP servers, OkraPDF becomes a core utility within AI agent ecosystems (Claude Code, Cursor). This creates stickiness and positions the platform as an essential tool for agentic document querying.
💬 Integration Tip
Add the MCP server configuration to your AI agent's config file (e.g., mcp.json for Claude Code) and restart the agent to instantly access pre-indexed documents.
Scored May 10, 2026
Find and compile academic literature with citation lists across Google Scholar, PubMed, arXiv, IEEE, ACM, Semantic Scholar, Scopus, and Web of Science. Use for requests like “find related literature,” “related work,” “citation list,” or “key papers on a topic.”
Search academic papers and conduct literature reviews using OpenAlex API (free, no key needed). Use when the user needs to find scholarly papers by topic/aut...
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
Tool for manual per-paper ArXiv paper processing: batch/source/pdf download then model-driven full-text reading and summary.md writing in chosen language.
Fetch academic papers from Sci-Hub given a DOI. Automatically downloads PDFs and saves them to research/papers/ with clean filenames. Use when the user provides a DOI or requests a paper from PubMed.
Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user needs to find papers on a topic, get details for specific DOIs, or draft sections of a literature review with proper citations.