Skip to main content
Glama
Folderr

Folderr

Official
by folderr-tech

Folderr MCP Server

A Model Context Protocol (MCP) server that provides tools to interact with Folderr's API, specifically for managing and communicating with Folderr Assistants.

Installation

Add to your MCP Settings

{
  "mcpServers": {
    "folderr": {
      "command": "npx",
      "args": ["-y", "@folderr/folderr-mcp-server"]
    }
  }
}

Related MCP server: Filesystem MCP Server

Features

The server provides the following tools:

Authentication

Two methods of authentication are supported:

  1. Login with Email/Password

    {
      "name": "login",
      "arguments": {
        "email": "user@example.com",
        "password": "your-password"
      }
    }
  2. API Token Authentication

    {
      "name": "set_api_token",
      "arguments": {
        "token": "your-api-token"
      }
    }

    API tokens can be generated from the Folderr developers section. This method is recommended for automated or long-running processes.

Assistant Management

  1. List Assistants

    {
      "name": "list_assistants",
      "arguments": {}
    }

    Returns a list of all available assistants for the authenticated user.

  2. Ask Assistant

    {
      "name": "ask_assistant",
      "arguments": {
        "assistant_id": "assistant-id",
        "question": "Your question here"
      }
    }

    Send a question to a specific assistant and receive their response.

Configuration

The server stores its configuration in a config.json file, which includes:

  • Base URL for the Folderr API

  • Authentication token (from login or API key)

Error Handling

The server provides detailed error messages for common scenarios:

  • Authentication failures

  • Invalid requests

  • API errors

  • Network issues

Development

To build the server:

npm install
npm run build

Usage in MCP Settings

Add the following to your MCP settings configuration:

{
  "mcpServers": {
    "folderr": {
      "command": "node",
      "args": ["/path/to/folderr-server/build/index.js"]
    }
  }
}

Authentication Flow

  1. Either:

    • Use the login tool with email and password

    • Use the set_api_token tool with an API token from Folderr's developers section

  2. The authentication token is automatically saved and used for subsequent requests

  3. All assistant-related tools require authentication before use

Error Messages

Common error messages and their meanings:

  • "Not logged in": No authentication token is set

  • "Login failed": Invalid credentials

  • "Failed to list assistants": Error retrieving assistant list

  • "Failed to ask assistant": Error sending question to assistant

Available Tools

7 tools
ask_assistantC

Ask a question to a specific assistant

Inputs: assistant_id (required), question (required).

execute_workflowC

Execute a workflow with the required inputs

Inputs: workflow_id (required), inputs (required).

get_workflow_inputsC

Get the required inputs for a workflow

Inputs: workflow_id (required).

list_assistantsB

List all available assistants

Inputs: no named parameters.

list_workflowsB

List all available workflows

Inputs: no named parameters.

loginC

Login to Folderr with email and password

Inputs: email (required), password (required).

set_api_tokenA

Set an API token for authentication (alternative to login)

Inputs: token (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: authentication (login, set_api_token), listing resources (list_assistants, list_workflows), workflow operations (get_workflow_inputs, execute_workflow), and assistant interaction (ask_assistant). The descriptions make it easy to differentiate between them.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with snake_case throughout (e.g., ask_assistant, execute_workflow, list_workflows). The naming is predictable and readable, with no deviations in style or convention.

    Tool Count5/5

    With 7 tools, the server is well-scoped for managing assistants and workflows in Folderr. Each tool serves a clear function, covering authentication, listing, and execution without being overly sparse or bloated.

    Completeness4/5

    The toolset covers core workflows: authentication, listing assistants/workflows, getting workflow inputs, and executing workflows. A minor gap is the lack of tools for creating or managing assistants/workflows, but the provided tools support basic interaction and execution effectively.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that extends AI capabilities by providing file system access and management functionalities to Claude or other AI assistants.
      277 npm
      5
      -
    • F
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server implementation that can be run directly or through Docker, enabling AI assistants to interact with external systems through the MCP standard.
      2
      -