Add a pair correction to Learning Memory. Source is set to 'agent' with trust=0.5 (lower than human steward decisions which are 1.0). Pair (id_a, id_b) is canonicalized to (min, max) before storage.
Risk signalsAccepts file system path (path)
Part of the GoldenMatch server.
Free to start. No card required.
AI agents use add_correction to create or modify resources in GoldenMatch. 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 add_correction repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach GoldenMatch.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"add_correction": {
"limits": [
{
"counter": "add_correction_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full GoldenMatch policy for all 42 tools.
These attack patterns abuse exactly the kind of access add_correction gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Add a pair correction to Learning Memory. Source is set to 'agent' with trust=0.5 (lower than human steward decisions which are 1.0). Pair (id_a, id_b) is canonicalized to (min, max) before storage.. It is categorised as a Write tool in the GoldenMatch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GoldenMatch MCP server in PolicyLayer and add a rule for add_correction: 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 GoldenMatch. Nothing to install.
add_correction 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 add_correction 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 add_correction. 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.
add_correction is provided by the GoldenMatch MCP server (pypi:goldenmatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 42 GoldenMatch tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.