How to Use the Keap MCP in LlamaIndex

Q: How do I load Keap data into LlamaIndex?

Initialize BasicMCPClient and wrap it with McpToolSpec. Call await mcptoolspec.totoollistasync() and pass the tools to your FunctionAgent.

Q: Can LlamaIndex filter which Keap tools the agent sees?

Yes. Use the allowedtools parameter when setting up the spec. This restricts the agent to safe read-only operations like listusers if needed.

Q: Does LlamaIndex automatically sync new Keap contacts?

No. You write the ingestion script that periodically calls listcontacts. The framework then updates your vector store with the fresh records.

Q: Can I create new records from a RAG query?

If you expose createcontact to the agent, it can write back to the CRM. Most developers separate their read-only RAG index from active writing tools.

Q: What happens to my ecommerce data during indexing?

Order histories and billing amounts from listinvoices flow through an ephemeral connection. The MCP server requires a single endpoint token and maintains zero-trust architecture, meaning no financial data rests on middleman servers.

Connect your Keap MCP Server to LlamaIndex vector stores for grounded, semantic sales queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keap MCP to LlamaIndex

Create your Vinkius account to connect Keap 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 Keap with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize your sales pipeline

The Keap MCP integration feeds `list_opportunities` and `list_contacts` directly into your LlamaIndex document stores. Your agent pulls raw CRM data and converts it into searchable embeddings. When a user asks about Q3 pipeline risks, the query engine searches the index instead of guessing. You get answers grounded in actual sales stages rather than hallucinated projections.

Query LlamaIndex campaigns

RAG applications use `list_campaigns` to ingest your entire marketing history. The agent reads the setup, pulls associated metadata via `list_tags`, and indexes the relationships. You ask the engine which tags correlate with high-value deals. It cross-references the campaign index with data from `list_orders` to give you a factual answer.

Combine CRM data with external docs

Your setup pulls individual account details using `get_business_profile` and `get_contact`. It merges this structured API data with unstructured PDFs or call transcripts stored in your vector database. The resulting index knows both what the customer bought via `list_invoices` and what they complained about in support tickets. You build a single queryable interface for the entire customer lifecycle.

Setup guide

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

Initialize `BasicMCPClient` and wrap it with `McpToolSpec`. Call `await mcp_tool_spec.to_tool_list_async()` and pass the tools to your `FunctionAgent`.

Yes. Use the `allowed_tools` parameter when setting up the spec. This restricts the agent to safe read-only operations like `list_users` if needed.

No. You write the ingestion script that periodically calls `list_contacts`. The framework then updates your vector store with the fresh records.

If you expose `create_contact` to the agent, it can write back to the CRM. Most developers separate their read-only RAG index from active writing tools.

Order histories and billing amounts from `list_invoices` flow through an ephemeral connection. The MCP server requires a single endpoint token and maintains zero-trust architecture, meaning no financial data rests on middleman servers.

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