Get all replies in a message thread
AI agents call mattermost_get_thread_replies to retrieve information from Mattermost without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing message thread replies without modifying, deleting, or executing any operations. It is a standard read operation with minimal risk, as it simply exposes access to data that the user already has permission to view in Mattermost.
From the tool's definition Tool name 'mattermost_get_thread_replies' and description 'Get all replies in a message thread' indicate a retrieval operation with no side effects. The verb 'Get' and the read-only nature of querying existing thread data confirm this is a query operation.
Attacks that exploit this kind of access
Get all replies in a message thread. It is categorised as a Read tool in the Mattermost MCP Server, which means it retrieves data without modifying state.
Register the Mattermost MCP server in PolicyLayer and add a rule for mattermost_get_thread_replies: 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 Mattermost. Nothing to install.
mattermost_get_thread_replies 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 mattermost_get_thread_replies 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 mattermost_get_thread_replies. 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.
mattermost_get_thread_replies is provided by the Mattermost MCP server (@conarti/mattermost-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 →