How to Use the N-Gram Frequency Engine MCP in LlamaIndex

Q: How do I configure the N-Gram Frequency Engine for LlamaIndex?

Run pip install llama-index-tools-mcp. Set up a BasicMCPClient, wrap it in an McpToolSpec, and call await mcptoolspec.totoollistasync(). Pass the resulting tools to your FunctionAgent.

Ground your LlamaIndex RAG pipelines in exact mathematical phrase counts instead of LLM approximations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect N-Gram Frequency Engine MCP to LlamaIndex

Create your Vinkius account to connect N-Gram Frequency Engine 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 N-Gram Frequency Engine with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Exact Phrase Frequencies

The `extract_ngram_frequencies` tool gives your LlamaIndex agents a deterministic foundation for semantic search. You pass a massive corpus into the tool, and it returns exact unigram, bigram, and trigram maps. Instead of just vectorizing raw text, your pipeline indexes these exact frequency distributions. When a user queries your knowledge base, the agent pulls hard data on phrase repetition rather than relying on fuzzy vector similarity alone.

Grounded RAG with MCP Server Data

`extract_ngram_frequencies` forces your LlamaIndex application to respect actual document statistics. An LLM cannot hallucinate a recurring theme if the frequency map proves that specific trigram only appears once. You inject the resulting JSON dictionary directly into your context window. The agent synthesizes answers based on mathematically proven word patterns, saving you thousands of tokens that would otherwise go to probabilistic summarization.

Query Past Extraction Sessions

The `extract_ngram_frequencies` tool outputs structured data that LlamaIndex instantly absorbs into its persistent index. You run this MCP Server across your weekly reports and store the resulting maps. Later, your FunctionAgent queries those historical configurations to track how specific bigrams trend over time. The math does not lie, and your RAG application now has a permanent record of exact phrasing shifts.

Setup guide

Set up N-Gram Frequency Engine 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 N-Gram Frequency Engine 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 N-Gram Frequency Engine tools.",
)
response = await agent.run("List recent N-Gram Frequency Engine 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 natural. 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 N-Gram Frequency Engine 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 N-Gram Frequency Engine MCP in LlamaIndex

Run `pip install llama-index-tools-mcp`. Set up a `BasicMCPClient`, wrap it in an `McpToolSpec`, and call `await mcp_tool_spec.to_tool_list_async()`. Pass the resulting tools to your `FunctionAgent`.

Yes. The tool returns a standard JSON frequency map. You convert that output into a Document object and index it directly alongside your raw text files.

LLMs are terrible at counting. When your user asks what phrases appear most often in a dataset, this MCP server provides the exact mathematical answer without burning inference tokens.

No. It provides a deterministic counterweight. You use vector search to find meaning, and you use the engine to prove exact textual repetition.

The engine processes raw corpus strings and nothing else. Vinkius isolates the execution in an ephemeral sandbox. The server computes the bigram and trigram counts, outputs the JSON, and wipes the memory state completely.

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