Run the group units seeder using a Mealie-native payload.
AI agents invoke seed_group_units to trigger actions in Mealie MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool 'runs' a seeder, which is an execution action that creates/populates unit data in the group. Seeders typically write bulk data but are triggered as an operation rather than a simple write. The blast radius is medium as it could overwrite or flood existing units data, but it is likely reversible.
From the tool's definition 'Run the group units seeder' — executes a seeder operation that populates/initializes data
Attacks that exploit this kind of access
Run the group units seeder using a Mealie-native payload. It is categorised as a Execute tool in the Mealie MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mealie MCP Server MCP server in PolicyLayer and add a rule for seed_group_units: 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 Mealie MCP Server. Nothing to install.
seed_group_units is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the seed_group_units 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 seed_group_units. 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.
seed_group_units is provided by the Mealie MCP Server MCP server (nikopol666/mealie-mcp). 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 →