get_decisions_for_context
AI agents call get_decisions_for_context to retrieve information from Metatron without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing decision records to inform coding agents. It has no side effects, does not modify data, execute code, or perform destructive operations. The sibling tools (submit_candidate_decision, submit_feedback) are write operations, while this one reads from the system.
From the tool's definition Tool name 'get_decisions_for_context' indicates retrieval of stored decision data without modification. The empty description limits certainty, but the verb 'get' and context (Metatron serves structured priors to agents) strongly suggest a read operation that…
Documented attack patterns abuse exactly the kind of access get_decisions_for_context 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 get_decisions_for_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_decisions_for_context": {}
}
}get_decisions_for_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_decisions_for_context. It is categorised as a Read tool in the Metatron MCP Server, which means it retrieves data without modifying state.
Register the Metatron MCP server in PolicyLayer and add a rule for get_decisions_for_context: 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.
get_decisions_for_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_decisions_for_context 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 get_decisions_for_context. 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.
get_decisions_for_context 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.