Skip to content
IronShard logo

IronShard MCP server

Which MCP servers are IronShard's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-23

← Back to IronShard

Whose server it is
  • Registry nameai.ironshard/agent-storage-sandboxverified in the MCP registry

The registry name sits under ironshard.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-23
  • Stateanswerschecked 2026-10-23
  • Tools8
  • Server calls itselfIronShard Object Storage Sandbox
  • Server version4.0.3
  • Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 270 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: roll storage back to an earlier point in time; look up every file an AI agent touched in the audit log.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • create_bucket, upload_object, delete_object change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it0 of 2 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer291 ms
  • Space in an agent's context≈ 1,205 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · branch production data so agents can experiment without touching it
  • cannot · roll storage back to an earlier point in time
  • cannot · look up every file an AI agent touched in the audit log

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: create_bucket, upload_object, delete_object

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-10-23
  • create_bucket

    Creates a 30-day bucket and its secret bearer token.

  • get_bucket_permissions

    Return currently permitted buckets and operations.

  • get_bucket

    Return bucket details with storage and egress usage.

  • upload_object

    Return a secret, short-lived PUT URL for an object up to 5 GB.

  • download_object

    Return a secret, short-lived GET URL for an object's bytes.

  • list_objects

    List one page of objects and path-like prefixes, ordered by key.

  • delete_object

    Delete an object; versioned buckets may retain older versions.

  • get_object_metadata

    Return an object's size, timestamps, ETag, content type, metadata, and tags.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "agent-storage-sandbox": {
      "type": "http",
      "url": "https://agents-mcp.ironshard.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http ironshard https://agents-mcp.ironshard.ai/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://agents-mcp.ironshard.ai/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.