yuplin2333/mcp-long-context-reader
If you are the rightful owner of mcp-long-context-reader and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
MCP Long Context Reader is a Python-based toolkit designed to address the context window limitations and high costs associated with processing extensive documents using Large Language Models (LLMs).
Tools
Functions exposed to the LLM to take actions
glance
Provides a quick look at the beginning of a file, showing the first few thousand characters and total line count.
search_with_regex
Finds and extracts text snippets using regular expression patterns.
retrieve_with_rag
Uses a Retrieval-Augmented Generation pipeline to find the most semantically relevant document chunks.
summarize_with_map_reduce
Summarizes large chunks in parallel and combines those summaries.
summarize_with_sequential_notes
An LLM reads the document sequentially, taking query-aware notes.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client