create_work — Content Sweep MCP Tool Mutating
create_work
(create work) is one of 35 tools on the
Content Sweep
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call create_work from your client
- Claude Code Content Sweep create_work run in your project directory
- Claude Desktop Content Sweep create_work ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Content Sweep create_work ~/.cursor/mcp.json
- VS Code Content Sweep create_work .vscode/mcp.json
- Zed Content Sweep create_work ~/.config/zed/settings.json
- Windsurf Content Sweep create_work ~/.codeium/windsurf/mcp_config.json
- Cline Content Sweep create_work ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Content Sweep create_work ~/.gemini/settings.json
- Grok Content Sweep create_work .mcp.json (in your project root)
- ChatGPT Content Sweep create_work Settings → Connectors → Advanced → Developer mode
- Claude.ai Content Sweep create_work Settings → Connectors → Add custom connector
- LangChain Content Sweep create_work pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agent-access https://contentsweep.ai/api/mcpOther tools on this server
- find_copies
- investigate_url
- capture_evidence
- prepare_takedown
- submit_takedown
- check_status
- monitor_case
- enroll_agent
- enroll_live
- get_account
- get_prices
- get_balance
- get_usage
- create_quote
- purchase_credits
- set_spending_policy
- create_rights_holder
- delegate_authority
- revoke_authority
- get_operation
- get_case
- get_evidence
- get_packet
- get_monitor
- pause_monitor
- resume_monitor
- exchange_token
- rotate_credential
- revoke_credential
- create_webhook
- revoke_webhook
- get_events
- get_webhook_deliveries
- replay_event
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.