ai-netcafe
Verified · 21 days agoTables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
claude mcp add docpick -- uvx docpick
Local document-extraction MCP that combines OCR, schema validation, and local LLM providers to turn documents into structured JSON. The repo has a real Python package, tests, built-in schemas, and an MCP server entry point, but the registry is stale at 0.1.2 while PyPI is already 0.1.3. Expect more setup than a hosted extractor because OCR engines and local model endpoints are part of the stack.
Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
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.
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.