Redis ConnectorSAFE
MCP server to interact with Redis Server, AWS Memory DB, etc for caching or other use-cases where in-memory and key-value based storage is appropriate
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/prajwalnayak7-mcp-server-redis)
Usage
The structure is as follows:
mcp-server-redis/ ├── src/ │ ├── __init__.py │ ├── main.py # Main entry point │ ├── config.py # Configuration │ ├── connection.py # Redis connection management │ ├── resources/ # Resource implementations │ │ ├── __init__.py │ │ ├── status.py # Connection status resources │ │ └── keys.py # Key-related resources │ └── tools/ # Tool implementations │ ├── __init__.py │ ├── basic.py # Basic Redis operations │ ├── lists.py # List operations │ ├── hashes.py # Hash operations │ ├── sets.py # Set operations │ └── pubsub.py # Pub/Sub operations ├── tests/ # Test directory │ └── __init__.py ├── README.md └── pyproject.toml
To use this server, you'll need to:
Install the required dependencies:
[If not already installed] https://docs.astral.sh/uv/
uv venv
source .venv/bin/activate
uv sync
Refer to the .env.example file to configure your Redis connection by adding the appropriate variables.
Run the server:
python src/server.py
Capabilities of this server
Resources:
- redis://status - Current connection status
- redis://info - Redis server information
- redis://keys/{pattern} - List keys matching a pattern
Tools:
- Basic operations:
- get_value - Get a value
- set_value - Set a value with optional expiry
- delete_key - Delete a key
- increment - Increment a numeric value
- List operations:
- list_push - Push values to a list
- list_range - Get range of list values
- Hash operations:
- hash_set - Set hash fields
- hash_get - Get hash fields
- Set operations:
- set_add - Add to a set
- set_members - Get set members
- Pub/Sub:
- publish_message - Publish a message
df0d0fb37d0bOBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-redis --env REDIS_PASSWORD=${REDIS_PASSWORD} -- uvx mcp-server-redis{
"mcpServers": {
"mcp-server-redis": {
"command": "uvx",
"args": [
"mcp-server-redis"
],
"env": {
"REDIS_PASSWORD": "${REDIS_PASSWORD}"
}
}
}
}Exposed tools (10)
3 read · 6 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
delete_key | destructive | Delete a Redis key |
get_value | read | Get value for a Redis key |
hash_get | read | Get hash fields |
hash_set | write | Set multiple hash fields |
list_push | write | Push values to a Redis list |
list_range | read | Get a range of values from a Redis list |
publish_message | write | Publish a message to a Redis channel |
set_add | write | Add members to a Redis set |
set_members | write | Get all members of a Redis set |
set_value | write | Set value for a Redis key |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
delete_key
Gates applied: no_behavioural_pass.
df0d0fb37d0bfull audit observations/trust-audit/mcp-server/prajwalnayak7__redis-connector.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | df0d0fb37d0b | SAFE | B | 89 | first audit |
Questions
What is the Redis Connector MCP server?
MCP server to interact with Redis Server, AWS Memory DB, etc for caching or other use-cases where in-memory and key-value based storage is appropriate
What tools does Redis Connector expose?
10 in total: 3 read-only, 6 that write, and 1 that can delete or overwrite (delete_key). Every one is listed on this page with its risk.
Is Redis Connector safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Redis Connector need?
It reads REDIS_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (df0d0fb37d0b), read on 2026-10-09. The repository is watched and re-audited when it changes.