Get prioritized list of commits requiring action
AI agents call fork_parity_get_actionable_items to retrieve information from Fork Parity MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and prioritizes existing commit information for human review and decision-making. It performs no writes, deletions, executions, or financial operations. It is a reporting/query tool that helps users identify what needs attention, consistent with Read category functions like 'list', 'get', or 'fetch'.
From the tool's definition Tool name and description indicate 'Get prioritized list' — a retrieval operation that queries and returns data about commits.
Attacks that exploit this kind of access
Get prioritized list of commits requiring action. It is categorised as a Read tool in the Fork Parity MCP MCP Server, which means it retrieves data without modifying state.
Register the Fork Parity MCP server in PolicyLayer and add a rule for fork_parity_get_actionable_items: 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 Fork Parity MCP. Nothing to install.
fork_parity_get_actionable_items 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 fork_parity_get_actionable_items 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 fork_parity_get_actionable_items. 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.
fork_parity_get_actionable_items is provided by the Fork Parity MCP server (moikas-code/fork-parity-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 →