How to Use the Namsor MCP in LlamaIndex

Q: How do I add Namsor tools to my LlamaIndex agent?

Install llama-index-tools-mcp and instantiate the McpToolSpec with your server endpoint. It fetches the available tools, which you can then pass directly to your agent.

Q: Can I filter which Namsor tools my LlamaIndex agent can use?

Yes. The McpToolSpec constructor accepts an allowedtools argument. This lets you give an agent access to only predictgender and predictcountry, for instance, to limit its scope.

Q: Does this MCP server integrate with LlamaIndex's async features?

It does. You can use await mcptoolspec.totoollistasync() to load the tools without blocking your event loop. This fits right into modern, async-first Python applications.

Enrich your LlamaIndex knowledge base with real-time name analytics for smarter RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Namsor MCP to LlamaIndex

Create your Vinkius account to connect Namsor to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Namsor with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Name Insights into Searchable Knowledge

This is about more than one-off API calls. With LlamaIndex, the output from Namsor's tools becomes part of a structured, searchable knowledge base. Run a list of names through `predict_ethnicity` or `predict_origin`, and the results are indexed automatically. Now you can ask questions in plain English like, "What's the distribution of predicted origins for our new users this month?" Your query engine will pull the answer directly from the indexed Namsor data, grounding the response in facts, not guesswork.

Ground Your LlamaIndex Agent in API Data

Connect your agent to a live source of demographic data. Instead of only relying on static documents, your RAG application can use this MCP server to fetch fresh information with tools like `predict_country` and `predict_gender`. This means your agent can answer questions by combining document context with live API calls. For example, it could find a user in your documents and then use `parse_full_name` on the fly to answer a specific question about their name structure.

Query Your Tool Call History

LlamaIndex's real power is its memory. Every time you use a Namsor tool, the input and output can be stored in a vector index. This creates a historical record of all your analyses. You can later perform semantic searches over that history. Ask, "Show me all the names that were difficult to predict a gender for," and LlamaIndex can retrieve the past API calls where `predict_gender` returned a low confidence score.

Setup guide

Set up Namsor MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Namsor MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Namsor tools.",
)
response = await agent.run("List recent Namsor data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Namsor. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Namsor now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Namsor MCP in LlamaIndex

Install `llama-index-tools-mcp` and instantiate the `McpToolSpec` with your server endpoint. It fetches the available tools, which you can then pass directly to your agent.

Yes. The `McpToolSpec` constructor accepts an `allowed_tools` argument. This lets you give an agent access to only `predict_gender` and `predict_country`, for instance, to limit its scope.

After calling a tool, take the resulting data and load it into your preferred index using LlamaIndex's standard data connectors. This makes the demographic information from Namsor instantly queryable for your RAG setup.

It does. You can use `await mcp_tool_spec.to_tool_list_async()` to load the tools without blocking your event loop. This fits right into modern, async-first Python applications.

Only the specific names required for a tool call are transmitted. Your Vinkius MCP server instance is isolated and the connection is authenticated with your token. The name data is used for the immediate prediction and is not logged or retained.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript