NeuronCite MCP server
2026년 11월 9일 커밋AI 클라이언트가 의미론적 문서 검색을 수행하고, 로컬 PDF 라이브러리를 인덱싱하며, 로컬 LLM을 사용하여 학술 인용을 자율적으로 검증할 수 있게 합니다.
다른 이름 FF-TEC/NeuronCite
- 스타
- 10
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 9일
- 라이선스
- AGPL-3.0
NeuronCite MCP란?
AI 클라이언트가 의미론적 문서 검색을 수행하고, 로컬 PDF 라이브러리를 인덱싱하며, 로컬 LLM을 사용하여 학술 인용을 자율적으로 검증할 수 있게 합니다.
프로젝트 README에서 생성된 요약
NeuronCite MCP server 정보
연구자와 학술 전문가들은 NeuronCite를 사용하여 로컬 PDF 라이브러리를 검색 가능한 지식 베이스로 변환할 수 있습니다. 이 도구는 AI 클라이언트가 의미론적 문서 검색을 수행하고, 대규모 파일 디렉토리를 인덱싱하며, 학술 인용을 자율적으로 검증할 수 있도록 지원합니다. Ollama와 통합되어 로컬 LLM을 통해 LaTeX 논문을 서지 정보와 대조하여 확인하며, 데이터를 클라우드로 전송하지 않고도 모든 주장에 대한 판정 및 신뢰도 점수를 제공합니다.
이 시스템은 초기 모델 다운로드 후 폐쇄망이나 보안 환경에서 실행할 수 있는 로컬 우선 솔루션으로 작동합니다. Claude와 같은 어시스턴트가 인덱싱 세션을 관리하고, HNSW 벡터 유사도 및 BM25 키워드 매칭을 사용한 하이브리드 검색을 실행하며, PDF 주석을 처리할 수 있도록 43개의 MCP 도구를 제공합니다. 사용자는 단일 Rust 바이너리, Docker 컨테이너 또는 웹 기반 GUI를 통해 서버와 상호작용할 수 있으며, 인용 검증 작업을 위해 실행 중인 Ollama 인스턴스만 있으면 됩니다.
활용 사례
- 1학술 인용 검증AI가 LaTeX 논문과 서지 정보를 파싱하여 모든 인용이 실제 출처 자료에 의해 뒷받침되는지 확인할 수 있습니다.
- 2의미론적 문서 검색개발자는 하이브리드 검색 방식을 사용하여 대규모 로컬 PDF 문서 모음 내에서 특정 구절을 찾을 수 있습니다.
- 3자동 PDF 주석 생성시스템이 검증 결과에 따라 PDF 내의 특정 텍스트 구절을 자동으로 강조 표시하고 주석을 달 수 있습니다.
- 4웹 기반 지식 인덱싱사용자는 웹사이트를 크롤링하고 DOI를 해결하여 인덱싱을 위한 로컬 문서 라이브러리를 확장할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능ff-tec/neuroncite is public and reachablegithub.com/ff-tec/neuroncite ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-09github.com/ff-tec/neuroncite ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음0 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기NeuronCite is an enterprise-grade semantic search engine that transforms your document library into an instantly searchable knowledge base -- and autonomously verifies every citation in your academic papers using local LLMs. No cloud. No API keys. Your data stays on your machine.
Written in Rust, it ships as a single binary (CPU) or minimal bundle (GPU) for Windows, macOS, and Linux. After a one-time download of models and runtime dependencies, the system operates fully offline, including in air-gapped and classified environments. A built-in MCP server with 43 tools lets AI assistants like Claude control the full workflow -- indexing, searching, verifying citations, annotating PDFs -- directly from the chat interface.
Why NeuronCite
Privacy by Design -- All document processing runs locally. No user data leaves the machine, no telemetry, no cloud accounts. No internet connection required after initial setup (embedding models, pdfium, and optional OCR/Ollama binaries). Network-dependent features (DOI resolution, HTML crawling, citation source fetching) are unavailable in air-gapped mode. Supports air-gapped and classified environments once all dependencies are provisioned.
Autonomous Citation Verification -- Feed a LaTeX paper and its bibliography.
NeuronCite indexes the cited PDFs, runs a local LLM via Ollama, and verifies
every \cite{} command against actual source material. Each citation receives a
verdict, confidence score, and correction suggestions.
Enterprise-Grade Architecture -- 16 Rust crates with clear separation of concerns. 43 MCP tools, 34 REST API endpoints, a browser-based GUI with 7 tabs, a Python client library, and 11 CLI commands. CPU-only builds compile into a single executable that runs without Docker, Kubernetes, or external infrastructure. Citation verification additionally requires a running Ollama instance.
