list_referral_candidates
Step 1 of recommending LMCP to a colleague. Returns the user's emailable contacts plus a playful invite template. Use this when the user wants to invite/recommend someone. Then: show a few candidates, let the user PICK (never email everyone), call create_referral_invites for the chosen ones to ge...
This record as markdown: /tools/com-local-mcp-local-mcp/list-referral-candidates.md
What list_referral_candidates does on Local
AI agents call list_referral_candidates to retrieve information from Local without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Max contacts to return (default 60) |
Parameters from the server's own tool schema.
Why list_referral_candidates is rated Low
The tool queries and returns existing contact information and a template. It performs no creation, modification, deletion, or execution of operations. The actual sending of emails is deferred to send_email and requires explicit user approval per recipient. This is a pure read operation that retrieves and presents data to enable user decision-making.
From the tool's definition Tool 'Returns the user's emailable contacts plus a playful invite template' and 'show a few candidates' — explicitly retrieves and displays contact data with no modification or side effects.
Attacks that exploit this kind of access
The rule that runs list_referral_candidates safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_referral_candidates, this is the rule to start with:
list_referral_candidates is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every list_referral_candidates call is checked against it from then on.
Questions about list_referral_candidates
Step 1 of recommending LMCP to a colleague. Returns the user's emailable contacts plus a playful invite template. Use this when the user wants to invite/recommend someone. Then: show a few candidates, let the user PICK (never email everyone), call create_referral_invites for the chosen ones to get each person's unique link, draft a short personalized message IN THE USER'S LANGUAGE (keep the warm-but-sarcastic tone, adapt per person), show it for EDITS, then send with send_email (one per recipient — send_email asks the user to confirm). Never send without the user picking + approving. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
list_referral_candidates accepts 1 parameter: limit. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for list_referral_candidates: 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 Local. Nothing to install.
list_referral_candidates 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 list_referral_candidates 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 list_referral_candidates. 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.
list_referral_candidates is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
This server
Across the catalogue