This record as markdown: /tools/holdmybeer-gg-blend-ai/join-objects.md
What join_objects does on Blend Ai
AI agents use join_objects to create or update resources in Blend Ai, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blend Ai environment.
Why join_objects is rated Medium
An AI agent can call join_objects faster than any human can review: one bad instruction and it creates or modifies resources in Blend Ai by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs join_objects safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Blend Ai, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For join_objects, this is the rule to start with:
join_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Blend Ai, apply this rule, and every join_objects call is checked against it from then on.
Questions about join_objects
join_objects is a write tool on the Blend Ai MCP server. It is categorised as a Write tool in the Blend Ai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Blend Ai MCP server in PolicyLayer and add a rule for join_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 Blend Ai. Nothing to install.
join_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 join_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 join_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.
join_objects is provided by the Blend Ai MCP server (holdmybeer-gg/blend-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Blend Ai, and thousands of servers like it.
This server
Across the catalogue