Manage contacts. Actions: get, list, create, update
AI agents use manage-contacts to create or update resources in Fergus MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fergus MCP Server environment.
The tool performs both Read operations ('get', 'list') and Write operations ('create', 'update'). According to severity hierarchy, Write is more severe than Read. The 'update' action can modify existing contact records, and 'create' adds new contacts. Neither action is irreversible (no delete/purge), so it does not qualify as Destructive.
From the tool's definition Tool supports 'get, list, create, update' actions. The 'create' and 'update' actions constitute reversible modifications to contact data.
Attacks that exploit this kind of access
Manage contacts. Actions: get, list, create, update. It is categorised as a Write tool in the Fergus MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fergus MCP Server MCP server in PolicyLayer and add a rule for manage-contacts: 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 Fergus MCP Server. Nothing to install.
manage-contacts 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 manage-contacts 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 manage-contacts. 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.
manage-contacts is provided by the Fergus MCP Server MCP server (jayco-design/fergus-mcp). 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 →