Retrieve message history for a conversation
AI agents call get_conversation_history to retrieve information from Copilot Studio Agent Direct Line without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical data from an existing conversation without modifying, deleting, or executing any operations. It is a simple data retrieval function analogous to a 'get' or 'fetch' operation. The blast radius of misuse is minimal, limited to potential exposure of conversation contents that may already be accessible to the user.
From the tool's definition Tool name is 'get_conversation_history' and description states 'Retrieve message history for a conversation' — core Read operation that queries existing conversation data with no side effects.
Attacks that exploit this kind of access
Retrieve message history for a conversation. It is categorised as a Read tool in the Copilot Studio Agent Direct Line MCP Server, which means it retrieves data without modifying state.
Register the Copilot Studio Agent Direct Line MCP server in PolicyLayer and add a rule for get_conversation_history: 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 Copilot Studio Agent Direct Line. Nothing to install.
get_conversation_history 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_conversation_history 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_conversation_history. 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_conversation_history is provided by the Copilot Studio Agent Direct Line MCP server (swigerb/copilot-studio-agent-direct-line-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 →