Searches for conversations by customer email or ID with optional date filtering. Required: customerIdentifier (email/ID) Optional: startDate, endDate (DD/MM/YYYY format) Optional: keywords (array of terms to filter by) Use when looking for conversation history with a specific customer.
AI agents call search_conversations_by_customer to retrieve information from MCP Server for Intercom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval tool that queries and returns conversation data based on customer identifiers and optional filters. It has no side effects, does not modify data, execute code, or perform destructive operations. The 'search' operation and retrieval-focused parameters clearly indicate Read category.
From the tool's definition Tool description states it 'Searches for conversations' and retrieves 'conversation history with a specific customer.' Parameters are all input filters (customerIdentifier, dates, keywords) with no modification operations described.
Documented attack patterns abuse exactly the kind of access search_conversations_by_customer gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server for Intercom, and nothing reaches the server without passing your rules. This is the rule we recommend for search_conversations_by_customer:
{
"version": "1",
"default": "deny",
"tools": {
"search_conversations_by_customer": {}
}
}search_conversations_by_customer is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Searches for conversations by customer email or ID with optional date filtering. Required: customerIdentifier (email/ID) Optional: startDate, endDate (DD/MM/YYYY format) Optional: keywords (array of terms to filter by) Use when looking for conversation history with a specific customer. It is categorised as a Read tool in the MCP Server for Intercom MCP Server, which means it retrieves data without modifying state.
Register the MCP Server for Intercom MCP server in PolicyLayer and add a rule for search_conversations_by_customer: 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 MCP Server for Intercom. Nothing to install.
search_conversations_by_customer 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 search_conversations_by_customer 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 search_conversations_by_customer. 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.
search_conversations_by_customer is provided by the MCP Server for Intercom MCP server (raoulbia-ai/mcp-server-for-intercom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Server for Intercom, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 MCP Server for Intercom tools catalogued and risk-classified — across an index of 43,000+ MCP servers.