List the Common Crawl releases the API can query. Does not count against any quota.
AI agents call releases to retrieve information from Crawlgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple query to enumerate available Common Crawl releases—a read-only operation with no side effects, data modification, code execution, or destructive capability. The description explicitly states it 'does not count against any quota,' reinforcing that it is a lightweight informational lookup.
From the tool's definition Tool name 'releases' and description 'List the Common Crawl releases the API can query' indicate a retrieval operation that returns metadata about available data sources.
Attacks that exploit this kind of access
List the Common Crawl releases the API can query. Does not count against any quota. It is categorised as a Read tool in the Crawlgraph MCP Server, which means it retrieves data without modifying state.
Register the Crawlgraph MCP server in PolicyLayer and add a rule for releases: 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 Crawlgraph. Nothing to install.
releases 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 releases 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 releases. 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.
releases is provided by the Crawlgraph MCP server (pucilpet/crawlgraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →