Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
nuget FieldCure.Mcp.RagClaude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
OPENAI_API_KEY=<value> ANTHROPIC_API_KEY=<value> GEMINI_API_KEY=<value> VOYAGE_API_KEY=<value> GROQ_API_KEY=<value> claude mcp add io.github.fieldcure-rag -- nuget FieldCure.Mcp.Ragรันในเทอร์มินัล
{ "mcpServers": { "io.github.fieldcure-rag": { "command": "nuget", "args": [ "FieldCure.Mcp.Rag" ], "env": { "OPENAI_API_KEY": "<value>", "ANTHROPIC_API_KEY": "<value>", "GEMINI_API_KEY": "<value>", "VOYAGE_API_KEY": "<value>", "GROQ_API_KEY": "<value>" } } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
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.
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
Built with C# and the official MCP C# SDK.
fieldcure-mcp-rag
├── serve --base-path <path> # Multi-KB MCP search server (stdio)
├── exec --path <kb-path> [--force] [--partial ...] # Headless indexing for a single KB
├── exec-queue --queue-file <path> [--sweep-all] # Process deferred indexing queue
├── prune-orphans --base-path <path> # Delete orphan KB folders
└── smoke-ocr --pdf <scanned.pdf> # Self-test: OCR a scanned PDF (Windows)
kb_id parameter. Can run while exec is indexing (SQLite WAL).--partial re-runs only downstream stages when models change, preserving OCR output.--sweep-all processes deferred entries too (used at app shutdown).., _ prefix, -backup-) are never touched.0 on a non-empty result. Surfaces DllNotFoundException / BadImageFormatException distinctly so a missing or arch-mismatched native is immediately visible. Useful for verifying that the OCR native path is wired correctly on a given host (notably win-arm64 dnx installs).System.Numerics.Vector[math: LaTeX] blocks.mp3, .wav, .m4a, .ogg, .flac, .webm) via Whisper.net — Windows-only. Model size (Tiny→Large) is auto-selected from detected GPU/RAM/cores at startup; each transcript chunk records audio.model_size and audio.transcribed_at for future reindex auditingstart_reindex MCP tool — no direct exec spawnorchestrator.lock)prune-orphans physical cleanup--sweep-all)cancel fileconfig.json with provider configuration/api/embed, contextualization via /api/chat with keep_alive and num_ctx support. Requires Ollama 0.4.0+./v1/embeddings, contextualization via /v1/chat/completions. Works with OpenAI, Azure OpenAI, Groq, LM Studio, Together AI./v1beta/models/{model}:embedContent with task_type asymmetric retrieval (RETRIEVAL_DOCUMENT / RETRIEVAL_QUERY) and Matryoshka dimension truncation (768 / 1536 / 3072). gemini-embedding-2, multilingual, 8k token input./v1/messages.OPENAI_API_KEY, ANTHROPIC_API_KEY, etc. Batch indexing commands (exec, exec-queue) are env-var-only. Interactive MCP search can fall back to MCP elicitation when the client supports it.Standard RAG chunking loses context — a sentence about "the protocol" becomes ambiguous when ripped from its surrounding paragraphs. This server addresses that with Unified Chunk Contextualization: a single LLM call per chunk that produces both contextual framing and bilingual (Korean + English) keywords in one pass.
The result is stored alongside the original chunk text:
This is enabled by setting contextualizer in config.json. It can be disabled (set provider/model to empty) if you prefer raw chunk indexing.
The exec command runs a 5-stage pipeline per file:
For large files, Stage 1 alone can take 20+ minutes — OCR on a 596-page scanned PDF, or Whisper transcription of a multi-hour audio recording. The first audio file in any KB also pays a one-time ggml model download (cached under {UserProfile}/.fieldcure/whisper-models/). To prevent expensive upstream work from being lost when later stages fail, the pipeline uses a 2-commit model:
Stages 1-3 (Extract → Chunk → Contextualize)
↓
[Commit 1] chunks saved as PendingEmbedding
↓
Stage 4 (Embed)
├─ success → [Commit 2a] promote chunks to Indexed
└─ failure → chunks remain PendingEmbedding (retry next exec)
Why this matters: A 25-minute OCR result is persisted on disk before any embedding API call. If Stage 4 fails (network error, rate limit, token limit, process crash, even power loss), the chunks survive. The next exec hash-skips the file (no OCR re-run) and the deferred retry pass attempts only Stage 4.
