Smart Reader MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Smart Reader MCPRead the PDF at ~/Downloads/invoice.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RETIRED — Prism / smart-reader-mcp
Status: retired product (hard cut, 2026-08-07)
Prism was a local media router (sniff + spawn Citra/Iris/Cue MCP servers). That composition belongs to the agent host / skills, not a seventh product.
Do not install as a product
Do not add
smart-reader-mcp/prismas a current MCP server for new agents.Do not treat this repository as an active Instrument, marketplace listing, or release authority.
Historical source remains for archaeology only.
Related MCP server: docsearch
What to use instead
Need | Authority |
PDF evidence | Citra — |
Image evidence | Iris — |
Video timeline | Cue — |
Unknown media type | Host skill: sniff (magic bytes / extension) then call the matching instrument MCP |
Family law |
|
Why retired
Multi-server MCP hosts already compose independent servers.
A router product doubles process tax and couples three release trains.
Instruments law: host owns composition; products own one evidence domain.
Historical package ids (non-authority)
@sylphx/smart-reader-mcpbin
prism/smart-reader-mcpMCP name
io.github.SylphxAI/smart-reader-mcp
If these still resolve on npm, they are legacy artifacts, not the current product model.
Sniff utility (non-product)
Magic-byte sniffing for host skills lives under src/sniff/ as reference code.
Prefer copying a minimal sniff into a host skill rather than depending on this package.
License
MIT — see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server that reads PDFs and exposes them as structured Markdown, metadata, outlines, images, and tables to LLM consumers via tools like pdf_read_markdown and pdf_info.Apache 2.0
- AlicenseAqualityDmaintenanceMCP server that enables searching and reading binary document files (PDF, DOCX, PPTX, XLSX, ODT, ODS, ODP, RTF, EPUB) using regex patterns and retrieving content by sections.2MIT
- FlicenseAqualityCmaintenanceConverts files (PDF, DOCX, PPTX, XLSX, images via OCR) and URLs to Markdown, enabling AI clients to read them via a single MCP tool.1-

smart-read-mcpofficial
AlicenseNot gradedqualityFmaintenanceProvides a universal read path for agents to extract facts, metadata, and provenance from local files and guarded remote URLs without using generative LLMs.MIT