AI agents use add_upvoter to create or update resources in Featurebase MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Featurebase MCP Server environment.
This tool modifies existing data (the upvote list for a post) in a way that is reversible (upvotes can be removed). It does not delete data, execute arbitrary code, or involve financial operations. While it could be misused to artificially inflate upvotes, the blast radius is limited to feedback system integrity, making it a straightforward Write operation with low severity.
From the tool's definition Tool name 'add_upvoter' and description 'Add an upvoter to a post' indicates modification of post metadata (upvote count/list) rather than destructive deletion or financial transaction. The tool creates or modifies data reversibly by adding an upvote record.
Documented attack patterns abuse exactly the kind of access add_upvoter gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Featurebase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_upvoter:
{
"version": "1",
"default": "deny",
"tools": {
"add_upvoter": {
"limits": [
{
"counter": "add_upvoter_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} add_upvoter 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.
Add an upvoter to a post. It is categorised as a Write tool in the Featurebase MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Featurebase MCP Server MCP server in PolicyLayer and add a rule for add_upvoter: 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 Featurebase MCP Server. Nothing to install.
add_upvoter 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_upvoter 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_upvoter. 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_upvoter is provided by the Featurebase MCP Server MCP server (marcinwyszynski/featurebase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Featurebase MCP Server, 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.
12 Featurebase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.