
帮助用户读取解析 PDF,并提供可引用页码与坐标证据定位内容
用于高速读取、解析和处理 PDF 文档的 MCP 工具,适合自动化文档工作流。
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML, images. Fast Rust MCP server + CLI. Local, no API key.
Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
Locus — the exact code chunk for the job: local BM25 search for agents.
Exact-version library docs from your lockfile — local, offline, no rate limits.
Sniff format and delegate to Sylphx Reader siblings for unified media read.
Spine — repository architecture with file-level proof: graph, paths, traces, and impact.
A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.
Citra — PDF answers with page-level proof: structure, tables, OCR, and page citations.
Iris — image facts with pixel-level proof. OCR runs only when requested.
Evidence-first video MCP. Timeline document with ffprobe streams and subtitle cues.
Cue — video answers with timestamp-level proof. Scenes and frames stay off until asked.