发送Markdown格式消息到钉钉群
AI agents use send_markdown_message to create or update resources in MCP Commute Assistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Commute Assistant environment.
This tool creates and sends messages to DingTalk groups, which is a reversible write operation. Messages can be deleted or edited afterward. While it modifies state (adds messages to a chat platform), it does not delete data, execute code, move money, or create irreversible changes.
From the tool's definition Tool name 'send_markdown_message' and description '发送Markdown格式消息到钉钉群' (send Markdown format message to DingTalk group) indicate the tool sends/posts messages to a communication platform.
Attacks that exploit this kind of access
发送Markdown格式消息到钉钉群. It is categorised as a Write tool in the MCP Commute Assistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Commute Assistant MCP server in PolicyLayer and add a rule for send_markdown_message: 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 Commute Assistant. Nothing to install.
send_markdown_message 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 send_markdown_message 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 send_markdown_message. 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.
send_markdown_message is provided by the MCP Commute Assistant MCP server (standup-coder/mcp4coder). 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 →