Skip to content
MCP server

Sevalla

Official Sevalla MCP server to deploy, debug and manage apps, databases and sites

Pricing
Free trial
Platforms
API, Web
Runs
Remotely
Version
2.0.0
Listing updated
3 days ago

About Sevalla

Sevalla is an MCP server for cloud and infrastructure. It runs as a hosted remote server, so there is nothing to install locally.

This remote server gives agents such as Claude Code, Cursor and Codex hands on the Sevalla company account. The README counts 27 tools: 22 purpose-built for everyday jobs like deploying, reading logs and metrics, environment variables, scaling and domains, and 5 generic tools that reach the rest of the Sevalla API.

The generic tools (search, read, create, update, delete) only accept operation IDs from a reviewed table generated from the Sevalla API v3 spec, so the server rather than the model picks the HTTP method and path. Every tool carries read-only, destructive, idempotent and open-world hints so clients can run reads freely and confirm destructive calls.

Sign-in is by OAuth through the Sevalla account. Sevalla's site pitches project-level isolation and scoped permissions so teams can limit where agents act, and logs and metrics access for investigating failed deploys. Sevalla itself bills for resources used rather than plans.

Install

Run in a terminal

claude mcp add --transport http mcp https://mcp.sevalla.com/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.sevalla.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.sevalla.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.sevalla.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.sevalla.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.sevalla.com/mcp"
    }
  }
}

Tools this server provides (27)

Taken from the project documentation; the running server may differ.

list_services
Lists services
get_application
Gets an application
get_static_site
Gets a static site
get_database
Gets a database
get_platform_options
Lists platform options
search_sevalla_docs
Searches Sevalla documentation
list_deployments
Lists deployments
get_deployment
Gets a deployment
get_deployment_logs
Reads deployment logs
trigger_deployment
Triggers a deployment
rollback_deployment
Rolls back a deployment
search_runtime_logs
Searches runtime logs
search_access_logs
Searches access logs
get_metrics
Fetches metrics
list_environment_variables
Lists environment variables
set_environment_variables
Sets environment variables
delete_environment_variables
Deletes environment variables
scale_process
Scales a process
add_domain
Adds a domain
create_application
Creates an application
create_static_site
Creates a static site
create_database
Creates a database
sevalla_api_search
Searches the generic API operations
sevalla_api_read
Reads via a reviewed API operation
sevalla_api_create
Creates via a reviewed API operation
sevalla_api_update
Updates via a reviewed API operation
sevalla_api_delete
Deletes via a reviewed API operation

What it does

Deploy and roll back
Triggers deployments, reads their logs and rolls a deployment back.
Logs and metrics
Searches runtime and access logs and fetches metrics.
Configuration control
Lists, sets and deletes environment variables, scales processes and adds domains.
Create services
Creates applications, static sites and databases.
Guarded API access
Generic tools only run operations from a reviewed table based on the API v3 spec.
Tool annotations
Every tool declares read-only, destructive and idempotent hints.

Good for

  • Deploy an app from a coding agent
  • Investigate a failed deployment from its logs
  • Change environment variables or scale a process
  • Spin up a database or static site
  • Look up a Sevalla docs answer while debugging

Pricing

Free trial

Usage-based pricing; free trial available; MCP server price not published

Prices change. Check sevalla.com before you buy.

Sevalla FAQ

How do I add it to Claude Code?

Run claude mcp add --transport http sevalla https://mcp.sevalla.com/mcp, then use /mcp and choose Authenticate.

Which clients are documented?

Claude Code, Claude Desktop, Cursor, Windsurf and OpenCode.

How many tools are there?

27: 22 purpose-built and 5 generic API tools.

How does Sevalla charge?

The site says no plans or seat pricing; you pay for the resources you use, and a free trial is available for applications.

Is Sevalla free?

Sevalla is a paid product with a free trial.

How do I add Sevalla to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.sevalla.com/mcp

What are the best alternatives to Sevalla?

The closest alternatives to Sevalla are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Sevalla

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools