Close and post a list of pre-posted objects (fechar postagem SIGEP) — creates a PLP
AI agents use post_objects to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
This tool creates a new PLP (posting list) by closing and posting pre-posted objects. It creates/finalizes data (a new record/document), which is a Write operation. While it involves a payment-adjacent protocol (AP2), the action itself is about creating a posting record, not directly moving money.
From the tool's definition 'Close and post a list of pre-posted objects' and 'creates a PLP'
Documented attack patterns abuse exactly the kind of access post_objects gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for post_objects:
{
"version": "1",
"default": "deny",
"tools": {
"post_objects": {
"limits": [
{
"counter": "post_objects_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}post_objects stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Close and post a list of pre-posted objects (fechar postagem SIGEP) — creates a PLP. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for post_objects: 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 Ap2. Nothing to install.
post_objects 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 post_objects 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 post_objects. 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.
post_objects is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.