Fe TypeScript MCP Server

It is generated with Stainless.

Installation

Direct invocation

You can run the MCP Server directly via npx:

export FE_API_KEY="My API Key"
npx -y ubtc-pv-fe-mcp@latest

Via MCP Client

There is a partial list of existing clients at modelcontextprotocol.io. If you already have a client, consult their documentation to install the MCP server.

For clients with a configuration JSON, it might look something like this:

{
  "mcpServers": {
    "ubtc_pv_fe_api": {
      "command": "npx",
      "args": ["-y", "ubtc-pv-fe-mcp", "--client=claude", "--tools=dynamic"],
      "env": {
        "FE_API_KEY": "My API Key"
      }
    }
  }
}

Exposing endpoints to your MCP Client

There are two ways to expose endpoints as tools in the MCP server:

1. Exposing one tool per endpoint, and filtering as necessary
2. Exposing a set of tools to dynamically discover and invoke endpoints from the API

Filtering endpoints and tools

You can run the package on the command line to discover and filter the set of tools that are exposed by the MCP Server. This can be helpful for large APIs where including all endpoints at once is too much for your AI's context window.

You can filter by multiple aspects:

• --tool includes a specific tool by name
• --resource includes all tools under a specific resource, and can have wildcards, e.g. my.resource*
• --operation includes just read (get/list) or just write operations

Dynamic tools

If you specify --tools=dynamic to the MCP server, instead of exposing one tool per endpoint in the API, it will expose the following tools:

1. list_api_endpoints - Discovers available endpoints, with optional filtering by search query
2. get_api_endpoint_schema - Gets detailed schema information for a specific endpoint
3. invoke_api_endpoint - Executes any endpoint with the appropriate parameters

This allows you to have the full set of API endpoints available to your MCP Client, while not requiring that all of their schemas be loaded into context at once. Instead, the LLM will automatically use these tools together to search for, look up, and invoke endpoints dynamically. However, due to the indirect nature of the schemas, it can struggle to provide the correct properties a bit more than when tools are imported explicitly. Therefore, you can opt-in to explicit tools, the dynamic tools, or both.

See more information with --help.

All of these command-line options can be repeated, combined together, and have corresponding exclusion versions (e.g. --no-tool).

Use --list to see the list of available tools, or see below.

Specifying the MCP Client

Different clients have varying abilities to handle arbitrary tools and schemas.

You can specify the client you are using with the --client argument, and the MCP server will automatically serve tools and schemas that are more compatible with that client.

• --client=<type>: Set all capabilities based on a known MCP client

  • Valid values: openai-agents, claude, claude-code, cursor
  • Example: --client=cursor

Additionally, if you have a client not on the above list, or the client has gotten better over time, you can manually enable or disable certain capabilities:

• --capability=<name>: Specify individual client capabilities
  • Available capabilities:
    • top-level-unions: Enable support for top-level unions in tool schemas
    • valid-json: Enable JSON string parsing for arguments
    • refs: Enable support for $ref pointers in schemas
    • unions: Enable support for union types (anyOf) in schemas
    • formats: Enable support for format validations in schemas (e.g. date-time, email)
    • tool-name-length=N: Set maximum tool name length to N characters
  • Example: --capability=top-level-unions --capability=tool-name-length=40
  • Example: --capability=top-level-unions,tool-name-length=40

Examples

1. Filter for read operations on cards:

--resource=cards --operation=read

2. Exclude specific tools while including others:

--resource=cards --no-tool=create_cards

3. Configure for Cursor client with custom max tool name length:

--client=cursor --capability=tool-name-length=40

4. Complex filtering with multiple criteria:

--resource=cards,accounts --operation=read --tag=kyc --no-tool=create_cards

Importing the tools and server individually

// Import the server, generated endpoints, or the init function
import { server, endpoints, init } from "ubtc-pv-fe-mcp/server";

// import a specific tool
import healthCheckAPI from "ubtc-pv-fe-mcp/tools/api/health-check-api";

// initialize the server and all endpoints
init({ server, endpoints });

// manually start server
const transport = new StdioServerTransport();
await server.connect(transport);

// or initialize your own server with specific tools
const myServer = new McpServer(...);

// define your own endpoint
const myCustomEndpoint = {
  tool: {
    name: 'my_custom_tool',
    description: 'My custom tool',
    inputSchema: zodToJsonSchema(z.object({ a_property: z.string() })),
  },
  handler: async (client: client, args: any) => {
    return { myResponse: 'Hello world!' };
  })
};

// initialize the server with your custom endpoints
init({ server: myServer, endpoints: [healthCheckAPI, myCustomEndpoint] });

Available Tools

The following tools are available in this MCP server.

