How to Use the Capsulink MCP in LlamaIndex

Q: How do I connect Capsulink to LlamaIndex?

Install llama-index-tools-mcp. Initialize BasicMCPClient with your Vinkius endpoint, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex query Capsulink click stats?

Yes. The agent uses getlinkdailystats to fetch the data, which you then embed into your index for natural language querying.

Q: Does LlamaIndex know which Capsulink folders exist?

It does if you run listlinkfolders. The output becomes part of your searchable context, allowing agents to organize new links correctly.

Q: How do I filter which MCP tools the agent accesses?

Use the allowedtools parameter when building your tool list. You might grant access to getlinkdetails while blocking deletelink for safety.

Index your Capsulink short link data and click stats directly into LlamaIndex vector stores for semantic querying.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capsulink MCP to LlamaIndex

Create your Vinkius account to connect Capsulink 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 Capsulink with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorizing MCP Server link metrics

Calling `get_link_daily_stats` and `get_link_stats` pulls raw click data that LlamaIndex instantly vectorizes. Your RAG application embeds those traffic numbers alongside your marketing documents. Asking your agent about campaign performance queries actual API data. The system retrieves the exact daily breakdown from the index rather than guessing based on outdated reports.

Semantic search for short URLs

The `list_links` and `list_link_folders` MCP tools feed your entire URL directory into the knowledge base. Users search for a specific promotion, and the engine finds the matching short link by semantic intent. Finding old redirects takes seconds instead of manual dashboard scrolling. You type a rough description of the link, and the agent returns the exact URL and its current destination.

Grounded link management

Modifying redirects relies on the `edit_link_destination` and `shorten_url` tools after validating against indexed rules. The agent checks your internal style guide in the vector store before creating a new URL. Removing old campaigns works the same way. It reads the index to confirm a project is dead before executing `delete_link` on the associated assets.

Setup guide

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

Install `llama-index-tools-mcp`. Initialize `BasicMCPClient` with your Vinkius endpoint, wrap it in `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

Yes. The agent uses `get_link_daily_stats` to fetch the data, which you then embed into your index for natural language querying.

It does if you run `list_link_folders`. The output becomes part of your searchable context, allowing agents to organize new links correctly.

Use the `allowed_tools` parameter when building your tool list. You might grant access to `get_link_details` while blocking `delete_link` for safety.

The MCP Server reads target URLs and click counts. Vinkius handles this via a zero-trust, ephemeral V8 isolate that destroys the connection state immediately after the query finishes.

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