If a single chunk in a file exceeds the embedding model's token limit (e.g., a math-dense page in a textbook), the binary split algorithm isolates that one chunk:
EmbedBatch([0..1249]) → 400 "input[846] too long"
├─ EmbedBatch([0..624]) → OK (promote 625)
└─ EmbedBatch([625..1249]) → 400
├─ EmbedBatch([625..937]) → 400
│ ... (binary search narrows toward chunk 846)
│ └─ EmbedBatch([846..846]) → 400 (mark chunk 846 Failed)
└─ EmbedBatch([938..1249]) → OK (promote 312)
Result: 1249 chunks indexed, only chunk 846 marked Failed. The file's status becomes Degraded — partially searchable instead of completely missing.
Each exec ends with a retry pass over any chunks left in PendingEmbedding state from previous runs:
FailedEach KB DB carries a PRAGMA user_version tag. The exec command migrates older schemas automatically as part of InitializeSchema(). The serve command opens DBs read-only and never triggers migration — older-schema KBs continue to serve search queries correctly while their new-feature columns remain unused.
dotnet tool install -g FieldCure.Mcp.Rag
git clone https://github.com/fieldcure/fieldcure-mcp-rag.git
cd fieldcure-mcp-rag
dotnet build
Index a folder and search it without any embedding setup (BM25 only):
# 1. Install
dotnet tool install -g FieldCure.Mcp.Rag
# 2. Create a minimal config
$kbPath = "$env:LOCALAPPDATA\FieldCure\Mcp.Rag\demo"
New-Item -ItemType Directory -Force -Path $kbPath
@'
{
"id": "demo",
"name": "Demo KB",
"sourcePaths": ["C:\\my-docs"]
}
'@ | Set-Content "$kbPath\config.json"
# 3. Index
fieldcure-mcp-rag exec --path $kbPath
# 4. Start the search server
fieldcure-mcp-rag serve --base-path "$env:LOCALAPPDATA\FieldCure\Mcp.Rag"
For full retrieval quality with semantic search and contextualization, add embedding and contextualizer blocks to config.json — see Usage below.
%LOCALAPPDATA%\FieldCure\Mcp.Rag\{kb-id}\config.json
{
"id": "my-kb-001",
"name": "Project Docs",
"created": "2026-04-03T00:00:00Z",
"sourcePaths": ["C:\\Users\\me\\Documents\\project-docs"],
"contextualizer": {
"provider": "anthropic",
"model": "claude-haiku-4-5-20251001",
"apiKeyPreset": "Claude"
},
"embedding": {
"provider": "openai",
"model": "text-embedding-3-small",
"apiKeyPreset": "OpenAI"
}
}
API keys are resolved from environment variables: apiKeyPreset: "OpenAI" → OPENAI_API_KEY, "Claude" → ANTHROPIC_API_KEY, "Gemini" (or "Google") → GEMINI_API_KEY.
Gemini embedding example — asymmetric retrieval with 1536-dim Matryoshka truncation (50% storage of full 3072 with identical MTEB score):
"embedding": {
"provider": "gemini",
"model": "gemini-embedding-2",
"apiKeyPreset": "Gemini",
"dimension": 1536
}
fieldcure-mcp-rag exec --path "C:\Users\me\AppData\Local\FieldCure\Mcp.Rag\my-kb-001"
fieldcure-mcp-rag serve --base-path "C:\Users\me\AppData\Local\FieldCure\Mcp.Rag"
A single serve process handles all knowledge bases under the base path. Tools accept a kb_id parameter to target a specific KB.
