log_interaction
Log a sales interaction — finds the person (or creates them), creates an action with metadata, and optionally updates the person's customFields. This is the primary tool for recording outreach activity. One call does everything.
This record as markdown: /tools/adrata-starfield-mcp/log-interaction.md
What log_interaction does on Starfield
AI agents call log_interaction to retrieve information from Starfield 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 |
|---|---|---|---|
type | string | Yes | Interaction type: linkedin_connection_request, linkedin_message, email, call, meeting, note |
title | string | Yes | What happened, e.g. "Sent LinkedIn connection request" |
status | string | — | Action status: COMPLETED (default), PLANNED, IN_PROGRESS |
message | string | — | The message sent (stored in action metadata) |
outcome | string | — | Result: accepted, pending, replied, no_response, meeting_booked |
personName | string | — | Name of the person |
companyName | string | — | Company name |
personEmail | string | — | Email of the person (used to find/create) |
customFields | object | — | Additional fields to set on the person record |
personLinkedin | string | — | LinkedIn URL |
Parameters from the server's own tool schema.
Why log_interaction is rated Low
Even though log_interaction only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (10 properties) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs log_interaction safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Starfield, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For log_interaction, this is the rule to start with:
log_interaction 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 Starfield, apply this rule, and every log_interaction call is checked against it from then on.
Questions about log_interaction
Log a sales interaction — finds the person (or creates them), creates an action with metadata, and optionally updates the person's customFields. This is the primary tool for recording outreach activity. One call does everything. It is categorised as a Read tool in the Starfield MCP Server, which means it retrieves data without modifying state.
log_interaction accepts 10 parameters: type, title, status, message, outcome, personName, companyName, personEmail, customFields, personLinkedin. Required: type, title. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for log_interaction: 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 Starfield. Nothing to install.
log_interaction 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 log_interaction 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 log_interaction. 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.
log_interaction is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Starfield, and thousands of servers like it.
This server
Across the catalogue