Record that a paper was shared on a platform, with the summary used. Feeds back into scoring to improve future relevance.
AI agents use record_share to create or update resources in Paper Scout MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paper Scout MCP Server environment.
This tool writes/creates a sharing record and updates scoring data. It is reversible in nature (logging an event and adjusting scoring weights), with no destructive, financial, or execution implications. Misuse has minimal blast radius as it only affects paper relevance scoring.
From the tool's definition Record that a paper was shared on a platform, with the summary used. Feeds back into scoring to improve future relevance.
Documented attack patterns abuse exactly the kind of access record_share gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Paper Scout MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for record_share:
{
"version": "1",
"default": "deny",
"tools": {
"record_share": {
"limits": [
{
"counter": "record_share_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}record_share 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.
Record that a paper was shared on a platform, with the summary used. Feeds back into scoring to improve future relevance. It is categorised as a Write tool in the Paper Scout MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paper Scout MCP Server MCP server in PolicyLayer and add a rule for record_share: 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 Paper Scout MCP Server. Nothing to install.
record_share 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 record_share 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 record_share. 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.
record_share is provided by the Paper Scout MCP Server MCP server (jonradoff/paper-scout). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Paper Scout 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.
10 Paper Scout MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.