Can my AI agent batch delete unused Uploadcare files?

Yes! Provide your agent with the list of unused UUIDs or ask it to identify temporary incomplete uploads, and simply command it to `batch delete these assets`. The agent uses the `batch_delete_files` tool to permanently erase them from the CDN instantly, freeing up your project's storage.

How can I quickly check my current CDN bandwidth and storage usage?

Instead of digging through the web dashboard, ask your AI agent to `get project info`. It instantly fetches your Uploadcare project-level metadata, returning your precise storage usage (bytes), traffic bandwidth usage, and active file count. Perfect for quick billing audits.

Will my temporary UI uploads expire automatically?

By default, temporary files uploaded via your front-end will be wiped after 24 hours. To prevent this, you can ask your agent to `store this file ` or `batch store` a bunch of UUIDs. The agent communicates with Uploadcare to mark the files as permanently stored, saving them from the garbage collector.

Uploadcare MCP Server for LlamaIndex 10 tools — connect in under 2 minutes

Name: Uploadcare
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Uploadcare as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to Uploadcare. "
            "You have 10 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in Uploadcare?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Uploadcare MCP Server

Connect your Uploadcare account to any AI agent to fully manage your file handling and CDN media infrastructure via natural conversation.

LlamaIndex agents combine Uploadcare tool responses with indexed documents for comprehensive, grounded answers. Connect 10 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.

What you can do

File Management — List uploaded assets, retrieve specific file technical metadata (like dimensions and CDN URLs), and manage permanent storage states.
Bulk Operations — Efficiently batch store or batch delete multiple temporary or permanent files in a single operation.
File Transport — Copy existing files manually to local or remote storage targets, directly through your AI agent.
Groups & Collections — List immutable file collections (groups) and inspect which individual files are contained within them.
Project Analytics — Retrieve your Uploadcare project-level metadata, checking your current account storage and bandwidth consumption in real time.

The Uploadcare MCP Server exposes 10 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Uploadcare to LlamaIndex via MCP

Follow these steps to integrate the Uploadcare MCP Server with LlamaIndex.

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Uploadcare

Why Use LlamaIndex with the Uploadcare MCP Server

LlamaIndex provides unique advantages when paired with Uploadcare through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine Uploadcare tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Uploadcare tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Uploadcare, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Uploadcare tools were called, what data was returned, and how it influenced the final answer

Uploadcare + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the Uploadcare MCP Server delivers measurable value.

Hybrid search: combine Uploadcare real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Uploadcare to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Uploadcare for fresh data

Analytical workflows: chain Uploadcare queries with LlamaIndex's data connectors to build multi-source analytical reports

Uploadcare MCP Tools for LlamaIndex (10)

These 10 tools become available when you connect Uploadcare to LlamaIndex via MCP:

batch_delete_files

This action is irreversible. Permanently removes multiple files in a single operation

batch_store_files

Marks multiple temporary files as permanently stored

copy_file

g. S3). Copies an existing file to local or remote storage

delete_file

This action is irreversible. Permanently removes a file and its variants from Uploadcare

get_file_details

Retrieves technical metadata for a specific Uploadcare file

get_group_details

Retrieves information about a specific file group

get_project_info

Retrieves project-level metadata and usage statistics

list_file_groups

Lists immutable file collections (groups) in the project

list_files

Supports pagination via limit. Lists files stored in your Uploadcare project

store_file

Marks a temporary file as permanently stored

Example Prompts for Uploadcare in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with Uploadcare immediately.

"What is our current project storage and bandwidth usage?"

"Can you check the dimensions and CDN URL for file UUID `9cd83...`?"

"Batch delete these 4 outdated temporary images: `e33b...`, `f55a...`, `8c11...`, `ab99...`."

Troubleshooting Uploadcare MCP Server with LlamaIndex

Common issues when connecting Uploadcare to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Uploadcare + LlamaIndex FAQ

Common questions about integrating Uploadcare MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query Uploadcare tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.