mcpField
D
dryai-mcp-server

dryai-mcp-server

Local
github.com/UnitaryLabsMemory & Knowledge0Updated 68w ago
Repository

About dryai-mcp-server

dryai-mcp-server connects Claude to Dry smartspaces to create and store memories and query their data. It is for users who keep structured information in Dry spaces.

Key features

  1. 01Create and store memories
  2. 02Query information in a smartspace
  3. 03Expose configured smartspaces as tools

Use cases

  1. 01Save structured memories during conversations
  2. 02Ask questions about information in a Dry smartspace

MCP support

The MCP server connects Claude to Dry smartspaces and makes configured spaces available as tools for asking questions and adding items.

#dryai#mcp-server#ai-assistant

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dryai": {
      "command": "npx",
      "args": [
        "-y",
        "@jrscally/dryai-mcp-server"
      ],
      "env": {
        "MCP_TOKEN": "<MCP_TOKEN>"
      }
    }
  }
}
Run commandnpx -y @jrscally/dryai-mcp-server
Environment variables to set
MCP_TOKENSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@jrscally/dryai-mcp-server

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

dryai-mcp-server

The Dry.ai Model Context Protocol (MCP) server enables seamless integration between Claude and your Dry smartspaces, turning conversations into persistent, structured data. Currently, you can use this server to create and store memories and query the information in your database (smartspace).

Begin by signing up for our alpha here

Watch a video of Dry in action here

Steps to Configure your User

  1. Log in to Dry.ai and navigate to your Dry Profile.

    Screenshot 2025-04-11 at 12 15 17 PM

  2. Generate an MCP Token from your profile. Make note of this token, as you will use it later. Select smartspacess that you are a member of which have been configured for MCP access. See

image

Steps to Configure a Smartspace for MCP

  1. Open the settings for the smartspace that you want to connect. Click the "Chat" tab and show More Options

    image

  2. Click the toggle to enable MCP on the smartspace and provide a description that will let Claude know when you want to send questions to this smartspace.

Steps to connect Dry to Claude Desktop

  1. Install Node.js (v18.x or later) Download from: https://nodejs.org/ Verify installation by opening Command Prompt (CMD) and running: node --version

  2. Modify your claude_desktop_config.json file to include the following configuration:

  {
     "mcpServers": {
       "dryai": {
        "command": "npx",
        "args": ["-y", "@jrscally/dryai-mcp-server"],
        "env": {
           "MCP_TOKEN": "<MCP TOKEN>"
        }
     }
     }
  }

You can access this by visiting Claude->Settings->Developer and pressing "Edit Config"

  1. Run Claude Desktop - it will connect to Dry and all of your configured smartspaces will appear as tools to ask questions and add items. Every time you create or install new memory types in your Dry space, you'll need to restart your Claude desktop app to sync its tools with the latest state of your Dry smartspace.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.