Fetch a LinkedIn company page by slug. Returns company data including name, industry, employee count, description, headquarters, and logo. Requires the OutX Chrome extension to be active within the last 48 hours. This tool handles async polling automatically.
AI agents call fetch_linkedin_company to retrieve information from Outx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves publicly available LinkedIn company data and returns structured information (name, industry, employee count, description, headquarters, logo). There are no write, delete, execute, or financial operations. This is a straightforward read/query operation with minimal risk - misuse would only expose publicly available company information already visible on LinkedIn.
From the tool's definition fetch_linkedin_company - 'Fetch a LinkedIn company page' and 'Returns company data including name, industry, employee count, description, headquarters, and logo' - purely retrieves and returns public company information with no modification or side effects
Attacks that exploit this kind of access
Fetch a LinkedIn company page by slug. Returns company data including name, industry, employee count, description, headquarters, and logo. Requires the OutX Chrome extension to be active within the last 48 hours. This tool handles async polling automatically. It is categorised as a Read tool in the Outx MCP Server, which means it retrieves data without modifying state.
Register the Outx MCP server in PolicyLayer and add a rule for fetch_linkedin_company: 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 Outx. Nothing to install.
fetch_linkedin_company 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 fetch_linkedin_company 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 fetch_linkedin_company. 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.
fetch_linkedin_company is provided by the Outx MCP server (outx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
fetch_linkedin_company is one line of Outx's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →