Medium Risk

foodblock_create_agent

Register a new AI agent in the FoodBlock system. The agent gets its own identity, Ed25519 keypair, and can sign blocks. Every agent must have an operator — the human or business it acts for. IMPORTANT: Save the returned credentials — they cannot be recovered after server restart.

Bulk/mass operation — affects multiple targets

Part of the Foodblock MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

foodblock-mcp Write Risk 3/5

AI agents use foodblock_create_agent to create or modify resources in Foodblock. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call foodblock_create_agent repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Foodblock.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

io-github-foodxdevelopment-foodblock-mcp.yaml
tools:
  foodblock_create_agent:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Foodblock policy for all 17 tools.

Tool Name foodblock_create_agent
Category Write
Risk Level Medium

View all 17 tools →

Agents calling write-class tools like foodblock_create_agent have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the foodblock_create_agent tool do? +

Register a new AI agent in the FoodBlock system. The agent gets its own identity, Ed25519 keypair, and can sign blocks. Every agent must have an operator — the human or business it acts for. IMPORTANT: Save the returned credentials — they cannot be recovered after server restart.. It is categorised as a Write tool in the Foodblock MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on foodblock_create_agent? +

Add a rule in your Intercept YAML policy under the tools section for foodblock_create_agent. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Foodblock MCP server.

What risk level is foodblock_create_agent? +

foodblock_create_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit foodblock_create_agent? +

Yes. Add a rate_limit block to the foodblock_create_agent rule in your Intercept 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.

How do I block foodblock_create_agent completely? +

Set action: deny in the Intercept policy for foodblock_create_agent. 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.

What MCP server provides foodblock_create_agent? +

foodblock_create_agent is provided by the Foodblock MCP server (foodblock-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Foodblock

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.