# Content Sweep (remote · contentsweep.ai)

Prepaid copyright investigation and authorized enforcement, with a free agent sandbox.

- Trust score: 66/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `contentsweep.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/ai-contentsweep-agent-access/api-mcp.md), [page](https://verifymcp.io/servers/ai-contentsweep-agent-access/api-mcp)

## Channel facts

- Endpoint: `https://contentsweep.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `required`
- 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 2026-09-29.

- **Endpoint Security**: 63/100
  - 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 (submit_takedown).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1211 tokens (~34/item across 35 items; 35 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 36 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Content Sweep MCP server?

Content Sweep is a hosted endpoint at https://contentsweep.ai/api/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-contentsweep-agent-access 'https://contentsweep.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-contentsweep-agent-access": {
      "url": "https://contentsweep.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-contentsweep-agent-access": {
      "type": "http",
      "url": "https://contentsweep.ai/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-contentsweep-agent-access]
url = "https://contentsweep.ai/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-contentsweep-agent-access": {
      "type": "remote",
      "url": "https://contentsweep.ai/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-contentsweep-agent-access --url 'https://contentsweep.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-contentsweep-agent-access:
    url: "https://contentsweep.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-contentsweep-agent-access": {
      "Transport": "http",
      "Url": "https://contentsweep.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-contentsweep-agent-access -t streamable-http -u 'https://contentsweep.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-contentsweep-agent-access": {
      "type": "http",
      "url": "https://contentsweep.ai/api/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.

### 2026-09-28 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 64, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 63, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-21 (score 62)

First indexed and scored.

## MCP tools (35)

### `find_copies` (~60 tokens)

Execute a pre-approved search quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `investigate_url` (~59 tokens)

Execute a pre-approved investigate quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `capture_evidence` (~60 tokens)

Execute a pre-approved evidence quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `prepare_takedown` (~61 tokens)

Execute a pre-approved prepare quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `submit_takedown` (~61 tokens)

Execute a pre-approved submit quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `check_status` (~59 tokens)

Execute a pre-approved status quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `monitor_case` (~59 tokens)

Execute a pre-approved monitor quote asynchronously. The quote bounds spending and contains rights scope/input. Returns an operation ID; poll get_operation. Submission is distinct from removal.

Input parameters:

- `idempotency_key` (string, required)
- `quote_id` (string, required)

### `enroll_agent` (~31 tokens)

Create free sandbox credentials without browser signup. Simulated resources cannot authorize live effects.

Input parameters:

- `name` (string, required)

### `enroll_live` (~33 tokens)

Enroll an accountable live organization with current terms and agent attestation. Launch gates apply.

Input parameters:

- `body` (object, required)

### `get_account` (~14 tokens)

Read authenticated account and environment.

### `get_prices` (~15 tokens)

Read current rate card; free.

### `get_balance` (~16 tokens)

Read available and reserved credits; free.

### `get_usage` (~15 tokens)

Read recent ledger entries; free.

### `create_quote` (~43 tokens)

Quote an action and its complete input without reserving funds. Use its ID with the matching task tool.

Input parameters:

- `action` (string, required)
- `input` (object, required)

### `purchase_credits` (~74 tokens)

Purchase prepaid credits. Live payment may return an MPP 402 challenge; send its card authorization separately from the account token. Sandbox credits are simulated.

Input parameters:

- `amount_cents` (integer, required)
- `automatic` (boolean)
- `idempotency_key` (string, required)
- `payment_authorization` (string)

### `set_spending_policy` (~31 tokens)

Set organization and credential limits; auto funding requires an explicit bounded mandate.

Input parameters:

- `body` (object, required)

### `create_rights_holder` (~24 tokens)

Register a partner-managed rights holder.

Input parameters:

- `body` (object, required)

### `create_work` (~25 tokens)

Register a work owned by a tenant rights holder.

Input parameters:

- `body` (object, required)

### `delegate_authority` (~32 tokens)

Record scoped, expiring copyright authority and appointment. Payment does not establish authority.

Input parameters:

- `body` (object, required)

### `revoke_authority` (~24 tokens)

Irreversibly revoke a delegation.

Input parameters:

- `id` (string, required)

### `get_operation` (~23 tokens)

Poll operation state and results; free.

Input parameters:

- `id` (string, required)

### `get_case` (~23 tokens)

Read tenant-owned case observations; free.

Input parameters:

- `id` (string, required)

### `get_evidence` (~27 tokens)

Export immutable metadata evidence; no media or storage paths.

Input parameters:

- `id` (string, required)

### `get_packet` (~23 tokens)

Read prepared packet and receipt; free.

Input parameters:

- `id` (string, required)

### `get_monitor` (~21 tokens)

Read monitoring budget and schedule.

Input parameters:

- `id` (string, required)

### `pause_monitor` (~19 tokens)

Pause recurring work.

Input parameters:

- `id` (string, required)

### `resume_monitor` (~36 tokens)

Resume within the existing expiry and total budget, optionally replacing delegation.

Input parameters:

- `delegation_id` (string)
- `id` (string, required)

### `exchange_token` (~26 tokens)

Issue a 15-minute token restricted to requested scopes.

Input parameters:

- `scopes` (array, required)

### `rotate_credential` (~18 tokens)

Rotate bootstrap credential and invalidate its child tokens.

### `revoke_credential` (~22 tokens)

Revoke a credential immediately.

Input parameters:

- `id` (string, required)

### `create_webhook` (~33 tokens)

Opt in to signed event delivery to a public HTTPS endpoint; returns signing secret once.

Input parameters:

- `url` (string, required)

### `revoke_webhook` (~22 tokens)

Stop delivery to an endpoint.

Input parameters:

- `id` (string, required)

### `get_events` (~20 tokens)

Read stable events; tolerate duplicate and out-of-order delivery.

### `get_webhook_deliveries` (~17 tokens)

Inspect webhook delivery history.

### `replay_event` (~38 tokens)

Replay an event to an owned active webhook with its original event ID.

Input parameters:

- `event_id` (string, required)
- `webhook_id` (string, required)

## Diagnostics

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

## Score history

- 2026-09-29: 66
- 2026-09-28: 66
- 2026-09-27: 65
- 2026-09-26: 65
- 2026-09-25: 64
- 2026-09-24: 64
- 2026-09-23: 63
- 2026-09-22: 63
- 2026-09-21: 62

## Common questions

### What is the Content Sweep MCP server?

Content Sweep is an MCP server listed in the public MCP registry as ai.contentsweep/agent-access. Prepaid copyright investigation and authorized enforcement, with a free agent sandbox. This page covers its hosted endpoint (https://contentsweep.ai/api/mcp).

### Is the Content Sweep MCP server safe to use?

Content Sweep scores 66 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 Content Sweep MCP server expose?

Content Sweep exposes 35 tools: find_copies, investigate_url, capture_evidence, prepare_takedown, submit_takedown, and 30 more. Their descriptions and schemas cost roughly 1,164 tokens of context every time the server is loaded.

### Does the Content Sweep MCP server require authentication?

No. We connected to Content Sweep without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Content Sweep MCP server still maintained?

Content Sweep is still listed as active in the MCP registry. We last reached this channel on 29 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://contentsweep.ai/api/mcp
- Authorisation metadata: https://contentsweep.ai/.well-known/oauth-protected-resource/api/mcp
- Website: https://contentsweep.ai/developers/agents
- Changelog RSS feed: https://verifymcp.io/servers/ai-contentsweep-agent-access/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-contentsweep-agent-access/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-contentsweep-agent-access/api-mcp