The Pragmatiks API exposes an MCP (Model Context Protocol) server that allows AI assistants to interact with your resources, providers, and operations directly.
Why Use MCP? MCP enables AI tools like Claude, Cursor, and GitHub Copilot to:
Manage resources - List, create, update, and delete resources through natural languageMonitor status - Check resource lifecycle states and troubleshoot issuesDeploy providers - Push code, monitor builds, and manage deploymentsHandle operations - Retry failed events and manage dead letter queues
Instead of switching between the CLI and your AI assistant, you can stay in your workflow and let the AI handle Pragmatiks operations directly.
The MCP server exposes the following tools:
Authentication Tool Description get_meGet current user information
Resources Tool Description list_resource_typesList available resource types from deployed providers list_resourcesList resources with optional filters (provider, type, tags) get_resourceGet a resource by ID get_resource_statusGet resource lifecycle status apply_resourceCreate or update a resource delete_resourceDelete a resource
Providers Tool Description list_providersList providers with deployment status push_providerPush provider code and trigger a build list_buildsList builds for a provider get_build_statusGet build status by version get_build_logsStream build logs deploy_providerDeploy a provider version delete_providerDelete a provider
Operations Tool Description list_dead_lettersList failed events in the dead letter queue get_dead_letterGet a single dead letter event retry_dead_letterRetry a failed event retry_all_dead_lettersRetry all failed events delete_dead_letterDelete a dead letter event
Authentication The MCP server requires authentication via your Pragmatiks account. When you configure the MCP server in your AI tool, you’ll need to provide your authentication token.
All MCP operations are automatically scoped to your organization. Resources and providers from other organizations are not accessible.
Endpoint The MCP server is available at:
https://api.pragmatiks.io/mcp
Next Steps
Configuration Guide Set up the MCP server in your AI tool.
