AI agents use http_put to create or update resources in MCP-RQuest — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-RQuest environment.
HTTP PUT requests modify or create data on remote servers. While not inherently destructive (PUT typically replaces resource state rather than permanently deleting), it has Write semantics. The high severity reflects that an AI agent with this tool could unintentionally modify data on any accessible web service—credentials, configurations, user records—depending on what URL and payload it constructs.
From the tool's definition Tool name 'http_put' and description 'Make an HTTP PUT request to the specified URL' indicate HTTP PUT method, which is used to create or modify data on remote servers. HTTP PUT is a write operation that updates or creates resources at the specified URL.
Documented attack patterns abuse exactly the kind of access http_put gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-RQuest, and nothing reaches the server without passing your rules. This is the rule we recommend for http_put:
{
"version": "1",
"default": "deny",
"tools": {
"http_put": {
"limits": [
{
"counter": "http_put_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}http_put stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Make an HTTP PUT request to the specified URL. It is categorised as a Write tool in the MCP-RQuest MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-RQuest MCP server in PolicyLayer and add a rule for http_put: 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 MCP-RQuest. Nothing to install.
http_put is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the http_put 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 http_put. 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.
http_put is provided by the MCP-RQuest MCP server (xxxbrian/mcp-rquest). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 MCP-RQuest tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 MCP-RQuest tools catalogued and risk-classified — across an index of 42,500+ MCP servers.