Retrieve the current state of a Linkup research task previously started with
AI agents call linkup-get-research to retrieve information from Linkup without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries the state of a previously created research task. It performs no side effects, creates no data, executes no code, and deletes nothing. It is a pure read operation that aligns with the 'Read' category. The low severity reflects minimal blast radius—retrieving task state poses minimal security risk even if misused by an AI agent.
From the tool's definition Tool name 'linkup-get-research' and description 'Retrieve the current state of a Linkup research task' indicate a retrieval operation that fetches status information about an existing task without modifying it.
Documented attack patterns abuse exactly the kind of access linkup-get-research gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Linkup, and nothing reaches the server without passing your rules. This is the rule we recommend for linkup-get-research:
{
"version": "1",
"default": "deny",
"tools": {
"linkup-get-research": {}
}
}linkup-get-research is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve the current state of a Linkup research task previously started with. It is categorised as a Read tool in the Linkup MCP Server, which means it retrieves data without modifying state.
Register the Linkup MCP server in PolicyLayer and add a rule for linkup-get-research: 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 Linkup. Nothing to install.
linkup-get-research 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 linkup-get-research 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 linkup-get-research. 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.
linkup-get-research is provided by the Linkup MCP server (linkup-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Linkup, 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.
4 Linkup tools catalogued and risk-classified — across an index of 43,000+ MCP servers.