get_all_conversations
AI agents call get_all_conversations to retrieve information from Multilead Open API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or query conversation records from the Multilead platform. The absence of action verbs like 'create', 'update', 'delete', or 'execute' indicates a read-only operation with no side effects. Even if an AI agent misuses it by retrieving sensitive conversations, the impact is limited to data exposure rather than modification or deletion.
From the tool's definition Tool name 'get_all_conversations' indicates retrieval of conversation data with no modification capability. The 'get' prefix is a standard pattern for read-only operations. No description provided to suggest otherwise.
Attacks that exploit this kind of access
get_all_conversations. It is categorised as a Read tool in the Multilead Open API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Multilead Open API MCP Server MCP server in PolicyLayer and add a rule for get_all_conversations: 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 Multilead Open API MCP Server. Nothing to install.
get_all_conversations 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_all_conversations 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_all_conversations. 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_all_conversations is provided by the Multilead Open API MCP Server MCP server (vanman2024/multilead-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 →