Quick Start
1. Download the binary for your platform from the Releases page.
2. Double-click the binary. The application opens in a native window
(WebView2 on Windows, WebKit on macOS/Linux) -- no terminal, no configuration
required. Linux GUI builds require libwebkit2gtk-4.1-0 at runtime (see
Installation for details).
3. Select a directory of PDFs in the Indexing tab, choose an embedding model, and click Start. The first run downloads the selected model (50 MB--1 GB depending on model size).
Terminal alternative: Run
neuroncitefrom the command line, or index directly withneuroncite index --directory ./papers.
Docker alternative:
docker run --gpus all -p 3030:3030 \ -v neuroncite-data:/data/Documents/NeuronCite \ ghcr.io/ff-tec/neuroncite:latest
Features
Hybrid Search
Combines three retrieval algorithms for high-precision document search:
- HNSW vector similarity -- Approximate nearest neighbor search over dense embeddings for semantic matching
- BM25 keyword matching -- SQLite FTS5 full-text index for exact term matching
- Reciprocal Rank Fusion -- Merges and normalizes scores from both retrieval methods
- Cross-encoder reranking -- Optional second-stage scoring with a cross-encoder model for precision-critical queries
- Sub-chunk refinement -- Configurable divisors for finer-grained passage retrieval within chunks
Document Indexing
- PDF extraction with three backends: pdf-extract (pure Rust, default), pdfium (multi-column layout support), and Tesseract OCR (image-heavy pages)
- HTML crawling with BFS traversal, depth limiting, rate limiting, domain filtering, regex URL patterns, and sitemap parsing
- Four chunking strategies: page-based, word-window (fixed word count with overlap), token-window (subword tokens), and sentence-based (respects citation boundaries)
- Eight embedding models from 33M to 335M parameters (384 to 4096 dimensions), downloaded from HuggingFace on first use
- GPU acceleration via ONNX Runtime with CUDA 12.4, DirectML, CoreML, and ROCm execution providers; CPU fallback on all platforms
Citation Verification
NeuronCite parses LaTeX papers for citation commands (\cite, \citep,
\citet, \autocite, and variants), resolves them against BibTeX entries, and
verifies each claim against indexed source PDFs using a local LLM via Ollama.
Five-stage verification pipeline:
- Parse LaTeX, extract citation commands, resolve cite-keys against BibTeX
- Match bibliographic entries to PDFs via Jaro-Winkler similarity (threshold 0.80)
- Group citations into batches for parallel processing, preserving co-citations and section context
- Verify each batch through the LLM with a minimum of 2 search queries per citation, including cross-corpus search for alternative sources
- Export 6 output files: annotation CSV, citation CSV/XLSX, corrections JSON, citation report JSON, full detail JSON, and annotated PDFs
Seven verdict types:
| Verdict | Meaning |
|---|---|
supported |
Claim explicitly found in cited source with page numbers and passages |
partial |
Source supports part of the claim; other parts absent or unsupported |
unsupported |
PDF found and read but no passage supports the claim |
not_found |
Source PDF not in indexed corpus |
wrong_source |
Claim verifiable but evidence found in a different source |
unverifiable |
Future projections, subjective statements, or insufficiently specific claims |
peripheral_match |
Text found only in non-substantive sections (TOC, bibliography, appendix) |
Each verdict includes a confidence score (0.00--1.00), critical/warning flags for contradictions and temporal mismatches, and correction suggestions with types (rephrase, add context, replace citation).
PDF Annotation
Highlights text passages in PDFs with color-coded annotations based on verification verdicts. Uses a 5-stage text matching pipeline:
- Exact byte-level match
- Normalized match with whitespace collapsing
- Fuzzy character-level match (string distance)
- Fallback extraction via multi-backend PDF text pipeline
- OCR fallback for scanned pages
Accepts annotation input as CSV or JSON. Supports comment annotations with popup text alongside highlights.
