Integration

Filebase integration

Filebase is a decentralized storage platform providing an S3-compatible API for storing data on IPFS and Sia networks. Simplify Web3 storage with familiar S3 operations, automatic IPFS pinning, geo-redundancy, and built-in CDN. Perfect for dApps, NFT storage, backups, and any application requiring decentralized, resilient storage with enterprise-grade reliability.

Connect Filebase How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Filebase.Built from the 9 Filebase tools below, on the connection you add once.

Common Filebase use cases

storing files
removing files
renaming files
existence checks
downloading files
cleanup unused buckets
setting up new storage
browsing bucket contents
managing storage buckets
getting CIDs

What you can do with Filebase

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Object, 6 operations

copy_objectCopy objectPUTCopies an object within Filebase. Copy between buckets or rename objects. Optionally update metadata during copy.
delete_objectDelete objectDELETEDeletes an object from a Filebase bucket. For IPFS buckets, this unpins the content from Filebase nodes.
get_objectGet objectGETDownloads an object from Filebase by bucket and key. Supports range requests for partial downloads.
get_object_metadataGet object metadataHEADRetrieves object metadata (size, type, CID) without downloading content. Quick way to check existence and properties.
list_objectsList objectsGETLists objects in a Filebase bucket using ListObjectsV2. Filter by prefix, use delimiters for folder structure, and paginate through large lists.
upload_objectUpload objectPUTUploads an object to Filebase. The object is stored on the bucket's configured decentralized network (IPFS or Sia).

Bucket, 3 operations

create_bucketCreate bucketPUTCreates a new Filebase bucket. By default, buckets are created on the IPFS network.
delete_bucketDelete bucketDELETEDeletes a Filebase bucket. The bucket must be empty (no objects) before it can be deleted.
list_bucketsList bucketsGETLists all storage buckets in your Filebase account. Returns bucket names and creation dates.

Use Filebase from Claude Code, Cursor or Codex

Connect Filebase in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Filebase operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Filebase

Create your workspace
Sign up free. Nothing to install.
Connect Filebase once
Add your Filebase connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.