# IronShard Object Storage Sandbox (remote · agents-mcp.ironshard.ai)

Create a free sandbox object storage bucket; upload, download, list, inspect, and delete objects.

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `agents-mcp.ironshard.ai`: 82/100 (this document), [markdown](https://verifymcp.io/servers/ai-ironshard-agent-storage-sandbox/agents-mcp.md), [page](https://verifymcp.io/servers/ai-ironshard-agent-storage-sandbox/agents-mcp)

## Channel facts

- Endpoint: `https://agents-mcp.ironshard.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_object).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 897 tokens (~99/item across 9 items; 8 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the IronShard Object Storage Sandbox MCP server?

IronShard Object Storage Sandbox is a hosted endpoint at https://agents-mcp.ironshard.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-ironshard-agent-storage-sandbox 'https://agents-mcp.ironshard.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-ironshard-agent-storage-sandbox": {
      "url": "https://agents-mcp.ironshard.ai/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.ai-ironshard-agent-storage-sandbox]
url = "https://agents-mcp.ironshard.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-ironshard-agent-storage-sandbox": {
      "type": "remote",
      "url": "https://agents-mcp.ironshard.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-ironshard-agent-storage-sandbox --url 'https://agents-mcp.ironshard.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-ironshard-agent-storage-sandbox:
    url: "https://agents-mcp.ironshard.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-ironshard-agent-storage-sandbox": {
      "Transport": "http",
      "Url": "https://agents-mcp.ironshard.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-ironshard-agent-storage-sandbox -t streamable-http -u 'https://agents-mcp.ironshard.ai/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 80, +1)

- [functional] Server version: 4.0.0b3 → 4.0.3

### 2026-09-14 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (8)

### `create_bucket` (~20 tokens)

Create Bucket

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

Output parameters:

- `bucket_name` (string): Name of the newly created bucket.
- `bucket_token` (string): Bearer credential required with the bucket name for all other operations.

### `get_bucket_permissions` (~44 tokens)

Get Bucket Permissions

Return currently permitted buckets and operations.

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.

Output parameters:

- `buckets` (array)

### `get_bucket` (~46 tokens)

Get Bucket

Return bucket details with storage and egress usage.

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.

Output parameters:

- `bucket_name` (string): Bucket to operate on.
- `created_at` (string): UTC creation time
- `egress` (object): Monthly egress quota and current UTC-calendar-month usage in bytes.
- `object_count` (integer): Number of objects
- `storage` (object): Storage quota and current usage in bytes.
- `versioning_enabled` (boolean): Whether object versioning is enabled.

### `upload_object` (~69 tokens)

Upload Object

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

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.
- `object_key` (string, required): Complete object key, including path-like prefixes.

Output parameters:

- `http_method` (string): HTTP method that must be used with the presigned URL.
- `url` (string): Short-lived presigned HTTPS URL containing all authorization information.

### `download_object` (~65 tokens)

Download Object

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

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.
- `object_key` (string, required): Complete object key, including path-like prefixes.

Output parameters:

- `http_method` (string): HTTP method that must be used with the presigned URL.
- `url` (string): Short-lived presigned HTTPS URL containing all authorization information.

### `list_objects` (~113 tokens)

List Objects

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

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.
- `page_size` (integer): Maximum objects to return, from 1 to 1000.
- `page_token`: Opaque continuation token from the preceding page.
- `prefix`: Only return keys beginning with this prefix.
- `recursive` (boolean): True for a flat listing; false for immediate children.

Output parameters:

- `bucket_name` (string): Bucket to operate on.
- `common_prefixes` (array): Immediate child prefixes when recursive is false. They behave like directories, although object storage has no real directories.
- `next_page_token`: Opaque token for the next page. Pass it unchanged as page_token; null means there are no more results.
- `objects` (array)

### `delete_object` (~64 tokens)

Delete Object

Delete an object; versioned buckets may retain older versions.

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.
- `object_key` (string, required): Complete object key, including path-like prefixes.

Output parameters:

- `bucket_name` (string): Bucket to operate on.
- `deleted` (boolean): True when the object was deleted.
- `object_key` (string): Complete object key, including path-like prefixes.
- `version_id`

### `get_object_metadata` (~71 tokens)

Get Object Metadata

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

Input parameters:

- `bucket_name` (string, required): Bucket to operate on.
- `bucket_token` (string, required): Secret bearer token returned with the public bucket.
- `object_key` (string, required): Complete object key, including path-like prefixes.

Output parameters:

- `bucket_name` (string): Bucket to operate on.
- `content_type`
- `etag`: Storage entity tag; it is not always a content checksum.
- `last_modified`: UTC time of the most recent modification.
- `metadata` (object): User-defined object metadata.
- `object_key` (string): Complete object key, including path-like prefixes.
- `size_bytes` (integer): Object size in bytes.
- `tags` (object)
- `version_id`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-ironshard-agent-storage-sandbox/agents-mcp#diagnostics

## Score history

- 2026-09-21: 82
- 2026-09-20: 82
- 2026-09-19: 81
- 2026-09-18: 81
- 2026-09-17: 80
- 2026-09-16: 80
- 2026-09-15: 79
- 2026-09-14: 79
- 2026-09-13: 78
- 2026-09-12: 78
- 2026-09-11: 77
- 2026-09-10: 77
- 2026-09-09: 76
- 2026-09-08: 76
- 2026-09-07: 75
- 2026-09-06: 75
- 2026-09-05: 75
- 2026-09-04: 74
- 2026-09-03: 74
- 2026-09-02: 73
- 2026-09-01: 73
- 2026-08-31: 72
- 2026-08-30: 72
- 2026-08-29: 71
- 2026-08-28: 71
- 2026-08-27: 70
- 2026-08-26: 62
- 2026-08-25: 60

## Common questions

### What is the IronShard Object Storage Sandbox MCP server?

IronShard Object Storage Sandbox is an MCP server listed in the public MCP registry as ai.ironshard/agent-storage-sandbox. Create a free sandbox object storage bucket; upload, download, list, inspect, and delete objects. This page covers its hosted endpoint (https://agents-mcp.ironshard.ai/mcp).

### Is the IronShard Object Storage Sandbox MCP server safe to use?

IronShard Object Storage Sandbox scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the IronShard Object Storage Sandbox MCP server expose?

IronShard Object Storage Sandbox exposes 8 tools: create_bucket, get_bucket_permissions, get_bucket, upload_object, download_object, and 3 more. Their descriptions and schemas cost roughly 492 tokens of context every time the server is loaded.

### Does the IronShard Object Storage Sandbox MCP server require authentication?

No. We connected to IronShard Object Storage Sandbox without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the IronShard Object Storage Sandbox MCP server still maintained?

IronShard Object Storage Sandbox is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agents-mcp.ironshard.ai/mcp
- Website: https://ironshard.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-ironshard-agent-storage-sandbox/agents-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-ironshard-agent-storage-sandbox/agents-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-ironshard-agent-storage-sandbox/agents-mcp