Add to claude_desktop_config.json:
{
"mcpServers": {
"rag": {
"command": "fieldcure-mcp-rag",
"args": ["serve", "--base-path", "C:\\Users\\me\\AppData\\Local\\FieldCure\\Mcp.Rag"],
"env": {
"OPENAI_API_KEY": "sk-...",
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
}
}
All tools (except list_knowledge_bases) require a kb_id parameter to specify the target knowledge base.
Document formats are provided by FieldCure.DocumentParsers:
## Page N headers; OCR fallback for scanned pages (Tesseract, eng+kor)src/FieldCure.Mcp.Rag/
├── Program.cs # CLI entry (exec | exec-queue | serve | prune-orphans)
├── MultiKbContext.cs # Multi-KB manager (lazy load, Classify, lazy unload)
├── ExecQueueRunner.cs # Deferred queue orchestrator
├── OrphanCleanupRunner.cs # prune-orphans CLI
├── Configuration/
│ ├── RagConfig.cs # config.json model (KeepAlive, NumCtx fields)
│ └── OllamaDefaults.cs # Shared defaults (KeepAlive="5m", NumCtx=8192)
├── Indexing/
│ ├── IndexingEngine.cs # 5-stage pipeline (2-commit model)
│ └── EmbeddingBatchSplitter.cs # Binary-split per-chunk failure isolation
├── Contextualization/
│ ├── IChunkContextualizer.cs
│ ├── OpenAiChunkContextualizer.cs # /v1/chat/completions
│ ├── OllamaChunkContextualizer.cs # /api/chat (keep_alive + num_ctx)
│ ├── AnthropicChunkContextualizer.cs
│ └── NullChunkContextualizer.cs
├── Embedding/
│ ├── IEmbeddingProvider.cs
│ ├── OpenAiCompatibleEmbeddingProvider.cs # /v1/embeddings
│ ├── OllamaEmbeddingProvider.cs # /api/embed (keep_alive)
│ ├── NullEmbeddingProvider.cs
│ └── EmbeddingBatchSizes.cs
├── Storage/
│ └── SqliteVectorStore.cs # SQLite + FTS5 + SIMD cosine similarity
├── Search/
│ ├── HybridSearcher.cs # BM25 + Vector → RRF
│ └── RrfFusion.cs
├── Chunking/
│ ├── TextChunker.cs
│ └── ChunkLimits.cs
└── Tools/
├── ListKnowledgeBasesTool.cs
├── SearchDocumentsTool.cs
├── GetDocumentChunkTool.cs
├── StartReindexTool.cs # Queue entry point + orchestrator spawn
├── CancelReindexTool.cs # Remove pending queue entry
├── GetIndexInfoTool.cs # Includes queue state
└── CheckChangesTool.cs
Knowledge base data is stored at %LOCALAPPDATA%\FieldCure\Mcp.Rag\{kb-id}\:
config.json — knowledge base configurationrag.db — SQLite database (chunks, embeddings, FTS5 index, file hashes, indexing lock)Queue and lock files at %LOCALAPPDATA%\FieldCure\Mcp.Rag\:
.deferred-queue.json — pending indexing requestsorchestrator.lock — PID lock for the queue orchestrator# Build
dotnet build
# Test
dotnet test
# Pack as dotnet tool
dotnet pack src/FieldCure.Mcp.Rag -c Release
Part of the AssistStudio ecosystem.
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
{ "mcpServers": { "io.github.fieldcure-rag": { "command": "nuget", "args": [ "FieldCure.Mcp.Rag" ], "env": { "OPENAI_API_KEY": "<value>", "ANTHROPIC_API_KEY": "<value>", "GEMINI_API_KEY": "<value>", "VOYAGE_API_KEY": "<value>", "GROQ_API_KEY": "<value>" } } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ผู้เผยแพร่ระบุตัวแปรสภาพแวดล้อมเหล่านี้: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, VOYAGE_API_KEY, GROQ_API_KEY
Rag ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-09 MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.