workspace_chat
AI agents call workspace_chat to retrieve information from RunWhen Platform MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Workspace chat access is primarily a read operation—retrieving messages or chat history with no indication of side effects like deletion, modification, or external execution. While the empty description reduces confidence slightly, the naming and context of other tools (create_*, delete_*, deploy_*) that perform write/destructive actions suggest this one retrieves data.
From the tool's definition Tool name 'workspace_chat' suggests retrieval or querying of chat messages/history from a workspace. The server description mentions 'workspace chat with AI assistant' as a data access capability.
Attacks that exploit this kind of access
workspace_chat. It is categorised as a Read tool in the RunWhen Platform MCP MCP Server, which means it retrieves data without modifying state.
Register the RunWhen Platform MCP server in PolicyLayer and add a rule for workspace_chat: 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 RunWhen Platform MCP. Nothing to install.
workspace_chat 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 workspace_chat 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 workspace_chat. 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.
workspace_chat is provided by the RunWhen Platform MCP server (runwhen-contrib/runwhen-platform-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 →