This record as markdown: /tools/0xyg3n-claude-c2/persist-startup.md
What persist_startup does on Claude C2
AI agents invoke persist_startup to trigger actions in Claude C2. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why persist_startup is rated High
Adding to the startup folder is a persistence mechanism that causes arbitrary code/programs to execute automatically whenever the system starts. This is a classic attacker technique (MITRE ATT&CK T1547.001).
From the tool's definition 'persist_startup' - 'Add to startup folder. Auto-selects client.' This tool establishes persistence by adding entries to the system startup folder, causing code to execute automatically on system boot.
Attacks that exploit this kind of access
The rule that runs persist_startup safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude C2, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For persist_startup, this is the rule to start with:
persist_startup stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude C2, apply this rule, and every persist_startup call is checked against it from then on.
Questions about persist_startup
Add to startup folder. Auto-selects client. It is categorised as a Execute tool in the Claude C2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude C2 MCP server in PolicyLayer and add a rule for persist_startup: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude C2. Nothing to install.
persist_startup is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the persist_startup rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for persist_startup. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
persist_startup is provided by the Claude C2 MCP server (0xyg3n/claude-c2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude C2, and thousands of servers like it.
Across the catalogue