AI agents use add_marker to create or update resources in Leaflet — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leaflet environment.
This tool generates Leaflet.js code for adding markers to a map. It produces code (a write/creation action) but operates in a documentation/code-generation context with no direct system side effects. The output is code text, not execution of that code, making it a Write category at low severity since misuse would only produce incorrect map marker code.
From the tool's definition Generate code for adding markers to a Leaflet map with optional popups, tooltips, and custom icons
Attacks that exploit this kind of access
Generate code for adding markers to a Leaflet map with optional popups, tooltips, and custom icons. It is categorised as a Write tool in the Leaflet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Leaflet MCP server in PolicyLayer and add a rule for add_marker: 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 Leaflet. Nothing to install.
add_marker 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 add_marker 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 add_marker. 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.
add_marker is provided by the Leaflet MCP server (philgebauer/leaflet-mcp-server). 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 →