MCP

Give your AI agent the keys.

The Canner MCP server turns the Canner API into native tools for AI agents. Point Claude Desktop, Cursor, or any Model Context Protocol client at it and your agent can deploy a project, read a failing build log, set an environment variable, attach a domain, or inspect a project’s Postgres databases, backups and dedicated instance — on Canadian infrastructure, on your behalf.

$npx @canner-ca/mcp

View on npm →API reference

Browser-based builders (Lovable, Bolt, v0)

AI app builders that run in the browser connect to a remote MCP server by URL. Point yours at the Canner endpoint below and authenticate with a Canner API token, then ask your agent to “save my app to Canner” — it can create a project and deploy your code straight from the chat, onto Canadian infrastructure. In Lovable: Connectors → Chat connectors → New MCP server. In Bolt and v0: add a custom MCP server in settings.

URLhttps://api.canner.ca/mcp

In your dashboard's API tokens, choose the “MCP connector (deploy only)” type — it's scoped to project + deploy access with no billing and no token management, so a credential you paste into a third-party builder can't do more than deploy.

Local clients (Claude Desktop, Cursor, Claude Code)

Desktop agents run the server over npx — nothing to install globally. Add it to your MCP client's config with a Canner API token. In Claude Desktop, edit claude_desktop_config.json; in Cursor, edit .cursor/mcp.json. Then restart the client and the Canner tools appear.

{
  "mcpServers": {
    "canner": {
      "command": "npx",
      "args": ["-y", "@canner-ca/mcp"],
      "env": { "CANNER_TOKEN": "cnr_your_token_here" }
    }
  }
}

Already used canner login with the CLI? You can drop the CANNER_TOKEN line — the server reads the token the CLI stored.

Tools

Over thirty tools, each wrapping a documented REST endpoint — including canner_create_project and canner_save_app, which deploy your code from the agent:

canner_whoamiConfirm which account the agent is signed in as, and which organization it acts for.canner_list_projectsList the projects in this organization.canner_get_projectGet one project's status, URL, and source.canner_list_deploymentsList a project's deployments, newest first.canner_get_deploymentRead one deployment in full — including its build log.canner_deployRebuild a GitHub-connected project from HEAD.canner_list_env_varsList a project's environment variables.canner_set_env_varAdd an environment variable.canner_list_domainsList a project's custom domains.canner_add_domainAttach a custom domain.canner_verify_domainRe-check DNS and provision TLS for a domain.canner_create_projectCreate a new empty project to deploy into.canner_save_appDeploy an app straight from your agent by sending its source files.canner_list_databasesList a project's databases, with size and Postgres version.canner_get_databaseConnection details for one database. Credentials are hidden unless explicitly requested.canner_create_databaseAdd another database to a project (Starter: one per project; paid plans can add more).canner_export_databaseStart a database export; poll canner_get_database_operation for the result.canner_copy_databaseCopy a database into another EMPTY database you own.canner_list_database_operations / canner_get_database_operationList recent database operations, or check one's status.canner_list_backupsList a database's backups and its backup policy (read-only — taking, restoring and deleting backups is done in the dashboard or CLI).canner_get_instanceA project's dedicated Postgres instance and its point-in-time-recovery window (read-only — creating, restoring and moving is done in the dashboard or CLI).canner_database_security_checkA read-only security and performance check of a database (policies, functions, views, indexes, primary keys). Reads the catalog, never your data.canner_audit_database_rolesWhat each role of a dedicated-instance database can do, with findings for a least-privilege setup (read-only).canner_get_instance_upgradeWhether the dedicated instance can be upgraded to a newer Postgres version and what would stop it (read-only — upgrading is done in the dashboard or CLI).canner_get_instance_configThe dedicated instance's tuning: preset, timeouts, maintenance window and any restart waiting for it (read-only).canner_set_instance_configChange the preset, timeouts and maintenance window. Takes effect at once, no restart.canner_restart_instanceRestart the dedicated instance now (a few seconds of dropped connections). Requires confirm: true, only with the owner's go-ahead.canner_list_extensionsExtensions available on a database of the dedicated instance and what is installed (read-only).canner_install_extensionInstall an extension (pgvector, PostGIS, pg_trgm, pg_cron…). pg_cron restarts the instance and needs confirm: true.canner_remove_extensionRemove an extension; refused while objects still use it.canner_get_replicationLogical replication of a database: on/off, WAL cap, publications, slots and their health (read-only).canner_set_replicationTurn logical replication on or off (restarts the instance, confirm: true) or change the WAL cap per slot.canner_get_instance_memoryThe memory budget split between the app and its dedicated Postgres, and whether a change is waiting (read-only).canner_apply_instance_memoryApply the memory split (restarts the instance, confirm: true).canner_set_instance_monitoringTurn query insights and the log viewer on or off (restarts the instance, confirm: true).

Zero dependencies

The server speaks the MCP stdio transport directly — no third-party packages. That's the same supply-chain discipline as the rest of Canner: the code you run inside your agent ships nothing extra to audit, and never reaches outside Canada in normal operation.

Safe by default

Destructive operations — deleting a project, revoking a token, dropping a database or domain — are deliberately not exposed, so an agent can't take them by mistake. Do those from the dashboard or the CLI.

What it stores and sends

The server writes nothing to your machine. It reads a token from the CANNER_TOKEN environment variable, or — if you've already run canner login — from the credentials file the CLI wrote at ~/.canner/credentials. Requests go only to api.canner.ca. There is no telemetry, analytics, or crash reporting. Run via npx, nothing is installed globally; to remove it, delete the entry from your MCP client's config file.

Use of the MCP server and the Canner service is governed by our Terms of Service and Privacy Policy.

Under the hood it calls the same REST API; for terminal workflows, see the CLI. Building for agents? The llms.txt file describes Canner for language models.