Prowpt MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROWPT_API_KEY | Yes | Your Prowpt API key (required for stdio transport) | |
| PROWPT_API_URL | No | API base URL (default: https://api.prowpt.ai) | https://api.prowpt.ai |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_projectsA | List all projects owned by the authenticated user |
| get_projectA | Get detailed information about a specific project |
| create_projectB | Create a new web app project |
| update_projectC | Update project name, description, or settings |
| delete_projectC | Delete a project permanently |
| clone_projectA | Clone an existing project. Provide a new name; slug is auto-generated if omitted. |
| publish_projectB | Publish the current draft to live (makes the app accessible via subdomain) |
| deploy_projectC | Deploy project to hosting |
| get_deploymentsC | Get deployment history for a project |
| list_source_filesC | List all source file paths in a project |
| read_source_fileC | Read the content of a specific source file |
| write_source_filesB | Write or update one or more source files |
| get_preview_urlC | Build a preview bundle and return the URL |
| get_source_versionsB | List source version history |
| restore_source_versionC | Restore project source to a previous version |
| send_promptA | Send a natural-language prompt to the Prowpt AI assistant to modify the app (uses Prowpt AI credits). Over stdio (Cursor/Claude Code) this blocks until completion (up to 5 minutes). Over HTTP (Claude.ai/ChatGPT connectors) it returns a run_id immediately; poll get_assistant_status(run_id=...) until status is 'completed' or 'failed'. |
| accept_previewC | Accept pending AI-generated changes |
| get_assistant_statusA | Check the status of an assistant generation run. If run_id is provided, looks up that specific run (use this after a send_prompt over HTTP). Otherwise returns the latest unacknowledged run for the project. |
| list_record_typesB | List all record types for a project |
| create_record_typeA | Create a new record type with field definitions. Each field needs {name, type}; label is auto-generated from name if omitted. select/multiselect options: use a plain string array (e.g. ["Small","Medium","Large"]); {label,value} objects are also accepted and auto-normalized. user_scope='profile' for one-per-user data (upsert /me/profile-records/) or 'collection' for many-per-user (CRUD with Bearer). |
| update_record_typeC | Update a record type's name, slug, fields, or other settings |
| list_recordsC | List records of a specific type |
| create_recordD | Create a new record |
| update_recordC | Update an existing record |
| delete_recordD | Delete a record |
| list_workflowsC | List all workflows for a project |
| create_workflowB | Create a workflow. Trigger types: form_submit, button_click, cron, chat_message, webhook (inbound HTTP), stripe_event. IMPORTANT node structure: each node needs type='action' (or 'condition'/'loop') with the specific action inside action.type. Example node: {"id": "n1", "type": "action", "action": {"type": "send_email", "config": {"to": "...", "subject": "...", "body": "..."}}, "next_node_id": null}. Action types: send_email, http_request, llm_chat, save_record, fetch_data, send_whatsapp, redirect, forward_to_human, send_reply. Node outputs propagate via {{nodes..body}}. |
| update_workflowC | Update a workflow's name, definition, or enabled status |
| delete_workflowD | Delete a workflow |
| execute_workflowC | Execute a workflow with trigger data |
| get_workflow_executionsC | Get execution history for a workflow |
| get_publish_statusC | Get current publish/deploy status |
| discard_draft_changesC | Discard unpublished draft changes |
| export_projectC | Export project as JSON backup |
| list_assetsC | List project assets (images, files) |
| upload_assetC | Upload an asset to a project |
| delete_assetC | Delete an asset |
| get_translationsC | Get all translations for a project |
| update_translationsC | Update translations for a locale |
| list_email_templatesA | List all email templates for a project (system and custom) |
| get_email_templateB | Get a specific email template by slug, including full HTML body and variables schema |
| upsert_email_templateA | Create or update an email template. For new templates 'name' is required. System templates only allow editing subject, body_html, body_text, and variables_schema. |
| delete_email_templateB | Delete a custom email template. System templates cannot be deleted. |
| preview_email_templateA | Render a preview of an email template with optional sample context variables |
| send_test_emailB | Send a test email using a template to a specified address |
| seed_email_templatesA | Seed default email templates for a project (inserts factory defaults, skips existing slugs) |
| reset_system_templatesB | Reset all system email templates to their factory defaults (overwrites customisations) |
| list_catalogA | List all npm packages available in the platform catalog (not project-specific) |
| list_project_packagesC | List npm packages enabled for a project, with version info and update availability |
| add_packageA | Add a catalog package to a project's dependencies. The package must exist in the platform catalog. |
| remove_packageA | Remove a package from a project's dependencies. Core packages (react, react-dom, etc.) cannot be removed. |
| get_project_contextA | IMPORTANT: Call this BEFORE writing code for a project. Returns full conventions, patterns, record types, templates, packages, and rules that the generated code MUST follow. |
| get_usageA | Get current usage (credits, projects, workflows, domains) |
| get_creditsB | Get current credit balance |
| purchase_credit_packA | Purchase credits (returns Stripe checkout URL). Minimum 5 credits. |
| get_account_infoA | Get current user account info, tier, and limits |
| connect_stripeA | Start Stripe Connect onboarding for a project (returns onboarding URL). Requires Starter+ tier. |
| get_stripe_statusB | Check whether a project has a connected Stripe account |
| disconnect_stripeC | Remove the Stripe Connect link from a project |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Prowpt Quickstart Guide | Getting started with the Prowpt MCP server |
| Code Quality Guidelines | Guidelines for generated React/TypeScript code |
TDQS
Scored across 59 tools
Each tool targets a distinct resource or action, with clear CRUD coverage for major entities (projects, records, workflows, email templates, source files). No overlapping purposes; even similar tools like preview_email_template and send_test_email are clearly differentiated.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., create_project, list_workflows, upload_asset). The verbs are descriptive and appropriate, and there is no mixing of naming conventions.
With 59 tools, the server is significantly above the typical well-scoped range (3-15). While the platform's feature set justifies many tools, this large number can overwhelm agents and suggests potential for consolidation or clearer grouping.
The tool set covers nearly all major operations for project management, records, workflows, email templates, source files, assets, Stripe, and more. Minor gaps exist (e.g., no explicit translation deletion), but the coverage is thorough for the domain.