About MCP-AIVA
MCP-AIVA is an MCP server for the TM Forum AIVA AI Assistant, helping users explore TM Forum Open APIs, standards, and implementation practices. Built-in prompts support domain-specific and API-level queries.
Key features
- 01Query TM Forum Open APIs
- 02Find APIs for a specific domain
- 03Get API capability details
- 04Explore standards and practices
- 05Use built-in prompts
Use cases
- 01List Open APIs and their purposes
- 02Identify APIs required by a standard
- 03Review TMF620 capabilities and practices
MCP support
MCP-AIVA provides TM Forum API and standards queries as an MCP server, with built-in prompts for common information requests.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP-AIVA
MCP server for the TM Forum AIVA AI Assistant
To use this locally with Claude Desktop, use the settings:
{
"mcpServers": {
"aiva": {
"command": "uv",
"args": [
"--directory",
"FULL_PATH_TO/MCP-AIVA",
"run",
"aiva-mcp-server.py"
]
}
}
}
Example Prompts
This MCP server provides several built-in prompts that you can use:
- Get a list of all TM Forum Open APIs:
List all the TM Forum Open APIs and their main purposes.
- Query APIs for a specific area:
What specific TM Forum API are required to implement the TM Forum Wholesale Broadband standard?
- Get detailed information about specific APIs:
What are the key features and capabilities of TMF620 Product Catalog Management API?
- Get information about TM Forum standards:
What specific TM Forum APIs are required to implement the TM Forum Wholesale Broadband standard?
- Get implementation best practices:
What are the best practices for implementing TMF620 Product Catalog Management API?
Debugging
For debugging, you can execute using the MCP Inspector with:
npx @modelcontextprotocol/inspector uv --directory FULL-PATH-TO/MCP-AIVA/ run aiva-mcp-server.py
Example Outputs
Here are example outputs in both Claude desktop and VSCode:



Comments
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.