Web Frontend (7 Tabs)
The SolidJS single-page application is compiled into the binary via rust-embed
and served at http://localhost:3030.
| Tab | Function |
|---|---|
| Sources | BibTeX management, web crawling (BFS with regex patterns, sitemap parsing), DOI resolution (Unpaywall, Semantic Scholar, OpenAlex), metadata extraction |
| Indexing | Directory selection, embedding model and chunking strategy configuration, real-time progress tracking, session management |
| Search | Multi-session hybrid search with vector/BM25/reranking toggles, sub-chunk refinement, grouped and flat result views, export as Markdown/BibTeX/CSL-JSON/RIS |
| Citations | LaTeX file selection with auto-detection of .bib files, Ollama model selection with connection test, verification mode presets (quick, balanced, thorough), live results with expandable verdicts |
| Annotations | CSV/JSON annotation input, source PDF directory selection, 5-stage text location pipeline, color configuration, per-quote progress tracking |
| Models | Embedding model catalog with download/activate controls, cross-encoder reranker management, Ollama LLM catalog, GPU/CUDA system info, model diagnostics |
| Settings | FTS5 index optimization, HNSW vector index rebuild, database reset, dependency detection (pdfium, Tesseract, Poppler), MCP server registration, real-time log streaming via SSE |
MCP Server (43 Tools)
The Model Context Protocol server exposes 43 tools for AI agent integration via JSON-RPC 2.0 over stdio, organized in 8 categories:
| Category | Tools | Purpose |
|---|---|---|
| Session Management | 5 | List, delete, update, diff, discover index sessions |
| Indexing | 4 | Index directories, add files, reindex, preview chunks |
| Search & Retrieval | 8 | Search, batch search, multi-session search, compare, text search, content retrieval, export |
| File & Chunk Inspection | 4 | List files, inspect chunks, compare files, quality reports |
| Citation Verification | 8 | Create jobs, add claims, submit, check status, fetch rows, export, retry, fetch sources |
| Annotation | 4 | Annotate PDFs, check status, inspect annotations, remove annotations |
| Web Sources | 3 | Fetch HTML, crawl websites, check crawl status |
| System | 3 | List models, health check, log streaming |
REST API (34 Endpoints)
Axum-based HTTP server with OpenAPI specification (utoipa), bearer token authentication with constant-time comparison, per-IP rate limiting, CORS, and Server-Sent Events for real-time progress streaming. Endpoints cover all functionality: sessions, indexing, search, citation, annotation, models, and system health.
Python Client
Typed access to all REST endpoints with subprocess server management.
from neuroncite import NeuronCiteClient
client = NeuronCiteClient() # default: http://127.0.0.1:3030
results = client.search(session_id="...", query="capital asset pricing model")
for r in results:
print(f" [{r.score:.2f}] {r.citation}")
30+ typed methods covering search, indexing, citation, annotation, and model management. See clients/python/README.md for the full API reference.
Installation
Pre-built Binaries
Download the binary for your platform from the Releases page. Each release includes SHA-256 checksums for verification.
| Platform | Architecture | GUI | Artifact |
|---|---|---|---|
| Windows | x86_64 | Native window (WebView2) | neuroncite-windows-x64.exe |
| Linux | x86_64 | Native window (WebKit2GTK) | neuroncite-linux-x64 |
| Linux | x86_64 | Browser-only (headless) | neuroncite-linux-x64-server |
| Linux | ARM64 | Native window (WebKit2GTK) | neuroncite-linux-arm64 |
| Linux | ARM64 | Browser-only (headless) | neuroncite-linux-arm64-server |
| macOS | ARM64 (Apple Silicon) | Native window (WebKit) | neuroncite-macos-arm64 |
| macOS | x86_64 (Intel) | Native window (WebKit) | neuroncite-macos-x64 |
Linux GUI variants require libwebkit2gtk-4.1-0 at runtime.
Server variants have zero runtime dependencies beyond glibc.
Docker
Four image variants are published to the GitHub Container Registry. See docker/README.md for compose profiles, environment variables, and local build instructions.
# NVIDIA GPU (default)
docker run --gpus all -p 3030:3030 \
-v neuroncite-data:/data/Documents/NeuronCite \
ghcr.io/ff-tec/neuroncite:latest
# AMD ROCm
docker run --device=/dev/kfd --device=/dev/dri -p 3030:3030 \
-v neuroncite-data:/data/Documents/NeuronCite \
ghcr.io/ff-tec/neuroncite:latest-rocm
# CPU only
docker run -p 3030:3030 \
-v neuroncite-data:/data/Documents/NeuronCite \
ghcr.io/ff-tec/neuroncite:latest-cpu
| Variant | Base Image | GPU | Tag |
|---|---|---|---|
| NVIDIA | CUDA 12.4 + cuDNN, Ubuntu 22.04 | CUDA | latest / <version>-nvidia |
| ROCm | ROCm 6.4, Ubuntu 22.04 | ROCm | latest-rocm / <version>-rocm |
| CPU | Ubuntu 22.04, x86_64 | None | latest-cpu / <version>-cpu |
| CPU ARM64 | Ubuntu 22.04, ARM64 | None | latest-cpu-arm64 / <version>-cpu-arm64 |
From Source
Prerequisites: Rust 1.88+ (stable), Node.js 22.22+ (or 24.15+ / 26+), npm.
git clone https://github.com/FF-TEC/NeuronCite.git
cd neuroncite
# Build the SolidJS frontend
cd crates/neuroncite-web/frontend && npm ci && npx vite build && cd ../../..
