Mark messages as READ by you (a read receipt). Lets the team see who has
AI agents call acknowledge to retrieve information from Claude Team MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only records that a message has been read by the user—a read receipt mechanism. It retrieves or records visibility/acknowledgment state without creating, modifying, deleting, or executing external operations. The most severe risk is low, as misuse would merely result in incorrect read receipts with no impact on data integrity or system operations.
From the tool's definition Tool name is 'acknowledge' and description states 'Mark messages as READ' and 'read receipt'. The action is to mark/acknowledge messages that have been read, with no data modification or side effects beyond recording acknowledgment status.
Attacks that exploit this kind of access
Mark messages as READ by you (a read receipt). Lets the team see who has. It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for acknowledge: 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 Claude Team MCP. Nothing to install.
acknowledge 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 acknowledge 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 acknowledge. 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.
acknowledge is provided by the Claude Team MCP server (lakshan12367/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 →