Redis Cloud APISAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Model Context Protocol (MCP) is a standardized protocol for managing context between large language models (LLMs) and external systems. This repository provides an MCP Server for Redis Cloud's API, allowing you to manage your Redis Cloud resources using natural language.
This lets you use Claude Desktop, or any MCP Client, to use natural language to accomplish things on your Redis Cloud account, e.g.:
- "Create a new Redis database in AWS"
- "What are my current subscriptions?"
- "Help me choose the right Redis database for my e-commerce application"
Features
Account Management
get_current_account: Get details about your current Redis Cloud accountget_current_payment_methods: List all payment methods configured for your account
Subscription Management
Pro Subscriptions
get_pro_subscriptions: List all Pro subscriptions in your accountcreate_pro_subscription: Create a new Pro subscription with advanced configuration options- Supports multi-cloud deployment
- Configure memory, persistence, and modules
- Set up Active-Active deployments
- Custom networking configuration
Essential Subscriptions
get_essential_subscriptions: List all Essential subscriptions (paginated)get_essential_subscription_by_id: Get detailed information about a specific Essential subscriptioncreate_essential_subscription: Create a new Essential subscriptiondelete_essential_subscription: Delete an Essential subscription
Database Capabilities
get_database_modules: List all available database modules (capabilities) supported in your account- Redis modules
- Database features
- Performance options
Cloud Provider Management
get_pro_plans_regions: Get available regions across cloud providers- AWS regions
- GCP regions
- Networking options
- Availability zones
Plans and Pricing
get_essentials_plans: List available Essential subscription plans (paginated)- Supp
adb9549c202aOBSERVED · 2026-10-08Connect
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-redis-cloud --env API_KEY=${API_KEY} --env SECRET_KEY=${SECRET_KEY} -- npx -y [email protected]{
"mcpServers": {
"mcp-redis-cloud": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"API_KEY": "${API_KEY}",
"SECRET_KEY": "${SECRET_KEY}"
}
}
}
}Exposed tools (18)
13 read · 4 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 |
|---|---|---|
create-essential-database | write | Create a new essential database inside the specified subscription ID. Returns a TASK ID that can be used to track the status of the database creation. |
create-essential-subscription | write | Create a new essential subscription. Returns a TASK ID that can be used to track the status of the subscription creation |
create-pro-database | write | Create a new database inside the specified subscription ID. Returns a TASK ID that can be used to track the status of the database creation |
create-pro-subscription | write | Create a new pro subscription. Returns a TASK ID that can be used to track the status of the subscription creation. |
delete-essential-subscription | destructive | Delete an essential subscription by ID |
get-current-account | read | Get the current Cloud Redis account |
get-current-payment-methods | read | Get the current payment methods for the current Cloud Redis account |
get-database-modules | read | Lookup list of database modules supported in current account (support may differ based on subscription and database settings). These modules are also called capabilities. |
get-essential-databases | read | Get the essential databases for the provided subscription Id |
get-essential-subscription-by-id | read | Get an essential subscription by ID for the current Cloud Redis account |
get-essential-subscriptions | read | Get the essential subscriptions for the current Cloud Redis account. |
get-essentials-plans | read | Get the available plans for essential subscriptions. Always ask for which provider the plans are want to be retrieved. |
get-pro-databases | read | Get the pro databases for the provided subscription Id |
get-pro-plans-regions | read | Lookup list of regions for cloud provider. These regions include the providers too. |
get-pro-subscription | read | Get pro subscription by ID. The payload must match the input schema. |
get-pro-subscriptions | read | Get the pro subscriptions for the current Cloud Redis account |
get-task-by-id | read | Get a task by ID for the current Cloud Redis account |
get-tasks | read | Get the current tasks for the current Cloud Redis account |
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 (6 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
delete-essential-subscription
.prettierrc.json
import { log } from "../../../utils/helpers.js";import { getArgValue } from "../../../utils/args.js";import { ToolHandlers } from "../../utils/types.js";import { AccountService } from "../../clients/generated/index.js";import { emptySchema } from "../../utils/common/schemas.js";@hey-api/client-fetch, @modelcontextprotocol/sdk, zod, @eslint/js, @hey-api/openapi-ts, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser
Gates applied: no_behavioural_pass.
adb9549c202afull audit observations/trust-audit/mcp-server/redis__redis-cloud-api.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 |
|---|---|---|---|---|---|
| 2026-10-08 | adb9549c202a | SAFE | B | 89 | first audit |
Questions
What tools does Redis Cloud API expose?
18 in total: 13 read-only, 4 that write, and 1 that can delete or overwrite (delete-essential-subscription). Every one is listed on this page with its risk.
Is Redis Cloud API 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 Cloud API need?
It reads API_KEY and SECRET_KEY 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 does Redis Cloud API run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-redis-cloud at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (adb9549c202a), read on 2026-10-08. The repository is watched and re-audited when it changes.