AI agents call slack_get_file_info to retrieve information from MCP Slack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file metadata from Slack without downloading or modifying content, which is a read-only operation. The server description explicitly states it is 'Secure read-only,' confirming no write, execute, or destructive capabilities. The blast radius is minimal—metadata disclosure is low-risk compared to file content or modifications.
From the tool's definition Tool name 'slack_get_file_info' and description 'Get metadata about a Slack file (no content download)' indicate retrieval of metadata only without side effects or data modification.
Attacks that exploit this kind of access
Get metadata about a Slack file (no content download). It is categorised as a Read tool in the MCP Slack MCP Server, which means it retrieves data without modifying state.
Register the MCP Slack MCP server in PolicyLayer and add a rule for slack_get_file_info: 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 MCP Slack. Nothing to install.
slack_get_file_info 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 slack_get_file_info 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 slack_get_file_info. 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.
slack_get_file_info is provided by the MCP Slack MCP server (pypi:mcp-slack-crunchtools). 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 →