upsert_profile

THE RISK

Medium Risk

Why upsert_profile needs a policy

This tool modifies user profile data reversibly—profiles can be updated or corrected later. It is not destructive (no deletion), not financial, and not execute-class. The blast radius is medium because incorrect profile data could affect lead targeting accuracy and business operations, but the operation itself is reversible and scoped to profile configuration rather than data deletion or external command execution.

From the tool's definition Tool name 'upsert_profile' and description 'Insert or update the user profile into the database' explicitly indicate create/modify operations via upsert (standard database terminology for insert-or-update).

Documented attack patterns abuse exactly the kind of access upsert_profile gives an agent:

POLICY

How to control upsert_profile

PolicyLayer is an MCP gateway — it sits between your AI agents and Prospectio MCP API, and nothing reaches the server without passing your rules. This is the rule we recommend for upsert_profile:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "upsert_profile": {
      "limits": [
        {
          "counter": "upsert_profile_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

upsert_profile 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.

Create a free account and register Prospectio MCP API — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Prospectio MCP API tools

Write generate_campaign Generate prospecting messages for contacts WITHOUT existing messages as a campaign. Write insert_leads Use this ONLY when the user asks for NEW opportunities/leads or when get/leads returns ins Read get_campaign_by_id Retrieve a specific campaign by its ID. Read get_campaign_messages Retrieve messages for a specific campaign with pagination. Read get_campaign_result Retrieve the full result of a completed campaign generation task. Read get_campaigns Retrieve all campaigns with pagination. Read get_leads ALWAYS USE THIS FIRST to retrieve existing data from the database before searching for new Read get_new_contacts Retrieve contacts that have NOT received any messages yet.

All 12 Prospectio MCP API tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about upsert_profile

What does the upsert_profile tool do? +

Insert or update the user profile into the database. It is categorised as a Write tool in the Prospectio MCP API MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upsert_profile? +

Register the Prospectio MCP API MCP server in PolicyLayer and add a rule for upsert_profile: 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 Prospectio MCP API. Nothing to install.

What risk level is upsert_profile? +

upsert_profile is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit upsert_profile? +

Yes. Add a rate_limit block to the upsert_profile 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.

How do I block upsert_profile completely? +

Set action: deny in the PolicyLayer policy for upsert_profile. 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.

What MCP server provides upsert_profile? +

upsert_profile is provided by the Prospectio MCP API MCP server (prospectio-ai/prospectio-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Prospectio MCP API tool call.

Start from Prospectio MCP API, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →