How to Use the Filebase (Web3 Storage) MCP in LlamaIndex

Q: Can LlamaIndex query Filebase (Web3 Storage) bandwidth usage?

Yes. Your agent can call platformgetusage to pull storage and bandwidth statistics. You can index this data to let users query their current storage costs using natural language.

Q: How does LlamaIndex handle document retrieval from Filebase (Web3 Storage)?

The agent uses rpccat to retrieve file contents directly from a CID. Once fetched, LlamaIndex parses the text, creates nodes, and injects them into the active query context.

Q: Can I filter pins before indexing them in LlamaIndex?

Yes. You can configure your agent to use psagetpin to retrieve specific pin statuses. This ensures only successfully pinned files are indexed, keeping your vector store clean.

Index your Filebase Web3 storage metadata directly into LlamaIndex vector stores for semantic search and RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Filebase (Web3 Storage) MCP to LlamaIndex

Create your Vinkius account to connect Filebase (Web3 Storage) 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 Filebase (Web3 Storage) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live IPFS Metadata with this MCP Server

This MCP Server provides `psa_list_pins` to let your LlamaIndex pipelines ingest current pinning records into vector indexes. Your agent can query this index to find specific files based on semantic descriptions rather than raw CIDs. By indexing the output of `rpc_pin_ls`, your RAG application can answer questions about what files are currently stored. It bridges the gap between decentralized storage states and your agent's knowledge base.

Semantic Search Over IPNS Records

The `platform_list_names` tool retrieves all active IPNS names so your agent can index their configurations. When a user asks for a specific project directory, the agent searches the index to find the matching IPNS record. It then uses `rpc_name_resolve` to fetch the actual content path. This setup lets you build document retrieval systems that point to mutable decentralized addresses without manual mapping.

Automated File Retrieval and Ingestion

The `rpc_cat` tool allows your LlamaIndex agent to fetch the raw contents of a file directly from IPFS using its CID. The agent reads the text, processes it into chunks, and embeds it into your vector store. If the file is structured as raw blocks, the agent can use `rpc_block_get` to handle low-level parsing. This enables your pipeline to ingest decentralized data sources on the fly during query execution.

Setup guide

Set up Filebase (Web3 Storage) 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 Filebase (Web3 Storage) 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 Filebase (Web3 Storage) tools.",
)
response = await agent.run("List recent Filebase (Web3 Storage) 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 Filebase. 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 Filebase (Web3 Storage) 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 Filebase (Web3 Storage) MCP in LlamaIndex

Use the LlamaIndex MCP tool spec to connect to the server. Your agent can run `psa_list_pins` to fetch your pinning history, then convert that metadata into document nodes for your vector index.

Yes. Your agent can call `platform_get_usage` to pull storage and bandwidth statistics. You can index this data to let users query their current storage costs using natural language.

The agent uses `rpc_cat` to retrieve file contents directly from a CID. Once fetched, LlamaIndex parses the text, creates nodes, and injects them into the active query context.

Yes. You can configure your agent to use `psa_get_pin` to retrieve specific pin statuses. This ensures only successfully pinned files are indexed, keeping your vector store clean.

This MCP server isolates your IPNS keys and API credentials in a secure V8 environment. Your LlamaIndex agent only sees the tool outputs, preventing sensitive keys from being exposed in your vector databases.

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