Connect AI tools over MCP

Plexivo speaks the Model Context Protocol (MCP). Connect your editor or AI assistant, and it can deploy apps, create databases and check on your organisation for you. It signs in with an API key and does only what that key allows.

The server#

What your assistant can do#

When it connects, your assistant receives Plexivo’s tools, each marked with its risk class. These are the ones you will use.

Build and deploy#

Inspect and diagnose#

Plan and cost#

Account#

Safety#

• The key’s permissions, nothing more. Every call passes the same sign-in, permission checks, limits and audit as the Plexivo API. A key works only in its own organisation and never does more than the person who created it can do.
• Each tool asks for the right permission. Reading needs Read, changing needs Create and change, and the wallet balance needs Billing. Without it, the tool refuses and names the permission it needs.
• Creating resources and new passwords need a confirmation. Your assistant must ask for a plan first. The plan carries a single-use confirmation token that runs only that exact call, from the same key, within 5 minutes. Ask your assistant to show you the plan before it confirms.
• Small changes run when asked. scale_app and set_env run without a confirmation. To stop them running over MCP, an owner or admin chooses Ask me before any change or Only watch and report in Plexivo AI settings.
• Deleting stays with people. The destroy tool always refuses and points to the Plexivo console. No setting changes that.
• The same checks and prices as the console. A resource your assistant creates passes the same plan, verification and wallet checks, counts towards the key’s monthly spend limit, and is billed at its normal price.
• Secrets stay out of answers. Plexivo removes secret-shaped values from every tool’s answer before it is sent.
• Every change is recorded. Each change made over MCP appears in Settings → Audit log with the API key that made it. Reads, plans and refusals are not recorded.

Create a key#

Owners and admins can create keys.

1. Open Developer settings. Go to Settings → Developer and choose Create API key.
2. Name it after the tool and the machine, such as “Cursor on my laptop”, in Key name.
3. Choose permissions. Keep Read and Create and change, the default, to let your assistant deploy. For an assistant that only looks, keep Read alone. Add Billing to let it see your wallet balance.
4. Set limits. Choose when it Expires, and set a Monthly spend limit (USD, optional) if you want one.
5. Choose Issue key, then copy the key. It is shown once.

On the same page, Editor and AI tools has a ready configuration: choose Copy configuration. More on keys in API keys.

Configure your client#

Keep the key out of files you commit. Set it in your shell:

export PLEXIVO_API_KEY="paste-your-key-here"

Claude Code#

claude mcp add --transport http plexivo https://api.plexivo.io/mcp \
  --header "Authorization: Bearer $PLEXIVO_API_KEY"

Add --scope user to use Plexivo in every project. Run claude mcp list to see it connected.

Cursor#

In your project, create .cursor/mcp.json:

{
  "mcpServers": {
    "plexivo": {
      "url": "https://api.plexivo.io/mcp",
      "headers": { "Authorization": "Bearer ${env:PLEXIVO_API_KEY}" }
    }
  }
}

Cursor reads PLEXIVO_API_KEY from the environment it was started in.

VS Code#

In your project, create .vscode/mcp.json. VS Code asks for the key the first time and keeps it out of the file:

{
  "inputs": [
    { "type": "promptString", "id": "plexivo-api-key", "description": "Plexivo API key", "password": true }
  ],
  "servers": {
    "plexivo": {
      "type": "http",
      "url": "https://api.plexivo.io/mcp",
      "headers": { "Authorization": "Bearer ${input:plexivo-api-key}" }
    }
  }
}

Other clients#

Any client that supports Streamable HTTP works. Give it the URL and the header Authorization: Bearer followed by your key. Plexivo reads the key from this header only. Many clients take the same configuration the console copies for you:

{
  "mcpServers": {
    "plexivo": {
      "type": "http",
      "url": "https://api.plexivo.io/mcp",
      "headers": { "Authorization": "Bearer ${PLEXIVO_API_KEY}" }
    }
  }
}

Try it#

Without a key, the server describes itself:

curl https://api.plexivo.io/mcp
# {"name":"plexivo","version":"0.1.0","transport":"streamable-http","protocolVersion":"2025-06-18"}

Then, in your editor or assistant:

1. Ask your assistant “Which Plexivo organisation am I connected to, and what is running?” It answers with your organisation and your resources.
2. Ask for a plan, such as “Plan a Plexivo Postgres database called orders-db”. A plan creates nothing: your assistant shows you what it would do.

If something is refused#

Limits#

MCP calls share the key’s limits with the rest of the API. By default:

• 120 requests a minute per key.
• 4 calls running at the same time per key.
• 20 calls a day that create resources. A plan does not count.
• The key’s monthly spend limit, if you set one.

See Limits on every key.

Next steps#