Redis
Give an agent access to Redis through the ilert MCP connector, and the two gates on reading key values.
Required permissions
list_databases
read
List all Redis databases. Useful for discovering which database numbers hold data.
scan_keys
read
List keys in a database matching a pattern. Useful for discovering available keys and their naming patterns.
get_key_info
read
Get detailed information about a key: type, TTL, size, and encoding. Helps understand key structure without reading its contents.
get_key_values
read
Read the values of multiple keys (up to 1 KB each). Returns the actual stored data.
get_metrics
read
Get Redis metrics including server info, memory usage, stats, clients, persistence, replication, CPU, and keyspace.
get_info
read
Get the raw output of the Redis INFO command, for cases where the parsed metrics are not enough.
get_key_values returns the actual values stored in Redis, which may contain sensitive data. It is treated as a sensitive tool and is gated twice, both off by default:
REDIS_ENABLE_SENSITIVE_TOOLS=trueon the connector you deploy — without it the connector refuses the request, whatever the agent asks forthe
get_key_valuestool enabled on the agent's Tools tab
Even with both enabled, a call reads at most 20 keys and each value is truncated to 1 KB. Keys holding a non-string type, and binary values that are not valid text, are reported as such rather than returned.
Deploy the ilert MCP connector
ilert does not connect to your Redis instance directly. The Redis MCP server calls the ilert MCP connector, a service you deploy in your own network and expose over a public HTTPS URL. Deployment, the auth token and all configuration options are on its own page:
Enable Redis on the connector with these variables:
REDIS_ENABLED=true
REDIS_HOST=redis.internal
REDIS_PORT=6379
REDIS_PASSWORD=your_password
REDIS_ENABLE_SENSITIVE_TOOLS=falseLeave REDIS_PASSWORD unset if no password is configured. There is no database-number setting — the agent selects the Redis database per request.
Keep REDIS_ENABLE_SENSITIVE_TOOLS at false unless you want the agent to read key contents — see the note above. Everything else, including key metadata and server metrics, works without it.
Connect Redis with agent
To connect Redis with your AI SRE agent:
Navigate to Agents in the ilert navigation menu
Open the agent detail view for the agent you want to configure
Go to the Tools tab
Under the ilert hosted MCP servers section, locate the Redis card
Click Connect on the Redis card
In the connection dialog that appears:
Select connector: Choose "Create new connector" (or select an existing connector if you have one)
Type: Select Bearer Token from the dropdown
Secret name: Enter a name for your connector (e.g., "Redis Production" or "Redis Main")
Secret value: Enter the
AUTH_TOKENvalue from your connector deploymentHost URL: Enter the public URL where your connector is reachable (e.g.,
https://ilert-mcp-connector.example.com)
Click Connect to complete the connection
After connecting, you can enable or disable specific tools needed for alert investigation, such as:
list_databases- List all Redis databasesscan_keys- List keys in a database matching a patternget_key_info- Get a key's type, TTL, size, and encodingget_key_values- Read the values of multiple keys (sensitive, disabled by default, also needsREDIS_ENABLE_SENSITIVE_TOOLSon the connector)get_metrics- Get server info, memory, stats, clients, persistence, replication, CPU, and keyspaceget_info- Get raw RedisINFOcommand output
The Redis integration is now connected and ready to use for root cause analysis.
Last updated
Was this helpful?