DreamingAI MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DreamingAI MCP Server create a new agent for summarizing emails"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is a Model Context Protocol (MCP) server that provides tools for interacting with the DreamingAI platform. It allows AI clients (like Claude or Cursor) to manage conversations, intelligent agents, prompt templates, and plugins within your enterprise AI ecosystem.
Features
Conversation Management: Full control over chat sessions and message history.
Agent Lifecycle: Create and manage AI agents with custom roles and behaviors.
Prompt Engineering: CRUD support for prompt templates with variable support.
Multi-Model Orchestration: List, inspect, and switch between AI models.
Extensible Plugins: Management of marketplace plugins for enhanced capabilities.
Related MCP server: Jilebi
How to Use
You can easily add this MCP server to your favorite AI client. You will need your DreamingAI API Key and your Base URL (usually https://dreamingai.exmay.com).
1. In Claude Desktop
If you use Claude Desktop, follow these steps:
Open your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add the following to the
mcpServerssection:
{
"mcpServers": {
"dreamingai": {
"command": "npx",
"args": ["-y", "@shivanshu814/dreamingai-mcp-server"],
"env": {
"DREAMINGAI_API_KEY": "YOUR_ACTUAL_API_KEY_HERE",
"DREAMINGAI_BASE_URL": "https://dreamingai.exmay.com"
}
}
}
}2. In Cursor
If you use Cursor:
Open Cursor Settings -> Models -> MCP.
Click + Add New MCP Server.
Name:
DreamingAIType:
commandCommand:
npx -y dreamingai-mcp-serverClick Add.
Note: You must have Node.js installed on your computer.
Configuration Details
Variable | Description | Default |
| Required. Your DreamingAI API key. | — |
| The URL of your DreamingAI instance. |
|
| Application identifier for the client. |
|
Available Tools
Dialogue (chat)
list_conversations: Retrieve all active chat sessions.create_conversation: Start a new session.send_message: Interact with the AI.get_conversation_history: Fetch past messages.delete_conversation: Delete session data.
Agents (agents)
list_agents: Search configured AI agents.get_agent: View agent details.create_agent: Define new agent personas.update_agent/delete_agent: Manage existing agents.
Templates (prompts)
list_prompts/get_prompt: Access the prompt library.create_prompt: Save new templates with variables.update_prompt/delete_prompt: Maintain prompt library.
Models & Plugins
list_models/switch_model: Manage model switching.list_plugins/install_plugin: Manage plugin lifecycle.activate_plugin/deactivate_plugin: Control plugin availability.
Local Development
Clone the repository:
git clone https://github.com/shivanshu814/dreamingai-mcp-server.gitNavigate to the project directory:
cd dreamingai-mcp-serverInstall dependencies:
npm installBuild the server:
npm run buildRun locally:
node dist/index.js
License
Apache-2.0 © GitCoffee Team.
Available Tools
23 toolsactivate_pluginA
Activate an installed plugin in DreamingAI
Inputs: pluginId (required).
create_agentA
Create a new AI agent in DreamingAI with custom role and behavior
Inputs: name (required), modelId, maxTokens, description, +3 more.
create_conversationB
Create a new chat conversation/session in DreamingAI
Inputs: title, agentId, modelId.
create_promptC
Create a new prompt template in DreamingAI
Inputs: title (required), content (required), tags, category, +2 more.
deactivate_pluginB
Deactivate an active plugin in DreamingAI
Inputs: pluginId (required).
delete_agentB
Delete an AI agent from DreamingAI
Inputs: agentId (required).
delete_conversationB
Delete a chat conversation/session from DreamingAI
Inputs: conversationId (required).
delete_promptB
Delete a prompt template from DreamingAI
Inputs: promptId (required).
get_agentA
Get details of a specific AI agent in DreamingAI
Inputs: agentId (required).
get_conversation_historyB
Get the message history for a specific conversation in DreamingAI
Inputs: conversationId (required), page, pageSize.
get_modelA
Get details and capabilities of a specific AI model in DreamingAI
Inputs: modelId (required).
get_promptA
Get details of a specific prompt template in DreamingAI
Inputs: promptId (required).
install_pluginB
Install a plugin from the DreamingAI marketplace
Inputs: pluginId (required).
list_agentsB
List all available AI agents in DreamingAI
Inputs: page, keyword, pageSize.
list_conversationsC
List all chat conversations/sessions in DreamingAI
Inputs: page, pageSize.
list_modelsA
List all available AI models and platforms in DreamingAI
Inputs: platform.
list_pluginsB
List all available plugins in DreamingAI marketplace
Inputs: status, keyword, category.
list_promptsB
List all prompt templates in DreamingAI
Inputs: tag, page, keyword, category, +1 more.
send_messageB
Send a message to a DreamingAI conversation and get an AI response
Inputs: message (required), conversationId (required), modelId.
switch_modelC
Switch the active AI model for conversations in DreamingAI
Inputs: modelId (required), conversationId.
uninstall_pluginB
Uninstall a plugin from DreamingAI
Inputs: pluginId (required).
update_agentA
Update an existing AI agent's configuration in DreamingAI
Inputs: agentId (required), name, modelId, maxTokens, +4 more.
update_promptA
Update an existing prompt template in DreamingAI
Inputs: promptId (required), tags, title, content, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 23 tools
Each tool targets a distinct resource and action, with clear separation between prompts, conversations, agents, models, and plugins. No two tools appear to perform the same operation, and even similar verbs like 'list' and 'get' are differentiated by whether they return all items or a single item.
All tool names follow a consistent verb_noun pattern in snake_case, with verbs like get, list, create, update, delete, send, switch, install, activate, deactivate, and uninstall. The pattern is uniform across all five domains, making the API predictable and easy to navigate.
With 23 tools, the server is slightly above the typical 3-15 tool range, but this is justified by the breadth of functionality covering prompts, conversations, agents, models, and plugins. Each tool corresponds to a meaningful operation, and the count feels appropriate for the comprehensive scope.
The tool surface provides complete CRUD and lifecycle coverage for prompts, agents, and plugins, plus conversation management including history and messaging, and model listing/selection. There are no obvious dead ends; all core workflows for managing an AI platform are represented.
Maintenance
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceA sophisticated MCP server providing advanced memory capabilities with RAG, hallucination detection, and enterprise-grade AI infrastructure for intelligent agent ecosystems.-
- AlicenseNot gradedqualityBmaintenanceA plugin-based MCP server that enables AI assistants to interact with external systems through custom tools, resources, and prompts.4AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that gives AI assistants access to a multi-agent business operations platform with specialized AI services covering real estate, legal, translation, research, content creation, training, and more.69 npmMIT
- AlicenseNot gradedqualityCmaintenanceMCP server that provides AI agents with persistent memory, cross-agent sharing, and context management, enabling them to remember conversations, track complex tasks, and evolve skills across tools.2MIT