Back to Home
manish6007 icon

mcp_servers

by manish6007

Overview

A combined Model Context Protocol (MCP) server that provides tools for querying Amazon Redshift databases and performing vector-based knowledge base searches.

Installation

Run Command
python -m combined_mcp_server.main

Environment Variables

  • AWS_REGION
  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY
  • REDSHIFT_CLUSTER_ID
  • REDSHIFT_DATABASE
  • REDSHIFT_HOST
  • REDSHIFT_RESULTS_BUCKET
  • KNOWLEDGEBASE_S3_BUCKET
  • POSTGRES_SECRET_NAME
  • POSTGRES_HOST
  • POSTGRES_DATABASE
  • POSTGRES_USER
  • POSTGRES_PASSWORD
  • BEDROCK_EMBEDDING_MODEL
  • MCP_TRANSPORT

Security Notes

The `run_query` tool directly accepts raw SQL as input, which is a significant SQL injection vulnerability if exposed to untrusted user input or if an LLM generates malicious SQL. The `list_tables` and `describe_table` tools use f-strings to embed `schema` and `table` names directly into SQL queries, also creating SQL injection opportunities if these parameters are not rigorously sanitized by the calling agent or application. The `query_vectorstore` tool similarly uses f-strings for the `query` parameter within `plainto_tsquery`, which could lead to unexpected behavior or resource exhaustion with malicious input. While intended for LLM agents, these patterns pose a high risk without strict input validation or sandboxing.

Similar Servers

Stats

Interest Score0
Security Score4
Cost ClassHigh
Avg Tokens400
Stars0
Forks0
Last Update2026-01-18

Tags

MCPRedshiftKnowledgebaseVector StoreAWSLLM ToolsBedrock