Provider REST API

16 actions

Connect Claude to Coolify

Manage applications, services, deployments, and servers. Toolspoke puts 16 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API token
Actions exposed: 16
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Coolify
Open the marketplace in your workspace, add Coolify to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

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

One block covers every tool you have installed. Coolify shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Coolify asks for

API token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Instance URLRequired: Your Coolify instance root, without /api/v1. Use https://app.coolify.io for Coolify Cloud.; https://coolify.example.com
API tokenRequired: Keys & Tokens → API tokens. Grant read-only for the list actions, or read/write for deploy, power, and environment changes.; 1|abcdef…

What Claude can do in Coolify

16 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 10Reads
Writes: 6Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_applications
List the applications on this Coolify instance with their status, domain, git source, and UUID. Call this first - every other application action takes the UUID.
get_application
Fetch one application's full configuration: domains, build and start commands, exposed ports, health check, resource limits, and current status.
application_logs
Read the tail of an application's container logs. Use it to diagnose a crashing or unhealthy application after a deployment.
list_running_deployments
List deployments. Without an application UUID this returns the deployments currently running across the instance; with one it returns that application's deployment history, newest first. Build logs are omitted - use get_deployment for those.
list_application_deployments
List one application's deployment history, newest first. Build logs are omitted - use get_deployment for those.
get_deployment
Fetch one deployment by UUID to check whether it finished, failed, or is still building. Set include_logs to also return the build log, which can be long.
list_application_envs
List an application's environment variable keys. Values are masked by default because they usually hold secrets. Set reveal_values only when the caller genuinely needs a value - every tool result is written to the workspace audit log in clear text.
list_servers
List the servers Coolify deploys to, with their address, SSH user, and proxy type. Returns the server UUID used by server_resources.
server_resources
List everything deployed on one server - applications, databases, and services - with each resource's current status.
list_resources
List every resource on the instance in one call - applications, databases, and services together with their type and status. Use it for an instance-wide health sweep; use list_applications when you only care about applications.

Writes

Creates or updates something on the other side.

deploy
Trigger a deployment of one or more resources, by UUID or by tag. Returns the deployment UUIDs - poll them with get_deployment. Set force to rebuild without the Docker layer cache.
start_application
Start an application's containers. Set force to rebuild without the Docker layer cache.
stop_application
Stop an application's containers, taking it offline but leaving its configuration and data intact. Use deploy when you want to ship new code instead.
restart_application
Restart an application's containers without rebuilding it.
update_application_env
Update an application's existing environment variable. Call create_application_env when the key does not exist yet. The change only takes effect on the next deployment.
create_application_env
Create a new environment variable on an application. Call update_application_env when the key already exists. The change only takes effect on the next deployment.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 16 actions above are the whole of it. A call to any other name is refused before it reaches Coolify rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Coolify, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Coolify of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Coolify: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Coolify. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Coolify's own rate limits. A call that Coolify refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Coolify?

16 named actions: 10 that only read and 6 that write. They include list_applications, get_application and application_logs. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Coolify connector need?

API token. The connector asks for instance url and api token. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Coolify connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 16 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Coolify connector not do?

The 16 actions above are the whole of it. A call to any other name is refused before it reaches Coolify rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Coolify, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Coolify of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Coolify. An agent has to ask. Toolspoke does not retry, queue or back off around Coolify's own rate limits. A call that Coolify refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Coolify's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Coolify?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More infrastructure connectors

Browse all of them