AI agents call history to retrieve information from Scrapegraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name and the apparent purpose of the server (scraping and monitoring), 'history' is most likely a read operation that retrieves historical data without side effects. The low confidence reflects the missing description; if implemented differently (e.g., to delete historical records), it could be Destructive instead.
From the tool's definition Tool name 'history' suggests retrieving historical data or logs. The empty description limits certainty, but context from sibling tools (crawl_*, extract, monitor_*) indicates this server is a web scraping/monitoring service where 'history' most likely…
Documented attack patterns abuse exactly the kind of access history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scrapegraph, and nothing reaches the server without passing your rules. This is the rule we recommend for history:
{
"version": "1",
"default": "deny",
"tools": {
"history": {}
}
}history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
history. It is categorised as a Read tool in the Scrapegraph MCP Server, which means it retrieves data without modifying state.
Register the Scrapegraph MCP server in PolicyLayer and add a rule for history: 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 Scrapegraph. Nothing to install.
history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the history 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 history. 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.
history is provided by the Scrapegraph MCP server (ScrapeGraphAI/scrapegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Scrapegraph, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Scrapegraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.