How to Use the Cosmic MCP in LlamaIndex

Q: Does the Cosmic MCP Server support LlamaIndex semantic search?

It provides the raw data streams via tools like getsingleobject and listuploadedmedia. LlamaIndex then embeds and indexes this data so you can search it semantically.

Q: How do I prevent my index from getting cluttered with deleted assets?

You can keep your index fresh by running wipemediaasset or wipecmsobject through your agent, then triggering a re-index of your active bucket objects.

Index your Cosmic content directly into LlamaIndex vector stores for grounded, real-time RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cosmic MCP to LlamaIndex

Create your Vinkius account to connect Cosmic 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 Cosmic with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Cosmic schemas for accurate RAG queries

Feed your vector index with live structural data by running `list_schema_types` and `get_schema_details`. LlamaIndex stores these rules so your query engine knows exactly how your headless content is modeled. This prevents your agent from hallucinating field names when it generates new content. It searches the indexed schema rules first, ensuring any subsequent tool calls match your actual database constraints.

Semantic search over your Cosmic media library

Use `list_uploaded_media` and `get_media_asset` to pull image metadata and index it for semantic retrieval. Your LlamaIndex agent can search past media uploads using natural language queries instead of digging through IDs manually. By indexing these assets, the agent quickly finds the exact image needed for a new draft, avoiding duplicate uploads and keeping your storage clean.

Ground LlamaIndex decisions with live Cosmic logs

This MCP Server lets your agent query live cloud logs using `get_single_object` and `list_bucket_objects`. The retrieved JSON payloads are indexed instantly, giving your agent a searchable history of recent content updates. Your pipeline can compare current drafts against indexed historical data, making sure updates are consistent with previous editorial decisions.

Setup guide

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

Set up the BasicMCPClient with your Vinkius URL and convert it to a tool spec. Your LlamaIndex agent can then run `list_bucket_objects` to pull and index your content.

Yes. The agent can query the index to find the right document ID, then call `patch_cms_object` to update the draft values with grounded information.

It provides the raw data streams via tools like `get_single_object` and `list_uploaded_media`. LlamaIndex then embeds and indexes this data so you can search it semantically.

You can keep your index fresh by running `wipe_media_asset` or `wipe_cms_object` through your agent, then triggering a re-index of your active bucket objects.

Your Cosmic API keys and bucket credentials never pass through the vector index. They are held securely within the Vinkius sandbox, ensuring only sanitized JSON payloads reach your local environment.

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