content-sweep-agent-accessSAFE
Official Content Sweep remote MCP and REST integration: prepaid copyright investigation, delegated enforcement, and a free simulated sandbox
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Official integration examples for the Content Sweep remote MCP server and REST API, published by Content Sweep LLC.
Agents can search supported sources for suspected text/identity copies, investigate URLs, collect metadata evidence, prepare takedown packets, submit within recorded copyright authority through activated routes, and monitor outcomes within an explicit budget.
This repository contains public clients and connection examples for the hosted service. The enforcement backend runs at Content Sweep.
Connect with MCP
- Endpoint: https://contentsweep.ai/api/mcp
- Transport: Streamable HTTP
- Registry name: ai.contentsweep/agent-access
- Authentication: Bearer access token for private data and execution. Browser OAuth and dynamic client registration are not supported.
Public initialize, tools/list, and enroll_agent let an agent discover the service and obtain a free sandbox account. Configure the returned token through your client's HTTP headers:
{
"mcpServers": {
"content-sweep": {
"url": "https://contentsweep.ai/api/mcp",
"headers": {
"Authorization": "Bearer "
}
}
}
}Your client must support remote Streamable HTTP and configurable headers; its configuration format may differ. Keep the actual token in its secret storage, outside this repository.
Try public discovery with the official MCP SDK (Node.js 20 or later):
npm ci npm run mcp:discover
The example lists tools without enrolling, spending credits, or contacting enforcement destinations. Task tools include find_copies, investigate_url, capture_evidence, prepare_takedown, submit_takedown, check_status, and monitor_case. Create a quote, pass its ID and an idempotency key to the task tool, then poll get_operation.
Try the free simulated sandbox
python3 sandbox.py
The Python and [Type
a2fbdf1077adOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add content-sweep-agent-access -- npx -y [email protected]
{
"mcpServers": {
"content-sweep-agent-access": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
zod
Gates applied: no_behavioural_pass.
a2fbdf1077adfull audit observations/trust-audit/mcp-server/founder-sweep__content-sweep-agent-access.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a2fbdf1077ad | SAFE | B | 89 | first audit |
Questions
What is the content-sweep-agent-access MCP server?
Official Content Sweep remote MCP and REST integration: prepaid copyright investigation, delegated enforcement, and a free simulated sandbox
Is content-sweep-agent-access safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does content-sweep-agent-access need?
No credential environment variables were found in its source, so it appears to need none.
How does content-sweep-agent-access run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as content-sweep-agent-access at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (a2fbdf1077ad), read on 2026-10-08. The repository is watched and re-audited when it changes.