get_opportunity_tool
AI agents call get_opportunity_tool to retrieve information from Capsulecrm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries CRM opportunity data with no side effects. It matches the Read category pattern of fetching existing data. Severity is low because retrieval alone poses minimal risk to business operations unless the data itself is highly sensitive, but typical CRM opportunity reads are routine.
From the tool's definition Tool name 'get_opportunity_tool' and context of sibling tools ('find_opportunities_tool', 'list_opportunities_tool') indicate this retrieves opportunity data from CapsuleCRM.
Attacks that exploit this kind of access
get_opportunity_tool. It is categorised as a Read tool in the Capsulecrm MCP Server, which means it retrieves data without modifying state.
Register the Capsulecrm MCP server in PolicyLayer and add a rule for get_opportunity_tool: 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 Capsulecrm. Nothing to install.
get_opportunity_tool 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 get_opportunity_tool 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 get_opportunity_tool. 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.
get_opportunity_tool is provided by the Capsulecrm MCP server (monadsag/capsulecrm-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 →