How to Use the Mozscape MCP in LlamaIndex

Q: How do I store Mozscape metrics in a LlamaIndex vector store?

You run the MCP tools like v2urlmetrics to retrieve the raw JSON data. LlamaIndex then parses this payload into document nodes, embeds them, and saves them to your vector database.

Q: Can LlamaIndex query Mozscape data without making new API calls?

Yes, if you index the outputs of tools like listlinkingdomains first. The agent will search your local vector index before deciding if it needs to hit the live MCP endpoint for fresh data.

Q: Does the LlamaIndex integration support bulk Mozscape URL lookups?

Yes, you can use fetchmultiplesitemetrics to pull data for up to 50 URLs at once. LlamaIndex can then batch-index these metrics to quickly build out your local knowledge base.

Q: How do I see if a specific backlink is still active?

You can have the agent run v2linkstatus or fetchlinkstatus. It checks the live Moz index to confirm if the link is active and passing equity.

Turn Mozscape link data into queryable vector indexes using LlamaIndex for RAG-driven SEO audits.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mozscape MCP to LlamaIndex

Create your Vinkius account to connect Mozscape 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 Mozscape with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live LlamaIndex RAG pipelines with Mozscape

Using this MCP Server, LlamaIndex takes the output from tools like `v2_top_pages` or `list_linking_domains` and writes it directly into your index. This means your agent answers questions based on actual, live SEO metrics rather than outdated training data. When you query your index about competitor backlink profiles, the system retrieves cached results from previous runs of `v2_link_intersect`. You avoid redundant API calls and get grounded, hallucination-free answers.

Search your link profile with natural language

This MCP Server lets LlamaIndex ingest massive lists of linking domains. By running `list_anchor_text` and indexing the results, you can query your link profile using natural language to find contextually relevant partners. The framework stores these relationships semantically. Instead of sorting spreadsheets, you ask your agent which domains linking via `filter_links_by_domain` have the highest contextual relevance to your niche.

Build a queryable history of brand authority

Track how your search footprint changes over time without manual exports. Your LlamaIndex agent can periodically trigger `fetch_brand_authority` and `fetch_histories` to update its internal knowledge graph. This creates a historical record of your SEO performance. When you ask the agent for a status update, it queries this local index to compare past and present Domain Authority.

Setup guide

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

You run the MCP tools like `v2_url_metrics` to retrieve the raw JSON data. LlamaIndex then parses this payload into document nodes, embeds them, and saves them to your vector database.

Yes, if you index the outputs of tools like `list_linking_domains` first. The agent will search your local vector index before deciding if it needs to hit the live MCP endpoint for fresh data.

Yes, you can use `fetch_multiple_site_metrics` to pull data for up to 50 URLs at once. LlamaIndex can then batch-index these metrics to quickly build out your local knowledge base.

You can have the agent run `v2_link_status` or `fetch_link_status`. It checks the live Moz index to confirm if the link is active and passing equity.

The raw backlink profiles and domain metrics stay in your local vector database. Our secure sandbox environment only acts as a stateless MCP conduit, ensuring your proprietary link data is never exposed.

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