Folderr

A Model Context Protocol (MCP) server that provides tools to interact with Folderr's API
  • javascript

2

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

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

Folderr MCP Server lets you authenticate with Folderr and manage Folderr Assistants through a dedicated MCP interface. It provides tools to log in, use API tokens, list available assistants, and ask questions to a specific assistant, all from your MCP client.

How to use

You connect to Folderr MCP Server from your MCP client and choose an authentication method to begin. Use the login tool with an email and password for interactive sessions, or use set_api_token to operate in automated or long-running processes. After you are authenticated, you can list your assistants and ask questions to a chosen assistant. All actions require you to be authenticated.

Practical usage patterns include authenticating once, then performing repeated assistant interactions without re-authenticating. When you need automated access, prefer the API token method and store the token securely for future requests.

How to install

Prerequisites you need before installing include a Node.js runtime and npm. Ensure Node.js is installed on your machine, then install and configure the MCP server as part of your MCP settings.

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

Alternative local runtime via a built server If you prefer to run a local server instance directly, build the server first and then start it with Node.

npm install
npm run build

Start the local server using the built file path shown in the configuration example.

node /path/to/folderr-server/build/index.js

Configuration and runtime options

The server stores its configuration in a config.json file, including the base URL for the Folderr API and the authentication token obtained through login or an API token. Use one of the authentication methods to obtain and save your token for subsequent requests.

Authentication tokens are saved automatically after a successful login or token setup and are used for all subsequent requests. All assistant-related tools require authentication before use.

Authentication flow

Choose one of the following to authenticate with Folderr MCP Server.

  1. Login with Email/Password
  2. API Token Authentication
{
  "name": "login",
  "arguments": {
    "email": "user@example.com",
    "password": "your-password"
  }
}
{
  "name": "set_api_token",
  "arguments": {
    "token": "your-api-token"
  }
}

Tools and usage

The server provides tools to manage and interact with Folderr Assistants.

List Assistants returns all available assistants for the authenticated user, and Ask Assistant sends a question to a specific assistant and returns the response.

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

Error handling and troubleshooting

Common error scenarios include authentication failures, invalid requests, API errors, and network issues. Typical messages include Not logged in, Login failed, Failed to list assistants, and Failed to ask assistant. Ensure an valid authentication token is present for all operations.

Development

To build the server for development or customization, install dependencies and build the project.

npm install
npm run build

Available tools

login

Authenticate with email and password to obtain a session token for subsequent requests.

set_api_token

Set a persistent API token for automated or long-running processes.

list_assistants

Retrieve a list of all assistants available to the authenticated user.

ask_assistant

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

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational