submit_candidate_decision
AI agents use submit_candidate_decision to create or update resources in Metatron — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metatron environment.
The tool creates or submits new decision data to a self-hosted codebase documentation system. This is a reversible write operation (decisions can presumably be updated or removed later). The empty description reduces confidence, but the name and context strongly suggest data creation rather than querying (Read) or irreversible deletion (Destructive).
From the tool's definition Tool name 'submit_candidate_decision' indicates submission of data; paired with sibling tool 'get_decisions_for_context' suggests a read-write pattern where this tool writes/creates decision records to the Metatron knowledge base.
Documented attack patterns abuse exactly the kind of access submit_candidate_decision gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Metatron, and nothing reaches the server without passing your rules. This is the rule we recommend for submit_candidate_decision:
{
"version": "1",
"default": "deny",
"tools": {
"submit_candidate_decision": {
"limits": [
{
"counter": "submit_candidate_decision_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}submit_candidate_decision 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.
submit_candidate_decision. It is categorised as a Write tool in the Metatron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metatron MCP server in PolicyLayer and add a rule for submit_candidate_decision: 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 Metatron. Nothing to install.
submit_candidate_decision 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 submit_candidate_decision 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 submit_candidate_decision. 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.
submit_candidate_decision is provided by the Metatron MCP server (kerbelp/metatron). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Metatron, 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.
3 Metatron tools catalogued and risk-classified — across an index of 43,000+ MCP servers.