ai-netcafe
Verified · 12 days ago23 agent tools + a measured per-call model cost dataset. No key needed to start.
Answer questions from documents too large to fit in context, reading only the sections you need.
claude mcp add docslicer -- uvx docslicer
A document-questioning server built to handle files that are too large for a single context window by selectively reading relevant sections. It is aimed at research, legal, policy, or enterprise document workflows where targeted retrieval matters more than full ingestion. Packaging across MCPB and PyPI is a decent maturity signal, though adoption still looks early.
23 agent tools + a measured per-call model cost dataset. No key needed to start.
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
MCP server for filesystem access
MCP server for terminal commands, file operations, and process management
Local-first knowledge management with bi-directional LLM sync via Markdown files.
Evidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.