Momen MCP Server

The official Model Context Protocol (MCP) server for Momen. This server bridges your AI assistants (like Cursor, Claude Desktop) with your Momen projects, enabling deep context awareness for smarter no-code development assistance.

✨ Features

• Project Insight: Access comprehensive project schemas, including Data Models, Action Flows, APIs, and configurations.
• Seamless Management: Fuzzy search and switch between your Momen projects effortlessly.
• Secure Context: OAuth-based authentication with persistent session management.
• AI Integration: Empower your AI tools to understand your specific Momen project structure.
• Gradle-style Daemon: CLI and MCP share a compatible daemon that keeps CRDT/ztype project state hot; --no-daemon runs one-shot and exits completely.

🚀 Quick Start

Setup in Cursor

1. Open Cursor Settings (Cmd + , or Ctrl + ,).
2. Navigate to Features -> MCP.
3. Click Add New MCP Server.
4. Enter the following details:
   • Name: Momen MCP
   • Type: command
   • Command: npx -y momen-mcp@latest
5. Save and check the connection status.

Setup in Claude Desktop

Add the following configuration to your Claude Desktop config file (typically at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "momen": {
      "command": "npx",
      "args": ["-y", "momen-mcp@latest"]
    }
  }
}

🛠️ Available Tools

Once connected, your AI assistant can use the tools below. Several are facade tools that take an op argument selecting the operation:

• Workspace: set_current_working_directory.
• Auth: auth (op: LOGIN / LOGOUT / WHOAMI / REAUTH), get_account_profile.
• Projects: get_projects, create_project, set_current_project, get_current_project, rename_project, rename_project_app, delete_project, reset_project, get_project_schema (backward-compatible simplified schema), project_inspect (op: DETAIL / METADATA / RESOURCES).
• Schema session: schema_session (op: LOAD / RELOAD / SYNC / SNAPSHOT / VALIDATE), schema_observe (op: STATE / EVENTS), schema_status. Edits stay in an in-memory CRDT session and only go live after sync_backend.
• Actionflow templates: list_actionflow_node_templates (the server-managed preset integration nodes — SMS, video/AI generation, etc. — available to schema_actionflow_node op=ADD_NODE).
• Schema editing (ztype facades) — each takes an op; changes apply immediately (use schema_undo to revert), then schema_session op=VALIDATE + sync_backend to deploy. Auto-generated from the ztype tool catalog. The high-traffic facades are resident MCP tools; the rest of the catalog is deferred behind search_tools / describe_tool (see Tool discovery below) and run through ztype_tool_calls:

