Rag
A production-grade RAG implementation that handles the messy parts: multi-format ingestion (DOCX, PDF with OCR, audio via Whisper), Korean-optimized chunking, and hybrid BM25 plus vector search with RRF. The indexing pipeline uses AI-powered chunk contextualization to generate bilingual keywords and preserve document context across chunking boundaries. A two-commit model saves expensive OCR and transcription work before hitting embedding APIs, so a rate limit or crash doesn't force you to re-process a 600-page scan. Supports Ollama, OpenAI, Gemini, and Anthropic for both embedding and contextualization. Exposes search tools over MCP stdio and runs headless indexing via CLI. Handles multiple knowledge bases in a single server process with SQLite WAL for concurrent read access during writes.
- tools
- 7
- transport
- STDIO
- env vars
- 5
- last updated
- May 25, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
list_knowledge_basesList all available KBs with status (file/chunk counts, indexing status)
List all available KBs with status (file/chunk counts, indexing status)
No parameter schema in public metadata yet.
search_documentsHybrid BM25 + vector search with RRF. Supports search_mode: auto, bm25, vector
Hybrid BM25 + vector search with RRF. Supports search_mode: auto, bm25, vector
No parameter schema in public metadata yet.
get_document_chunkRetrieve full content of a specific chunk by ID
Retrieve full content of a specific chunk by ID
No parameter schema in public metadata yet.
start_reindexQueue an indexing request. Scope merge, force/deferred flags, orchestrator auto-spawn
Queue an indexing request. Scope merge, force/deferred flags, orchestrator auto-spawn
No parameter schema in public metadata yet.
cancel_reindexRemove a pending (not-yet-started) queue entry
Remove a pending (not-yet-started) queue entry
No parameter schema in public metadata yet.
get_index_infoIndex metadata, queue state (status/position/deferred/last_error), contextualization health
Index metadata, queue state (status/position/deferred/last_error), contextualization health
No parameter schema in public metadata yet.
check_changesDry-run filesystem scan. Lightweight, no API calls
Dry-run filesystem scan. Lightweight, no API calls
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
OPENAI_API_KEYANTHROPIC_API_KEYGEMINI_API_KEYVOYAGE_API_KEYGROQ_API_KEYReadme
FieldCure MCP RAG Server
A Model Context Protocol (MCP) server for indexing and searching local document collections. Supports DOCX, HWPX, PDF (with OCR), Excel, PowerPoint, and audio (Whisper transcription, Windows-only), with hybrid keyword + semantic search optimized for Korean and English.
Built with C# and the official MCP C# SDK.
Commands
Details
- Repository
- github.com/fieldcure/fieldcure-mcp-rag
- Categories
- AI & LLM Tools, Search & Web Crawling
- Package
FieldCure.Mcp.Rag- Transport
- STDIO
- Registry
- MCP registry, active
More from fieldcure
Related AI & LLM Tools MCP servers
View all
Giskard Memorygiskard09/giskard-memoryPay-per-use semantic memory for AI agents. SHA256 commitment, Ed25519 sig, Lightning.0stars
User Promptjacob-j-thomas/user-context-retrieval-mcp-serverAn MCP server that enables AI agents to ask users clarifying questions via pop-up terminal windows.0stars
Memory Ftskurovu146/claude-memory-mcpLong-term memory for Claude Code with SQLite FTS5 search and BM25 ranking0stars
Agent Guardmdfifty50-boop/agent-guard-mcpConstitutional guardrails and loop detection for AI agents0starsAgent Securitymdfifty50-boop/agent-security-mcpSecurity scanning and threat detection for AI agents0stars
Gemini Code Context Mcpqmediat/gemini-code-context-mcpCodebase Q&A for Claude Code through Gemini's 1M-token window, with workspace scans and caching.0stars