AI agents use chat_append_stream to create or update resources in Slack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack environment.
The tool appends to chat content, which is a write operation that modifies data reversibly. While the description is empty (lowering confidence slightly), the name and server context strongly suggest message modification. Severity is high because uncontrolled message appending could manipulate conversations, inject false information, or spam channels.
From the tool's definition Tool name 'chat_append_stream' indicates appending to chat messages; server description states it provides access to 'messages' among other Slack data; 'append' suggests modifying/adding content to existing messages or streams.
Attacks that exploit this kind of access
chat_append_stream. It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slack MCP server in PolicyLayer and add a rule for chat_append_stream: 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 Slack. Nothing to install.
chat_append_stream is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the chat_append_stream 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 chat_append_stream. 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.
chat_append_stream is provided by the Slack MCP server (karbassi/slack-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 →