AI agents use set_api_keys to create or update resources in LinkedIn Post Generator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LinkedIn Post Generator environment.
This tool creates or modifies stored API keys, which is a reversible Write operation. It poses high severity because compromised or maliciously-set API keys could grant unauthorized access to external services (YouTube, LinkedIn) in the user's name, enable credential theft, or allow an AI agent to pivot to those platforms.
From the tool's definition Tool name 'set_api_keys' indicates modification of credential storage. The server context shows it manages authentication for YouTube and LinkedIn API access.
Documented attack patterns abuse exactly the kind of access set_api_keys gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LinkedIn Post Generator, and nothing reaches the server without passing your rules. This is the rule we recommend for set_api_keys:
{
"version": "1",
"default": "deny",
"tools": {
"set_api_keys": {
"limits": [
{
"counter": "set_api_keys_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_api_keys 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.
set_api_keys. It is categorised as a Write tool in the LinkedIn Post Generator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LinkedIn Post Generator MCP server in PolicyLayer and add a rule for set_api_keys: 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 LinkedIn Post Generator. Nothing to install.
set_api_keys 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 set_api_keys 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 set_api_keys. 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.
set_api_keys is provided by the LinkedIn Post Generator MCP server (nvkanirudh/linkedin-post-generator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LinkedIn Post Generator, 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.
6 LinkedIn Post Generator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.