Exchange the browser-provided authorization code for a persistent access token.
AI agents invoke linkedin_exchange_code to trigger actions in LinkedIn Custom MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool performs an OAuth 2.0 authorization code exchange, which triggers an external operation (contacting LinkedIn's OAuth endpoint) and produces a persistent access token. It doesn't merely read data — it creates and stores credentials that grant ongoing access to the LinkedIn account.
From the tool's definition Exchange the browser-provided authorization code for a persistent access token
Documented attack patterns abuse exactly the kind of access linkedin_exchange_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LinkedIn Custom MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for linkedin_exchange_code:
{
"version": "1",
"default": "deny",
"tools": {
"linkedin_exchange_code": {
"limits": [
{
"counter": "linkedin_exchange_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}linkedin_exchange_code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Exchange the browser-provided authorization code for a persistent access token. It is categorised as a Execute tool in the LinkedIn Custom MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LinkedIn Custom MCP Server MCP server in PolicyLayer and add a rule for linkedin_exchange_code: 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 Custom MCP Server. Nothing to install.
linkedin_exchange_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the linkedin_exchange_code 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 linkedin_exchange_code. 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.
linkedin_exchange_code is provided by the LinkedIn Custom MCP Server MCP server (saramali15792/linkedin_mcp_custom_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LinkedIn Custom 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.
17 LinkedIn Custom MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.