# Build the Rust binary (all features enabled by default)
cargo build --release -p neuroncite
The binary is at target/release/neuroncite (Linux/macOS) or
target/release/neuroncite.exe (Windows).
For a server-only build without native GUI:
cargo build --release -p neuroncite \
--no-default-features \
--features backend-ort,web,mcp,pdfium,ocr
Python Client
# From PyPI (once published):
pip install neuroncite
# From source:
pip install ./clients/python
Requires Python 3.10+. See clients/python/README.md for the full API reference.
Usage
Web UI
neuroncite
# or explicitly:
neuroncite web --port 3030
Starts the API server and opens the SolidJS web frontend in a native window
(WebView2 on Windows, WebKit on macOS/Linux). Falls back to the default browser
if the native window cannot be created. The frontend is served at
http://localhost:3030.
Headless Server
neuroncite serve --port 3030 --bind 0.0.0.0
Runs the REST API without opening a browser or native window. Suitable for remote servers, Docker, and automation.
CLI Indexing
neuroncite index \
--directory /path/to/pdfs \
--model "BAAI/bge-small-en-v1.5" \
--strategy word \
--chunk-size 300 \
--overlap 50
Indexes a directory of PDFs without running a persistent server. Embedding models are downloaded from HuggingFace on first use.
CLI Search
neuroncite search \
--directory /path \
--session-id 1 \
--query "heteroskedasticity-consistent covariance matrix" \
--hybrid \
--rerank
Executes a single search query against an existing session. Results are printed
as JSON (default) or plain text (--format text).
MCP Server (Claude Code & Claude Desktop App)
neuroncite mcp install # registers in Claude Code settings (default)
neuroncite mcp install --target claude-desktop # registers in Claude Desktop App settings
neuroncite mcp uninstall # removes registration from Claude Code settings
neuroncite mcp status # shows current registration status
neuroncite mcp serve # starts stdio JSON-RPC server
All Commands
| Command | Description |
|---|---|
neuroncite / neuroncite web |
Launch web UI in a native window (browser fallback) |
neuroncite serve |
Headless API server |
neuroncite index |
Index a directory of PDFs |
neuroncite search |
Execute search queries |
neuroncite annotate |
Annotate PDFs from CSV/JSON |
neuroncite doctor |
Check runtime dependencies (Tesseract, pdfium, GPU) |
neuroncite sessions |
List index sessions in a database |
neuroncite export |
Export results as Markdown, BibTeX, CSL-JSON, RIS, or plain text |
neuroncite models list|info|download|verify|system |
Manage embedding models and check system capabilities |
neuroncite mcp install|uninstall|serve|status |
Register, remove, run, and check MCP server |
neuroncite version |
Print version, build features, and Git commit hash |
Architecture
PDFs / HTML pages
|
v
Extract text
(pdf-extract / pdfium / Tesseract OCR / readability)
|
v
Chunk text
(page / word-window / token-window / sentence)
|
v
Embed chunks
(ONNX Runtime with CUDA / DirectML / CoreML / CPU)
|
v
Store vectors + metadata
(HNSW index + SQLite FTS5)
|
v
Hybrid search
(vector kNN + BM25 keyword + RRF fusion + optional reranking)
|
v
Ranked results with citations, page numbers, and scores
Cargo Workspace (16 Crates)
| Layer | Crate | Responsibility |
|---|---|---|
| Binary | neuroncite |
Entry point, CLI argument parsing (clap), execution mode dispatch |
| Presentation | neuroncite-web |
SolidJS frontend (rust-embed), native GUI (tao/wry), SSE broadcast |
| Presentation | neuroncite-api |
REST API server (Axum), 34 endpoints, OpenAPI, bearer auth, rate limiting, SSE |
| Presentation | neuroncite-mcp |
MCP server (43 tools, JSON-RPC 2.0 over stdio) |
| Domain | neuroncite-pipeline |
Background job executor, GPU worker with priority channels, two-phase indexing |
| Domain | neuroncite-search |
Hybrid search, BM25, Reciprocal Rank Fusion, deduplication, reranking |
