How to Use the Crisp MCP in LlamaIndex

Q: How do I connect Crisp to my LlamaIndex pipeline?

Install llama-index-tools-mcp and initialize the MCP client with your Vinkius Crisp URL. Pass the McpToolSpec to your FunctionAgent to start querying Crisp data.

Q: Can I index Crisp visitor profiles for semantic search in LlamaIndex?

Yes, you can use listvisitors to pull Crisp user records and index them into LlamaIndex. This lets you run semantic queries over your customer base to find patterns.

Q: Does the search engine support real-time updates of conversations?

You can build a LlamaIndex agent loop that regularly calls listconversations to fetch new threads. The pipeline then indexes the fresh Crisp messages to keep your search results current.

Index live Crisp support chats and visitor profiles into LlamaIndex vector stores for real-time customer RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crisp MCP to LlamaIndex

Create your Vinkius account to connect Crisp 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 Crisp with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Crisp chat histories for LlamaIndex RAG

The `get_messages` tool extracts the full text of your active Crisp support conversations for LlamaIndex ingestion. Your pipeline converts these messages into embeddings to store them in your vector database. Your LlamaIndex query engine searches these indexed Crisp conversations to draft replies. This grounds your agent's answers in actual historical support resolutions instead of hallucinations.

Ground query engines in Crisp visitor profiles

The `get_visitor_profile` tool fetches verified user details from Crisp to ground your LlamaIndex query engine. This MCP Server integration ensures your RAG pipeline knows the user's tier before generating a response. Filtering vector search results becomes simple when using this Crisp metadata. This restricts search results to documentation that matches the visitor's specific subscription level.

Sync active conversations with your index

The `list_conversations` tool retrieves your active Crisp inbox queue to keep your LlamaIndex vector store current. This Crisp MCP tool allows your pipeline to run scheduled syncs of live support activity. Your agent calls `send_message` to update the Crisp thread once the LlamaIndex query engine finds the correct answer. This turns your static vector index into an active support helper.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the MCP client with your Vinkius Crisp URL. Pass the `McpToolSpec` to your `FunctionAgent` to start querying Crisp data.

Yes, you can use `list_visitors` to pull Crisp user records and index them into LlamaIndex. This lets you run semantic queries over your customer base to find patterns.

You can build a LlamaIndex agent loop that regularly calls `list_conversations` to fetch new threads. The pipeline then indexes the fresh Crisp messages to keep your search results current.

Yes, use the allowed tools filter in your MCP tool spec to restrict access. You can allow read tools like `get_messages` while blocking write tools like `send_message`.

Vinkius runs the Crisp MCP Server in a secure, ephemeral sandbox. Your visitor profiles and conversation logs are processed in memory and never cached on Vinkius 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