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

Q: Can AutoGen agents manage Filebase (Web3 Storage) gateways?

Yes. Agents can monitor bandwidth using platformgetgatewayusage and decide to deploy new gateways via platformcreategateway when usage spikes, coordinating the entire process through conversation.

Q: How do AutoGen agents resolve IPNS names on Filebase (Web3 Storage)?

An agent can call rpcnameresolve to translate an IPNS name to an IPFS path. Another agent can then fetch the contents using rpccat to verify the data is correct.

Coordinate Filebase Web3 storage operations, gateway deployments, and IPNS updates using AutoGen multi-agent debate.

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 AutoGen

Create your Vinkius account to connect Filebase (Web3 Storage) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Pinning with this MCP Server

This MCP Server exposes `psa_add_pin` to let your AutoGen agents coordinate file pinning through multi-agent debate. A budget agent can check costs while a storage agent proposes pinning a new CID. They negotiate using `platform_get_usage` to ensure the operation fits within your storage limits. Once they reach a consensus, the storage agent executes the pin, preventing unauthorized or wasteful operations.

Multi-Agent Gateway Management

The `platform_create_gateway` tool enables your agents to deploy dedicated gateways when bandwidth limits are reached. A performance monitoring agent can track latency and flag when a new gateway is needed. It then requests approval from the admin agent, which uses `platform_update_gateway` to adjust configurations. This cooperative loop keeps your content delivery fast without manual oversight.

Coordinated IPNS Updates and Verification

The `platform_update_name` tool allows your writing agent to point an IPNS name to a newly published CID. Before making the change live, a QA agent verifies the content. The QA agent uses `rpc_name_resolve` to check the IPNS path and ensure the file resolves correctly. If it passes, the agents agree to finalize the update, maintaining a reliable production state.

Setup guide

Set up Filebase (Web3 Storage) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Filebase (Web3 Storage) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Filebase (Web3 Storage)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Filebase (Web3 Storage) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Filebase (Web3 Storage)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Filebase (Web3 Storage) data")
    print(result.messages[-1].content)

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 AutoGen

You register the MCP server tools with your AssistantAgent. One agent can propose a pin using `psa_add_pin`, while a second agent verifies the pin status using `psa_get_pin` before completing the task.

Yes. Agents can monitor bandwidth using `platform_get_gateway_usage` and decide to deploy new gateways via `platform_create_gateway` when usage spikes, coordinating the entire process through conversation.

An agent can call `rpc_name_resolve` to translate an IPNS name to an IPFS path. Another agent can then fetch the contents using `rpc_cat` to verify the data is correct.

The agents debate the action based on system instructions. If the budget agent flags that `platform_get_bucket_usage` is too high, it will block the pinning tool call until older pins are removed.

This MCP server holds your API keys and IPFS keys securely in the V8 isolate sandbox. AutoGen agents only exchange tool schemas and clean outputs, keeping your critical credentials completely private.

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