How to Use the Marchex MCP in LlamaIndex

Q: How do I configure the Marchex MCP Server for LlamaIndex?

Install llama-index-tools-mcp via pip. Instantiate a BasicMCPClient with your endpoint, wrap it in an McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex query historical Marchex call data?

Yes. You can configure the agent to run searchcalls on a schedule. It ingests the historical call records and indexes them for semantic search alongside your other business documents.

Q: How does the agent handle large campaign lists?

The system uses listcampaigns to pull the directory, then iterates through the IDs. You can apply an allowedtools filter to restrict the agent from pulling too much data at once.

Turn conversation intelligence into searchable knowledge. Connect the Marchex MCP Server to LlamaIndex to query call analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marchex MCP to LlamaIndex

Create your Vinkius account to connect Marchex 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 Marchex with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Marchex data with LlamaIndex

Stop treating API endpoints like simple calculators. By connecting this MCP Server, LlamaIndex ingests your raw telecom data and transforms it into a queryable vector space. You build RAG applications that actually understand your marketing performance based on hard numbers. The integration maps directly to your existing index structure. Your setup calls `list_campaigns` and `get_campaign_details`, then chunks that metadata into searchable nodes. When a user asks about last quarter's ad spend, the engine retrieves facts instead of hallucinating.

Ground answers in real call metrics

Traditional RAG fails when it relies entirely on static PDFs. You need live operational data to answer serious business questions. The engine uses `get_call_analytics` to pull fresh volume and duration stats straight from the source. The agent combines these real-time metrics with your historical indexes. If a manager asks why lead quality dropped, the system runs `search_calls` to find the exact interactions dragging down the average. It grounds every response in actual conversation data.

Map your telecom infrastructure

Complex account hierarchies confuse standard LLMs. You have to feed them the exact structure of your tracking numbers and users to get accurate answers. The agent runs `list_accounts` and `list_users` to build a topological map of your organization. It stores this hierarchy in the knowledge base. When someone needs to audit a specific tracking line, the system queries `list_numbers` and `get_number_details` to verify the routing configuration. The AI knows exactly who owns which phone number.

Setup guide

Set up Marchex 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 Marchex 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 Marchex tools.",
)
response = await agent.run("List recent Marchex 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 Marchex. 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 Marchex 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 Marchex MCP in LlamaIndex

Install `llama-index-tools-mcp` via pip. Instantiate a `BasicMCPClient` with your endpoint, wrap it in an `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

Yes. You can configure the agent to run `search_calls` on a schedule. It ingests the historical call records and indexes them for semantic search alongside your other business documents.

The system uses `list_campaigns` to pull the directory, then iterates through the IDs. You can apply an `allowed_tools` filter to restrict the agent from pulling too much data at once.

No, because the RAG pipeline grounds its answers in live API responses. When you ask about billing, the agent explicitly calls `get_account_details` and reads the exact JSON payload before responding.

Security is built into the architecture. When the MCP Server processes requests for `list_numbers` and associated routing data, it operates strictly within an isolated sandbox environment. The tokenized endpoint ensures your infrastructure details never leak into public training sets.

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