How to Use the Frontify MCP in LlamaIndex

Q: How do I index Frontify asset metadata in LlamaIndex?

Use the McpToolSpec to load the getprojectassets tool from this MCP Server. You can then query the tool and load the returned asset records directly into your vector store.

Q: Can LlamaIndex agents update Frontify metadata?

Yes. Your agent can use patchassetmetadata to write new tags directly to your assets based on semantic analysis of the file contents.

Q: How does LlamaIndex prevent hallucinations when querying Frontify?

LlamaIndex queries the executegraphqlpayload tool to get fresh data directly from your DAM. This ensures your agent relies on real-time API responses rather than outdated training data.

Q: Can I filter which Frontify tools LlamaIndex can access?

Yes, you can use the allowedtools filter in the MCP client setup. This lets you restrict the agent to read-only tools like listnativebrands while blocking destructive tools like wipemediaasset.

Index your Frontify brand assets and guidelines directly into LlamaIndex using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Frontify MCP to LlamaIndex

Create your Vinkius account to connect Frontify 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 Frontify with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index guidelines with LlamaIndex semantic search

The `list_brand_guidelines` tool lets you pull active documentation trees directly into your LlamaIndex pipelines. Your pipeline indexes these guidelines into a vector database, letting you perform semantic searches over brand rules instead of manual lookups. This indexing makes it easy to ground your RAG applications in official brand documentation. Your agent queries the index to answer design questions, ensuring every response matches your actual Frontify rules.

Index and search asset metadata semantically

The `get_project_assets` tool retrieves asset lists and metadata to build a searchable index of your media library. LlamaIndex stores these records, allowing your agent to find specific files using natural language queries instead of strict ID matches. You can also use `patch_asset_metadata` to update tags based on search insights. This creates a feedback loop where your index stays updated as your asset library grows and changes.

Monitor account limits with vector-grounded alerts

The `get_account_limits` tool provides real-time data on your asset storage and usage boundaries. Your LlamaIndex agent can index these limits to alert your team when storage capacity is nearly full. Keeping this data indexed prevents unexpected API failures during large uploads. Your system knows exactly when to pause ingestion based on current account constraints.

Setup guide

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

Use the McpToolSpec to load the get_project_assets tool from this MCP Server. You can then query the tool and load the returned asset records directly into your vector store.

Yes. Your agent can use patch_asset_metadata to write new tags directly to your assets based on semantic analysis of the file contents.

LlamaIndex queries the execute_graphql_payload tool to get fresh data directly from your DAM. This ensures your agent relies on real-time API responses rather than outdated training data.

Yes, you can use the allowed_tools filter in the MCP client setup. This lets you restrict the agent to read-only tools like list_native_brands while blocking destructive tools like wipe_media_asset.

The integration handles brand assets, metadata schemas, and project configurations. Your data is processed in a secure, zero-trust isolated V8 MCP sandbox that isolates your API token and prevents data leaks.

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