Call any Slack Web API method directly.
AI agents invoke slack_api_call to trigger actions in Slack Max API MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool allows invocation of any Slack Web API method, spanning the full range of capabilities: reading data, writing/modifying content, deleting messages or channels, managing users, and potentially triggering financial or administrative actions.
From the tool's definition "Call any Slack Web API method directly" — arbitrary API method execution with no restriction on which methods can be called
Attacks that exploit this kind of access
Call any Slack Web API method directly. It is categorised as a Execute tool in the Slack Max API MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Slack Max API MCP server in PolicyLayer and add a rule for slack_api_call: 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 Max API MCP. Nothing to install.
slack_api_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the slack_api_call 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_api_call. 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_api_call is provided by the Slack Max API MCP server (jeongwoobin335/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 →