AI agents use add_object to create or update resources in Recall MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Recall MCP Server environment.
This tool creates and stores data in a Recall bucket, which is a reversible modification operation. It does not execute arbitrary code, delete data, or move funds, making it Write-category. Severity is medium because misuse could consume storage resources or result in unwanted data storage, but damage is limited to the bucket owner's account and can be reversed by deletion.
From the tool's definition "Add an object to a Recall bucket" — creates/uploads new data objects to blockchain storage. The description confirms this is a create operation (add), consistent with Write category definition.
Documented attack patterns abuse exactly the kind of access add_object gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Recall MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_object:
{
"version": "1",
"default": "deny",
"tools": {
"add_object": {
"limits": [
{
"counter": "add_object_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_object 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.
Add an object to a Recall bucket. It is categorised as a Write tool in the Recall MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Recall MCP Server MCP server in PolicyLayer and add a rule for add_object: 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 Recall MCP Server. Nothing to install.
add_object 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 add_object 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 add_object. 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.
add_object is provided by the Recall MCP Server MCP server (recallnet/recall-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Recall MCP Server, 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.
9 Recall MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.