| Domain | neuroncite-citation |
LaTeX/BibTeX parsing, batch claim extraction, LLM-driven verification |
| Domain | neuroncite-annotate |
PDF annotation with 5-stage text matching pipeline |
| Core | neuroncite-store |
SQLite storage (r2d2 pool), HNSW index, FTS5 full-text search, workflow tracking |
| Core | neuroncite-embed |
Dense embeddings via ONNX Runtime, model download and management, cross-encoder reranking |
| Core | neuroncite-pdf |
PDF discovery and text extraction (pdf-extract, pdfium, Tesseract OCR) |
| Core | neuroncite-html |
HTML fetching, readability extraction, caching, BFS crawling with SSRF protection |
| Core | neuroncite-chunk |
Text chunking strategies (page, word, token, sentence) |
| Core | neuroncite-llm |
LLM abstraction layer, Ollama HTTP client |
| Foundation | neuroncite-core |
Shared types, trait definitions, configuration, error types (zero internal dependencies) |
| Dev | neuroncite-testgen |
Test data generation and property-based testing utilities |
Feature Flags
| Flag | Purpose | Default |
|---|---|---|
backend-ort |
ONNX Runtime embedding backend with CUDA support | Enabled |
web |
SolidJS frontend embedded via rust-embed | Enabled |
gui |
Native window via tao/wry (requires web) |
Enabled |
mcp |
Model Context Protocol server for AI agent integration | Enabled |
pdfium |
Multi-column PDF extraction backend | Enabled |
ocr |
Tesseract OCR fallback for scanned pages (requires pdfium) |
Enabled |
For the full architecture document, see docs/architecture.pdf.
Hardware Requirements
| Component | Minimum | Recommended |
|---|---|---|
| RAM | 4 GB | 8 GB+ |
| CPU | 2 cores | 4+ cores |
| GPU | Not required | NVIDIA (CUDA 12.4+) or AMD (ROCm 6.4+) |
| Disk | 200 MB (binary) + model size | 2 GB+ for large collections |
Embedding model sizes range from 50 MB (bge-small, 33M parameters) to 1 GB (large models, 335M parameters). GPU acceleration is optional -- the CPU execution provider works on all platforms. The application runs entirely offline after the initial model download.
Documentation
- neuroncite.com -- Project website with feature overview, FAQ, and roadmap
- REST API and CLI Reference -- Full endpoint documentation, Python client guide, MCP setup
- Pricing and Licensing -- AGPL-3.0 (free) and Enterprise license comparison
- Architecture Document -- Full system design (16 crates, data flow, design decisions)
- Docker Deployment -- Image variants, compose profiles, environment variables, local builds
- Python Client -- Full API reference with 30+ typed methods
- Tools and Scripts -- CI validators, code generators, developer utilities
- Commercial License -- Dual licensing details and use-case matrix
Contributing
Contributions are welcome. See CONTRIBUTING.md for development setup, code style guidelines, testing instructions, and the pull request process.
Please read the Code of Conduct before participating.
Security
To report a vulnerability, see SECURITY.md for the disclosure process and response timeline.
License
NeuronCite is dual-licensed:
- AGPL-3.0-only -- free copyleft license for any use, including commercial. Requires source disclosure when distributing or providing network access. See LICENSE.
- Commercial license for proprietary products, SaaS deployments, and redistribution without AGPL source-disclosure obligations. See COMMERCIAL_LICENSE.md.
For commercial licensing inquiries: licensing@neuroncite.com
Copyright (C) 2026 Felix Fritz. All rights reserved.
NeuronCite MCP 질문
NeuronCite를 사용하려면 인터넷 연결이 필요한가요?
아니요, 모델과 종속성을 처음 다운로드한 후에는 폐쇄망 환경에서도 완전히 오프라인으로 작동할 수 있습니다.
인용 검증은 어떻게 작동하나요?
LaTeX 파일을 파싱하고 BibTeX를 기준으로 인용을 해결하며, Ollama를 통해 로컬 LLM을 사용하여 인덱싱된 PDF와 대조해 주장을 검증합니다.
GPU를 사용할 수 있나요?
네, CUDA, DirectML, CoreML, ROCm 기반의 ONNX Runtime을 통한 GPU 가속을 지원합니다.
어떤 검색 알고리즘을 사용하나요?
HNSW 벡터 유사도, BM25 키워드 매칭, Reciprocal Rank Fusion을 결합한 하이브리드 방식을 사용하며, 선택적으로 cross-encoder 리랭킹을 지원합니다.