• schema_actionflow — op: ADD / ADD_GLOBAL_VARS / ADD_INPUT_PARAMS / ADD_OUTPUT_FIELDS / ADD_CUSTOM_CODE_NODE_OUTPUT_VALUE / CLEAR_OUTPUT / CLEAR_CUSTOM_CODE_NODE_OUTPUT_TYPE / DELETE / DELETE_GLOBAL_VARS / DELETE_INPUT_PARAMS / DELETE_OUTPUT_FIELDS / DELETE_CUSTOM_CODE_NODE_OUTPUT_VALUE / GET_DETAIL / SELECTABLE_TYPES / LIST / SET_OUTPUT / SET_CUSTOM_CODE_NODE_OUTPUT_TYPE / UPDATE / UPDATE_GLOBAL_VARS / UPDATE_INPUT_PARAMS / UPDATE_CUSTOM_CODE_NODE_OUTPUT_VALUE
• schema_actionflow_node — op: ADD_BRANCH_ITEM / ADD_NODE / ADD_CODE_INPUT / ADD_VAR_TARGETS / DELETE_NODES / DELETE_CODE_INPUT / DELETE_VAR_TARGETS / CONTEXT_INFO / MOVE_NODE / RENAME_CODE_INPUT / UPDATE_NODE
• schema_add_tpa_config_parameters — op: ADD_TPA_CONFIG_PARAMETERS
• schema_add_tpa_configs — op: ADD_TPA_CONFIGS
• schema_add_tpa_parameter_children — op: ADD_TPA_PARAMETER_CHILDREN
• schema_add_tpa_response_data — op: ADD_TPA_RESPONSE_DATA
• schema_add_tpa_response_data_children — op: ADD_TPA_RESPONSE_DATA_CHILDREN
• schema_api — op: ADD / ADD_INPUT_VARIABLES / ADD_PARAMETERS / ADD_RESPONSE_CONFIGS / ADD_WORKSPACES / ADD_WORKSPACE_CONSTANTS / DELETE / DELETE_INPUT_VARIABLES / DELETE_PARAMETERS / DELETE_RESPONSE_CONFIGS / DELETE_WORKSPACES / DELETE_WORKSPACE_CONSTANTS / LIST / LIST_WORKSPACES / GET_DETAIL / UPDATE / UPDATE_INPUT_VARIABLES / UPDATE_PARAMETERS / UPDATE_RESPONSE_CONFIGS / UPDATE_WORKSPACE / UPDATE_WORKSPACE_CONSTANTS
• schema_binding_inspect — op: BINDING_OPTIONS / BINDING_TYPE / FORMULA_CONFIG_OPTIONS / FORMULA_OPERATORS
• schema_common — op: SET_DISPLAY_NAME
• schema_component — op: LIST_PAGES / GET_CONTEXT_INFO / GET_INFO / GET_CHILDREN_INFO
• schema_condition_expr — op: DELETE_TERM / LIST_OPERATORS / INSERT_TERM / NEST / TOGGLE_AND_OR / TOGGLE_NOT / SET_OPERATOR
• schema_conditional_branch — op: DELETE / INSERT / REORDER / UPDATE
• schema_create_binding — op: CONDITIONAL / CONST / FORMULA / OPTION / SET_FORMULA_CONFIG
• schema_delete_tpa_config_parameters — op: DELETE_TPA_CONFIG_PARAMETERS
• schema_delete_tpa_configs — op: DELETE_TPA_CONFIGS
• schema_delete_tpa_parameter_children — op: DELETE_TPA_PARAMETER_CHILDREN
• schema_delete_tpa_response_data — op: DELETE_TPA_RESPONSE_DATA
• schema_delete_tpa_response_data_children — op: DELETE_TPA_RESPONSE_DATA_CHILDREN
• schema_get_all_tpa_config_infos — op: GET_ALL_TPA_CONFIG_INFOS
• schema_get_tpa_config_detail — op: GET_TPA_CONFIG_DETAIL
• schema_request_filter — op: ADD_FILTER / ADD_CONDITION / ADD_SORT / DELETE_FILTER / DELETE_CONDITION / DELETE_SORT / CONTEXT / NEST_CONDITION / REORDER_FILTERS / REORDER_SORT / SET_UPDATE_COLUMN_ARITHMETIC / TOGGLE_CONDITION_AND_OR / TOGGLE_CONDITION_NOT / UPDATE_FILTER / SET_CONDITION_OPERATOR / UPDATE_SORT
• schema_set_tpa_config_paging — op: SET_TPA_CONFIG_PAGING
• schema_table — op: ADD_CONSTRAINTS / ADD_FIELDS_RELATIONS / ADD_TABLES / ADD_EXTENSION / DELETE_CONSTRAINTS / DELETE_FIELDS_RELATIONS / DELETE_TABLES / DELETE_EXTENSION / LIST_NAMES / LIST_EMBEDDING_MODELS / GET_INFOS
• schema_trigger — op: ADD_DB_TRIGGERS / ADD_SCHEDULED_TRIGGERS / DELETE_DB_TRIGGERS / DELETE_SCHEDULED_TRIGGERS / GET_ALL_DB_TRIGGER_INFOS / GET_ALL_SCHEDULED_TRIGGER_INFOS / GET_DB_TRIGGER_DETAIL / GET_SCHEDULED_TRIGGER_DETAIL / UPDATE_DB_TRIGGER / UPDATE_SCHEDULED_TRIGGER
• schema_type — op: ADD_ENUMS / ADD_OBJECTS / ADD_FIELDS / DELETE_ENUMS / DELETE_OBJECTS / DELETE_FIELDS / LIST_ENUMS / LIST_OBJECTS / UPDATE_ENUMS / UPDATE_OBJECTS
• schema_update_tpa_config — op: UPDATE_TPA_CONFIG
• schema_update_tpa_config_parameter — op: UPDATE_TPA_CONFIG_PARAMETER
• schema_update_tpa_parameter_child — op: UPDATE_TPA_PARAMETER_CHILD
• schema_update_tpa_response_data — op: UPDATE_TPA_RESPONSE_DATA
• schema_update_tpa_response_data_child — op: UPDATE_TPA_RESPONSE_DATA_CHILD
• schema_zai_config — op: ADD_ZAI_CONFIGS / ADD_ZAI_CONFIG_INPUT_ARGS / DELETE_ZAI_CONFIGS / DELETE_ZAI_CONFIG_INPUT_ARGS / GET_ALL_ZAI_CONFIG_INFOS / GET_ZAI_CONFIG_DETAIL / GET_ZAI_CONFIG_SELECTABLE_TYPES / UPDATE_ZAI_CONFIG / UPDATE_ZAI_CONFIG_INPUT_ARGS / UPDATE_ZAI_CONFIG_OUTPUT

