Timeweb Cloud MCP server with 245 tools
Timeweb Cloud MCP Server
A broad Timeweb Cloud MCP server: 245 tools across servers, Kubernetes, databases, S3, domains, mail and billing
High risk
We rate an entry high when the tool writes to external systems, handles money, production databases or secrets, or runs arbitrary commands. The CLI installs it only with your consent.
Why this level
- It covers creating and deleting servers, databases, Kubernetes clusters and domains in a live Timeweb Cloud account
- The huge tool count increases the risk that an agent touches the wrong service on an unclear request
Install
Manual install
npx timeweb-mcpRunning the server via npx with the TIMEWEB_TOKEN variable.
This is third-party code. Review the repository files before installing.
What it does
The server registers 245 tools, 6 MCP resources and 2 prompts covering almost all of Timeweb Cloud's infrastructure: App Platform apps and VCS providers, cloud and dedicated servers, disks, backups and images, projects, VPC, floating IPs, network disks and Firewall, Kubernetes, load balancers and container registries, databases, S3 storage, domains, DNS and mail, SSH and API keys, Timeweb AI agents, and account, billing, plan and location data. The project generates and normalizes code from Timeweb Cloud's official OpenAPI spec, which declares 341 operations across 23 groups, but the README honestly states that not every operation is already a separate MCP tool.
Who it is for. For DevOps engineers who want the broadest possible Timeweb Cloud API coverage in one server, rather than a set of narrow tools.
Good fit when
- You need coverage of nearly all Timeweb Cloud services: Kubernetes, databases, S3, mail, not just servers and DNS
- You need MCP resources like allowed_presets or database_presets to guide the agent
- An actively experimental development status is acceptable
Not a fit when
- You need a guarantee that a specific OpenAPI operation is already an MCP tool: check the list against src/tools/index.ts
- You need a stable API with no changes between versions: the project explicitly warns it develops independently of Timeweb Cloud
Example request
Show all databases in my Timeweb Cloud project and their current presetsLimitations
The project is in active experimental development, and the README explicitly warns that some API features may be incompletely implemented or may change between versions. The token variable is named TIMEWEB_TOKEN, and the README separately warns not to confuse it with TIMEWEB_CLOUD_TOKEN used by other Timeweb tools. Given the huge scope (245 tools), there is a real risk of accidentally touching the wrong service with an unclear agent request.
How to disable. Remove the server from your MCP client configuration and revoke the Timeweb Cloud API token if needed.
MCP
- Transport
- stdio
- Authentication
- API key
| Environment variables | |
|---|---|
| TIMEWEB_TOKEN required, secret | The Timeweb Cloud API token from the API and Terraform section. |
Security check
- It covers creating and deleting servers, databases, Kubernetes clusters and domains in a live Timeweb Cloud account
- The huge tool count increases the risk that an agent touches the wrong service on an unclear request
README in short
The Russian README gives a table of tool, resource and prompt counts, lists the covered Timeweb Cloud services, and honestly notes the active experimental status with possible API changes between versions. It states the requirements (Node.js 20+, npm, an stdio-capable client) and how to get the API token in the Timeweb Cloud panel, with an explicit warning not to confuse the TIMEWEB_TOKEN variable with TIMEWEB_CLOUD_TOKEN.
FAQ
Are all 341 operations from the Timeweb Cloud OpenAPI spec implemented?
No, the README states this does not mean every operation is already a separate MCP tool; the current list is in src/tools/index.ts.
How is TIMEWEB_TOKEN different from TIMEWEB_CLOUD_TOKEN?
They are different variables: the README warns not to confuse them, since some other Timeweb tools use the second name.
Related
An MCP server built into the Netdata agent: metrics, logs, alerts and live process, service and container data for an AI assistant
GitHub's official MCP server: code, issues, pull requests, Actions and security alerts straight from the agent
Agent Skills for Google products
Agent Skills for Google products and technologies
Official Google skill collection for working with Google Cloud, BigQuery, GKE, ads and analytics from an agent
AWS's official MCP server suite: docs, IaC, containers, serverless, databases, cost and monitoring