NeuronDB
by pgElephant
Overview
The NeuronMCP server acts as a Model Context Protocol (MCP) gateway, enabling MCP-compatible clients (like Claude Desktop) to interact with the NeuronDB PostgreSQL extension for vector search, machine learning, RAG pipelines, and agent runtime capabilities.
Installation
docker run -i --rm -e NEURONDB_HOST=localhost -e NEURONDB_PORT=5433 -e NEURONDB_DATABASE=neurondb -e NEURONDB_USER=neurondb -e NEURONDB_PASSWORD=neurondb neurondb-mcp:latestEnvironment Variables
- NEURONDB_HOST
- NEURONDB_PORT
- NEURONDB_DATABASE
- NEURONDB_USER
- NEURONDB_PASSWORD
- NEURONDB_MCP_CONFIG
Security Notes
The C-based PostgreSQL extension code (`NeuronDB/src/search/sparse_search.c`, `hybrid_search.c`, `semantic_keyword_search.c`, `multi_vector_search.c`, `faceted_vector_search.c`, `temporal_vector_search.c`, `diverse_vector_search.c`) constructs SQL queries by directly concatenating user-provided table and column names (`tbl_str`, `col_str`, `facet_str`, `ts_str`) into the query string using `%s` in `appendStringInfo`. This is a classic SQL injection vulnerability, as malicious input in these parameters could alter the SQL query. For instance, a user could supply a table name like `mytable; DROP TABLE important_data;` leading to data loss or unauthorized access. While the Node.js/TypeScript layer of NeuronMCP generally uses parameterized queries and `escapeIdentifier` for dynamic SQL, the underlying C extension functions contain this critical flaw. The `PluginManager` allows loading external plugins, which could be a risk if not sourced from trusted origins.
Similar Servers
mcp-server-neon
Enables natural language interaction with Neon Postgres databases, facilitating database management, migrations, and query optimization via an LLM agent.
meilisearch-mcp
Connects LLMs (like Claude and OpenAI agents) to Meilisearch, enabling natural language control for managing search indices and performing searches.
cratedb-mcp
The CrateDB MCP Server enables natural-language Text-to-SQL querying, cluster health monitoring, and documentation retrieval for CrateDB database clusters, acting as a bridge for AI assistants.
dx-mcp-server
Empowers AI applications to interact with and query a user-provided Postgres database via the Model Context Protocol (MCP).