• Schema editing — low-level: ztype_tool_calls.
• Tool discovery: search_tools, describe_tool. Only the high-traffic ztype facades are registered as resident tools; find any deferred catalog facade with search_tools, read its op list and argument schema with describe_tool, then execute it via ztype_tool_calls.
• Deploy: sync_backend.
• Data: runtime_graphql (raw GraphQL: queries, mutations, aggregates, relations, invoking actionflows/AI agents, presigned asset uploads).
• Logs & docs: search_logs, search_docs, get_doc_page.
• Platform backend passthrough: platform_graphql.
• Escape hatch: agent_command (invoke any internal command directly).

CLI / Daemon

Every command below is available. Multi-word verbs and their aliases are shown together; --args '<json>' accepts the same arguments as the matching MCP tool.

# Server / daemon
momen-mcp mcp
momen-mcp version-check
momen-mcp daemon start
momen-mcp daemon foreground
momen-mcp daemon status
momen-mcp daemon stop

# Auth
momen-mcp login
momen-mcp logout
momen-mcp whoami
momen-mcp reauth
momen-mcp account profile            # alias: account me

# Projects
momen-mcp projects search
momen-mcp projects list
momen-mcp project create
momen-mcp project set-current
momen-mcp project current            # alias: project get-current
momen-mcp project detail
momen-mcp project metadata           # alias: project inspect
momen-mcp project resources
momen-mcp project rename
momen-mcp project rename-app
momen-mcp project delete
momen-mcp project reset
momen-mcp project sync-backend       # alias: project deploy-backend

# Actionflow
momen-mcp actionflow list-node-templates

# Schema
momen-mcp schema load
momen-mcp schema reload
momen-mcp schema status
momen-mcp schema state
momen-mcp schema events
momen-mcp schema sync
momen-mcp schema snapshot
momen-mcp schema validate            # alias: schema type-check
momen-mcp schema tool-call           # alias: schema tool-calls
momen-mcp schema undo
momen-mcp schema redo

# Runtime data
momen-mcp runtime graphql
momen-mcp runtime query
momen-mcp runtime insert
momen-mcp runtime update
momen-mcp runtime delete

# Logs & docs
momen-mcp logs search
momen-mcp docs search
momen-mcp docs get-page

# Zion Backend passthrough
momen-mcp platform graphql

# Global flags (combine with any command)
momen-mcp --no-daemon whoami
momen-mcp --cwd <dir> schema status
momen-mcp schema status --pretty
momen-mcp schema load --args '{"projectExId":"..."}'

Normal CLI commands reuse a compatible daemon. Compatibility includes product, Node major/platform, backend URL, auth user, ztype/schema version, CRDT/json-joy versions, workspace root, and startup flags. The daemon exits after 3 hours idle; loaded project schemas unload after 5 minutes idle.

🔒 Security

On first use, the server will launch a browser window for secure OAuth authentication with Momen. Tokens are stored securely on your local machine.

🏗️ What is Momen?

Momen is a next-generation full-stack no-code platform with a powerful backend designed for headless use. While Momen provides a visual editor for building complete applications, its backend can be used independently as a Backend-as-a-Service (BaaS) for custom frontend development.

Why Use Momen as BaaS?

✅ Enterprise-Grade PostgreSQL - Powerful relational database with full ACID compliance
✅ Auto-Generated GraphQL API - Your data model automatically becomes a type-safe GraphQL schema
✅ Built-in Backend Logic - Actionflows for complex workflows without writing backend code
✅ Native AI Integration - Built-in AI agents with RAG, tool use, and structured output
✅ Third-party API Relay - Import OpenAPI specs, use as backend relay with authentication
✅ Stripe Integration - Native payment processing for subscriptions and one-time charges
✅ File Storage - Image and binary asset management with CDN
✅ Authentication - Built-in user management with JWT tokens
✅ Real-time Subscriptions - WebSocket support via GraphQL subscriptions
✅ Predictable Pricing - Project-based pricing, no per-request charges

🔗 Links

• Momen Website
• Model Context Protocol

📖 Additional Resources

Momen Documentation

• Official Momen Docs
• Quick Start Guide
• Database Configuration
• Actionflow Guide
• AI Agent Tutorial
• Stripe Integration

Note: This tool is designed to assist development within the Momen ecosystem.