DocumentationNeuronMCP Documentation
Documentation Branch: You are viewing documentation for the main branch (3.0.0-devel). Select a branch to view its documentation:

NeuronMCP Tool Catalog

Overview

NeuronMCP provides 100+ tools organized into categories. This catalog lists all available tools with descriptions and parameters.

Total Tools: 100+ (27 PostgreSQL + 70+ NeuronDB)

Vector Operations (50+ Tools)

Vector Search (8 tools)

  • vector_search - Vector similarity search with configurable distance metrics
  • vector_search_l2 - L2 (Euclidean) distance search
  • vector_search_cosine - Cosine similarity search
  • vector_search_inner_product - Inner product search
  • vector_similarity - Calculate vector similarity
  • vector_arithmetic - Vector arithmetic operations
  • vector_distance - Compute distance between vectors
  • vector_similarity_unified - Unified vector similarity with multiple metrics

Vector Quantization (7 tools)

  • vector_quantize - Quantize/dequantize vectors
  • quantization_analyze - Analyze quantization impact

Supported Quantization Types: int8, fp16, binary, uint8, ternary, int4

Embeddings (8 tools)

  • generate_embedding - Generate text embedding
  • batch_embedding - Batch generate embeddings
  • embed_image - Generate image embedding
  • embed_multimodal - Multimodal embedding (text + image)
  • embed_cached - Use cached embedding if available
  • configure_embedding_model - Configure embedding model
  • get_embedding_model_config - Get model configuration
  • list_embedding_model_configs - List all model configurations

Hybrid Search (7 tools)

  • hybrid_search - Semantic + lexical search
  • reciprocal_rank_fusion - RRF on multiple rankings
  • semantic_keyword_search - Semantic + keyword search
  • multi_vector_search - Multiple embeddings per document
  • faceted_vector_search - Category-aware retrieval
  • temporal_vector_search - Time-decay relevance scoring
  • diverse_vector_search - Diverse result set

Index Management (6 tools)

  • create_hnsw_index - Create HNSW index
  • create_ivf_index - Create IVF index
  • get_index_status - Monitor index status and statistics
  • drop_index - Remove indexes with cleanup
  • tune_hnsw_index - Tune HNSW index parameters
  • tune_ivf_index - Tune IVF index parameters

ML Tools

Training & Prediction (8 tools)

  • train_model - Train ML model with 52+ algorithms
  • predict - Single prediction
  • predict_batch - Batch prediction
  • evaluate_model - Evaluate model
  • list_models - List all models
  • get_model_info - Get model details
  • delete_model - Delete model
  • export_model - Export model

Supported Algorithms

  • Classification: logistic, random_forest, svm, knn, decision_tree, naive_bayes
  • Regression: linear_regression, ridge, lasso
  • Clustering: kmeans, gmm, dbscan, hierarchical

Analytics (7 tools)

  • analyze_data - General data analysis
  • cluster_data - Clustering analysis
  • reduce_dimensionality - Dimensionality reduction (PCA)
  • detect_outliers - Outlier detection
  • quality_metrics - Quality metrics (Recall@K, Precision@K, etc.)
  • detect_drift - Data drift detection
  • discover_topics - Topic discovery

ONNX (4 tools)

  • import_onnx_model - Import ONNX model
  • export_onnx_model - Export ONNX model
  • get_onnx_model_info - Get ONNX model info
  • predict_onnx - Predict with ONNX model

AutoML (1 tool)

  • automl - Automated ML pipeline

RAG & Reranking Tools

RAG Pipeline

  • process_documents - Process and chunk documents
  • retrieve_context - Semantic search with reranking
  • generate_response - Generate responses with LLM

Reranking (6 tools)

  • rerank_cross_encoder - Cross-encoder reranking
  • rerank_llm - LLM-powered reranking
  • rerank_cohere - Cohere reranking API
  • rerank_colbert - ColBERT reranking
  • rerank_ltr - Learning-to-rank reranking
  • rerank_ensemble - Ensemble reranking

PostgreSQL Administration (27 Tools)

Server Information (8 tools)

  • get_server_version - Get PostgreSQL version
  • get_database_stats - Get database statistics
  • list_databases - List all databases
  • get_connections - Get connection information
  • get_locks - Get lock information
  • get_replication_status - Get replication status
  • get_settings - Get PostgreSQL settings
  • list_extensions - List installed extensions

Database Object Management (8 tools)

  • list_tables - List tables
  • list_indexes - List indexes
  • list_schemas - List schemas
  • list_views - List views
  • list_sequences - List sequences
  • list_functions - List functions
  • list_triggers - List triggers
  • list_constraints - List constraints

User and Role Management (9 tools)

  • create_user, alter_user, drop_user - User management
  • create_role, alter_role, drop_role - Role management
  • grant_permission, revoke_permission - Permission management
  • grant_role, revoke_role - Role assignment

Performance and Statistics (4 tools)

  • get_table_stats - Get table statistics
  • get_index_stats - Get index statistics
  • get_active_queries - Get active queries
  • get_wait_events - Get wait events

Size and Storage (4 tools)

  • get_table_size - Get table size
  • get_index_size - Get index size
  • analyze_bloat - Analyze table bloat
  • get_vacuum_stats - Get vacuum statistics

Administration (16 tools)

  • explain_query, explain_analyze - Query analysis
  • vacuum_table, analyze_table, reindex - Maintenance operations
  • terminate_query, kill_query - Query management
  • set_config, reload_config - Configuration management
  • And more administration tools

Dataset Loading Tools

  • load_huggingface_dataset - Load datasets from HuggingFace Hub
  • load_url_dataset - Load CSV, JSON, Parquet from URLs
  • load_s3_dataset - Load datasets from S3 buckets
  • load_github_dataset - Load datasets from GitHub repositories
  • load_local_dataset - Load datasets from local files
  • auto_embed_dataset - Automatic embedding generation during loading