Create or update a contact (requires approval).
AI agents use contacts_create_or_update to create or update resources in AIOS Co-Founder MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AIOS Co-Founder MCP environment.
This tool falls into the Write category because it creates or updates contact records, which are data modifications. The reversible nature (updates can be corrected, contacts can be deleted later) distinguishes it from Destructive actions.
From the tool's definition Tool explicitly performs "Create or update a contact" — these are reversible write operations that modify data in the contacts system. The description confirms it modifies contact data.
Attacks that exploit this kind of access
Create or update a contact (requires approval). It is categorised as a Write tool in the AIOS Co-Founder MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AIOS Co-Founder MCP server in PolicyLayer and add a rule for contacts_create_or_update: 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 AIOS Co-Founder MCP. Nothing to install.
contacts_create_or_update 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 contacts_create_or_update 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 contacts_create_or_update. 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.
contacts_create_or_update is provided by the AIOS Co-Founder MCP server (varun-b-nagaraj/python-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →