mcp-redis
Verified Safeby redis
Overview
Provides a natural language interface for AI agents to efficiently manage, search, and interact with structured and unstructured data in Redis.
Installation
uvx --from redis-mcp-server@latest redis-mcp-server --url "redis://localhost:6379/0"Environment Variables
- REDIS_URL
- REDIS_HOST
- REDIS_PORT
- REDIS_USERNAME
- REDIS_PWD
- REDIS_SSL
- REDIS_SSL_CA_PATH
- REDIS_SSL_KEYFILE
- REDIS_SSL_CERTFILE
- REDIS_SSL_CERT_REQS
- REDIS_SSL_CA_CERTS
- REDIS_CLUSTER_MODE
- REDIS_DB
- REDIS_ENTRAID_AUTH_FLOW
- REDIS_ENTRAID_CLIENT_ID
- REDIS_ENTRAID_CLIENT_SECRET
- REDIS_ENTRAID_TENANT_ID
- REDIS_ENTRAID_IDENTITY_TYPE
- REDIS_ENTRAID_USER_ASSIGNED_CLIENT_ID
- REDIS_ENTRAID_SCOPES
- REDIS_ENTRAID_RESOURCE
- MCP_DOCS_SEARCH_URL
- MCP_REDIS_LOG_LEVEL
Security Notes
The server primarily uses environment variables for sensitive configurations like Redis credentials and EntraID authentication details, reducing the risk of hardcoded secrets. It exposes direct Redis commands as MCP tools; while Redis commands themselves can be powerful, the server does not appear to directly execute arbitrary user-provided code (e.g., no 'eval'). Input parsing, like in 'json_set', is handled safely. The 'search_redis_documents' tool performs an HTTP request to a configurable URL, which could be a risk if the URL is misconfigured by the user, but this is an external dependency rather than an inherent vulnerability in the server's core logic. The code appears well-structured and does not contain obvious malicious patterns or obfuscation.
Similar Servers
Context-Engine
A Retrieval-Augmented Generation (RAG) stack for codebases, enabling context-aware AI agents for developers and IDEs through unified code indexing, hybrid search, and local LLM integration.
mcp-server-datahub
The DataHub MCP Server enables AI agents to discover, explore lineage, understand usage, and generate SQL queries for data assets within a DataHub ecosystem.
Web-Algebra
Translates natural language instructions into RDF operations for loading, querying, and writing Linked Data, consumable via executable JSON or as MCP tools for AI agents.
mcp-structured-memory
Provides structured, domain-specific memory management through markdown files for ongoing projects, allowing AI to accumulate and organize valuable context over time.