About RAGandRAGfind
RAGandRAGfind is an MCP server published by bmetallica in the RAG category: document-centric RAG platform with ingestion, hybrid retrieval, MCP integration, admin tooling, and a separate local-first search UI called RAGfind.
The repository has 2 stars and 0 forks, with the last commit 3 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/bmetallica/RAGandRAGfindThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (32)
compare_document_versionsCompare a document with an earlier version, either explicitly or by automatically choosing the most likely previous version.
Parameters not published.
compare_documentsCompare two documents and summarize shared themes, differences, and action-item deltas.
Parameters not published.
cross_referenceFind sections across documents that reference the same topic, concept, or term.
Parameters not published.
extract_api_surfaceExtract API endpoints, HTTP methods, response codes, and payload hints from a document or section.
Parameters not published.
extract_config_keysExtract config keys, environment variables, and CLI flags from a document or section.
Parameters not published.
extract_deadlinesExtract deadlines, due dates, and time-bound commitments from a document or section.
Parameters not published.
extract_decisionsExtract explicit decisions, approvals, and resolutions from a document or section.
Parameters not published.
extract_entitiesExtract people, organizations, dates, contact data, and other named entities from a document or section.
Parameters not published.
extract_meeting_actionsExtract open tasks, responsibilities, and action items from a meeting protocol or similar document.
Parameters not published.
extract_operational_notesExtract troubleshooting notes, warnings, runtime caveats, and operational hints from a document or section.
Parameters not published.
Show all 32 tools
extract_requirementsExtract requirements, prerequisites, dependencies, and setup conditions from a document or section.
Parameters not published.
extract_risksExtract risks, blockers, warnings, and critical issues from a document or section.
Parameters not published.
extract_setup_stepsExtract installation, setup, configuration, and run steps from a document or section.
Parameters not published.
forgetDelete one of your own notes or stored files. Cannot touch crawled, uploaded or git-synced documents.
Parameters not published.
get_document_contextFetch chunks from a specific document by source reference or document id for targeted follow-up questions.
Parameters not published.
get_document_download_linkReturn a stable download link for the original document file. Use this when the user wants the complete/original document instead of extracted text.
Parameters not published.
get_document_fulltextReturn extracted text for a single document. Use this for reading/searching content, not as the primary tool for delivering the original PDF/file to the user.
Parameters not published.
get_document_sectionReturn a single section from a document by section index or by ranking sections against a query.
Parameters not published.
get_document_structureReturn a structure-oriented view of a document with section levels and previews.
Parameters not published.
get_fileReturn the content of one file or document by its ref or path. Use startLine/endLine for long files.
Parameters not published.
get_noteRead one of your own notes in full, so you can extend it instead of writing a second one.
Parameters not published.
get_original_documentReturn metadata and a stable download link for the original source file of a document. Prefer this tool when the user asks for the complete document, original PDF, original file, attachment, or download link.
Parameters not published.
list_document_sectionsList heuristic sections for a document and optionally rank them for a follow-up query.
Parameters not published.
list_documentsList documents currently available in the RAG database, prioritizing local uploads and synced files.
Parameters not published.
list_sourcesList available files, documents and notes to navigate the knowledge base.
Parameters not published.
save_fileStore a source file under its path. Writing the same path again replaces the previous content.
Parameters not published.
save_noteStore knowledge under a stable key. Writing the same key again replaces the previous note - read it with get_note first and extend it.
Parameters not published.
search_knowledgeSearch the knowledge base for code, documentation and own notes. Returns short excerpts with their source path.
Parameters not published.
search_rag_contextSearch the ingested RAG corpus and return the most relevant document excerpts.
Parameters not published.
smart_searchSearch with document-type and category filters plus reranking and expanded context.
Parameters not published.
summarize_documentCreate a server-side summary for a whole document, with optional focus query.
Parameters not published.
summarize_document_sectionCreate a server-side summary for a specific document section or the best matching section for a query.
Parameters not published.
Ask AI
Ask AI about RAGandRAGfind
Powered by Claude
Security checks
6 checks have not been run yet.