Convert multiple URLs to markdown in parallel
AI agents call batch_convert to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads content from multiple URLs and converts it to markdown format. This is fundamentally a read/fetch operation with no writes, deletions, or code execution. Severity is medium because batch URL fetching could be misused to exfiltrate data or trigger SSRF-like access to internal endpoints, especially in a gateway context that may have access to internal services.
From the tool's definition 'Convert multiple URLs to markdown' — fetches remote URLs and transforms content to markdown; no data modification implied
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Convert multiple URLs to markdown in parallel. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for batch_convert: 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 ContextForge MCP Gateway. Nothing to install.
batch_convert 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 batch_convert 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 batch_convert. 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.
batch_convert is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →