
Omilia MCP Tools
A set of tools for working with Omilia Cloud Platform that helps manage miniapps, orchestrator apps, and dialog logs through an MCP server.
README
Omilia MCP Tools
This repository contains a set of tools for working with the Omilia Cloud Platform (OCP). These utilities help manage miniapps, orchestrator apps, and dialog logs.
Tools Overview
- search_miniapps: Search for miniapps by name or keyword.
- get_miniapp: Retrieve details for a specific miniapp using its ID.
- set_miniapp_prompt: Update prompts (welcome, error, reaction messages) for a miniapp.
- get_dialog_logs: Fetch logs for a specific dialog session.
- search_orchestrator_apps: Search for Orchestrator apps by keyword.
- get_orchestrator_app: Retrieve the canvas (nodes and edges) for an Orchestrator app by ID.
- search_dialog_logs: Search dialog logs with various filters (date, app, region, etc.).
- search_numbers: Search for phone numbers with optional search term.
- search_variable_collections: Search variable collections with optional search term.
- get_collection_variables: Get a list of all variables in a collection by ID.
Installation
- Make sure you have Python 3.10 or newer installed.
- Install uv.
- Clone this repository and navigate to the project directory.
- Copy the file
.env.example
to.env
and set the appropriate values. - Test if the istallation is correct by running
uv run mcp dev src/main.py
. This should open the mcp development server. Click on connect and try it out.
Usage
You can use these tools in two main ways:
1. Self-hosting (MCP Python SDK)
You can run your own MCP server using the official Python MCP SDK. This is the most flexible option and is recommended for advanced users. For full instructions, see the MCP Python SDK README.
2. Local usage with Gemini CLI, Cursor, or Claude Desktop
You can also use this project locally with any MCP-compatible client, such as:
Each of these clients allows you to connect to local MCP servers. For more information, see their respective documentation:
- Gemini CLI: Configuring custom MCP servers
- Claude Desktop: MCP servers
- Cursor: Configuring custom MCP servers
Configuring MCP Servers
To use this project with any of the above clients, you need to configure your MCP servers. For example, you can use the following mcp.json
configuration (place it in the appropriate config directory for your client):
{
"mcpServers": {
"Omilia MCP": {
"command": "uv",
"args": [
"run",
"--with",
"mcp",
"mcp",
"run",
"<path_to_cloned_repository>>/omilia-mcp/src/main.py"
],
"env": {
"PATH": "<depending on how you installed the needed tools you may need to paste your PATH here>"
}
}
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.