Resource api:

• health_check_api (read):
• list_stamps_api (read): Get all stamps of company

Resource api.auth:

• login_api_auth (write): Login by email & password . Returns a custom JWT token which includes user's roles and permissions.
• refresh_token_api_auth (write): Refresh JWT token using refresh token
• register_otp_api_auth (write): Register OTP for user
• verify_email_api_auth (write): Verify email using verification code
• verify_otp_api_auth (write): Verify OTP for user

Resource api.notifications:

• list_api_notifications (read): Get notifications
• mark_as_read_api_notifications (write): Mark notification as read

Resource api.users:

• create_api_users (write): Create a new user
• retrieve_api_users (read): Get a user by id
• update_api_users (write): Update a user
• list_api_users (read): Get paginated list of users
• delete_api_users (write): Delete a user
• change_password_api_users (write): Update user password
• reset_account_api_users (write): Reset user account
• retrieve_current_api_users (read): Get the current login user
• update_password_api_users (write): Update user password
• update_status_api_users (write): Update user status

Resource api.users.signatures:

• create_users_api_signatures (write): Create a new signature for current user
• list_users_api_signatures (read): Get list signatures of current user
• delete_users_api_signatures (write): Delete a signature of a user
• set_default_users_api_signatures (write): Set a signature as default for a user

Resource api.superadmin:

• send_email_to_all_api_superadmin (write): Send email to all users
• send_welcome_email_api_superadmin (write): Send welcome email to user

Resource api.files:

• retrieve_api_files (read): Get file by id
• delete_api_files (write): Delete file by id
• create_with_preuploaded_api_files (write): Get direct upload URL
• get_direct_upload_url_api_files (write): Get direct upload URL
• upload_api_files (write): Upload files

Resource api.departments:

• create_api_departments (write): Create a new department
• retrieve_api_departments (read): Get a department by ID
• update_api_departments (write): Update a department by ID
• list_api_departments (read): Get departments by paginate and filter
• delete_api_departments (write): Delete a department by ID
• get_employees_api_departments (read): Get employees by department slug
• get_related_departments_api_departments (read): Get related departments by ID
• get_relationships_api_departments (read): Get all department relationships

Resource api.department_roles:

• create_api_department_roles (write): Create a new department role
• retrieve_api_department_roles (read): Get a department role by ID
• update_api_department_roles (write): Update a department role by ID
• list_api_department_roles (read): Get paginated department roles
• delete_api_department_roles (write): Delete a department role by ID
• get_by_department_api_department_roles (read): Get department roles by department ID

Resource api.employees:

• create_api_employees (write): Create employee
• retrieve_api_employees (read): Get employee by ID
• update_api_employees (write): Update employee by ID
• list_api_employees (read): Get employees with pagination
• delete_api_employees (write): Delete employee by ID
• get_histories_api_employees (read): Get employee histories by ID
• get_status_summary_api_employees (read): Get employees status summary
• upload_avatar_api_employees (write): Upload employee avatar

Resource api.documents:

• create_api_documents (write): Create a new document
• retrieve_api_documents (read): Get document by uniqueCode
• list_api_documents (read): Get documents with pagination
• add_appendix_and_related_files_api_documents (write): Add appendix and related files to document
• add_approvers_api_documents (write): Add more approvers to pending document
• cancel_api_documents (write): Cancel pending/need-update document
• create_new_version_api_documents (write): Create a new version of the document
• download_api_documents (read): Download document directly by document ID
• notify_api_documents (write): Notify document is successfully signed and stamped
• request_re_sign_api_documents (write): Request re-sign for document
• review_api_documents (write): Review document by id
• set_signatures_api_documents (write): Set signatures for document
• set_stamps_api_documents (write): Set stamps for document
• signatures_api_documents (read): Get signatures of approved document
• signed_files_api_documents (read): Get signed files of document by uniqueCode
• status_summary_api_documents (read): Get documents status summary

Resource api.document_categories:

• create_api_document_categories (write):
• retrieve_api_document_categories (read):
• update_api_document_categories (write):
• list_api_document_categories (read): Get document categories with pagination
• delete_api_document_categories (write):

Resource api.document_issuers:

• create_api_document_issuers (write):
• retrieve_api_document_issuers (read):
• update_api_document_issuers (write):
• list_api_document_issuers (read): Get document issuers with pagination
• delete_api_document_issuers (write):

Resource api.folders:

• create_api_folders (write):
• retrieve_api_folders (read):
• update_api_folders (write):
• list_api_folders (read): Get folders with pagination
• delete_api_folders (write):

Resource api.library:

• retrieve_api_library (read): Get items by id
• list_api_library (read): Get items with pagination
• create_shortcut_api_library (write): Create shortcut to file
• download_api_library (read): Download file directly by file ID
• get_breadcrumbs_api_library (read): Get breadcrumbs by folder id
• get_temp_url_api_library (read): Get temporary URL by file ID
• upload_api_library (write): Upload file to library

Resource api.permissions.policies:

• update_permissions_api_policies (write): Update a department role with permissions attached
• list_permissions_api_policies (read): List all resources and their permissions

Resource api.permission_requests:

• create_api_permission_requests (write): Create a new permission request
• list_api_permission_requests (read): Get all permission requests
• approve_api_permission_requests (write): Approve a permission request
• assign_api_permission_requests (write): Assign permission requests to multiple users
• check_api_permission_requests (read): Check permission for a specific item and type
• deny_api_permission_requests (write): Deny a permission request

Resource api.settings:

• delete_api_settings (write): Delete a setting
• create_or_update_api_settings (write): Create or update a setting
• list_all_api_settings (read): List all the settings
• list_public_api_settings (read): List all public settings

Resource files:

• retrieve_temp_url_files (read): Get temporary URL by file ID