How to Use the KnowFirst MCP in LlamaIndex

Q: Is it difficult to add KnowFirst tools to a LlamaIndex agent?

No, it's straightforward. You wrap the client in a McpToolSpec and call totoollistasync(). LlamaIndex handles the conversion, so your agent can immediately use tools like searchintelligenceentities.

Q: Can I control which KnowFirst tools my LlamaIndex agent can access?

Yes, the McpToolSpec has an allowedtools filter. You can give one agent access to only getmarketintelligencetrends while another, more privileged agent can also use auditentitychanges.

Turn live KnowFirst intelligence into a searchable knowledge base with LlamaIndex, so your RAG apps answer questions with real data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KnowFirst MCP to LlamaIndex

Create your Vinkius account to connect KnowFirst 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 KnowFirst with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Self-Updating Knowledge Base

Don't just get data; index it. With LlamaIndex, the output from KnowFirst tools like `get_entity_profile` and `get_market_intelligence_trends` is automatically fed into a vector index. Now your application has a memory of past intelligence reports. You can set up an agent that periodically calls `get_market_intelligence_trends` for the 'Tech' sector and adds the results to your knowledge base. When a user asks 'what happened in tech last quarter?', the answer comes from your indexed, factual data, not a guess from the LLM.

Query Your MCP Server History with LlamaIndex

LlamaIndex turns API calls into queryable events. After running a complex investigation using `search_intelligence_entities` and `get_entity_connections`, you can ask your index questions about the investigation itself. For example, 'Which data sources did we consult when researching company X?'. This is powerful for analysis and compliance. Your agent can build a graph of connections using `get_entity_connections`, index the results, and then answer natural language questions about that graph. The context isn't lost after the API call finishes. It becomes a permanent, searchable asset.

Ground Responses in Verifiable Data

Connect your agent's brain to a real-world data feed. A LlamaIndex agent can be configured to first search its indexed KnowFirst data before trying to answer a question. This ensures responses are grounded in data you've already vetted. For instance, if a user asks about a company's history, the agent can pull from indexed `audit_entity_changes` calls. It can even cite its sources by retrieving the original data from `list_entity_data_points`, giving you trustworthy answers with a clear data lineage.

Setup guide

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

LlamaIndex stores the results of your KnowFirst API calls in a vector index. This lets you perform semantic searches over all the data you've ever retrieved, asking questions in plain English instead of making new API calls every time.

Yes. You can index your private PDFs and documents alongside live data pulled from KnowFirst's `get_entity_profile` tool. Your agent then queries this unified index to get a complete picture.

No, it's straightforward. You wrap the client in a `McpToolSpec` and call `to_tool_list_async()`. LlamaIndex handles the conversion, so your agent can immediately use tools like `search_intelligence_entities`.

Yes, the `McpToolSpec` has an `allowed_tools` filter. You can give one agent access to only `get_market_intelligence_trends` while another, more privileged agent can also use `audit_entity_changes`.

Your API requests for entity profiles, connections, and market trends are sent over a TLS-encrypted connection to Vinkius. The data is processed in a dedicated, isolated environment that is destroyed after your session. Vinkius infrastructure is zero-trust and doesn't log the content of your API calls.

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