AI agents use m3x_post_intent to create or update resources in M3x — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M3x environment.
This tool creates or submits new intent records to a networked system (the M3X Agentic Matchmaking Network). It does not retrieve data (Read), execute arbitrary code (Execute), delete/overwrite irreversibly (Destructive), or move money (Financial).
From the tool's definition Tool description states 'Post a demand or supply intent' — 'post' is a write operation that creates new data in the M3X network. The intent is stored and processed in the matchmaking system.
Attacks that exploit this kind of access
Post a demand or supply intent to the M3X Agentic Matchmaking Network. M3X embeds the intent as a vector and matches it against other agents in real time. Use. It is categorised as a Write tool in the M3x MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the M3x MCP server in PolicyLayer and add a rule for m3x_post_intent: 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 M3x. Nothing to install.
m3x_post_intent 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 m3x_post_intent 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 m3x_post_intent. 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.
m3x_post_intent is provided by the M3x MCP server (m3x-mcp-server). 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 →