AI agents call research.signal.calibration to retrieve information from Rekko MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the naming convention and context within a research-focused module, this tool likely retrieves or evaluates calibration metrics for prediction signals (a read/query operation). However, the empty description significantly lowers confidence. If it were to execute backtests or trigger trading actions, it could be Execute. If it modifies signal models, it would be Write.
From the tool's definition Tool name 'research.signal.calibration' suggests analysis or evaluation of signal quality/accuracy; described under a research module focused on 'prediction market intelligence' and 'strategy signals'. No description provided to confirm exact functionality.
Attacks that exploit this kind of access
research.signal.calibration. It is categorised as a Read tool in the Rekko MCP MCP Server, which means it retrieves data without modifying state.
Register the Rekko MCP server in PolicyLayer and add a rule for research.signal.calibration: 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 Rekko MCP. Nothing to install.
research.signal.calibration 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 research.signal.calibration 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 research.signal.calibration. 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.
research.signal.calibration is provided by the Rekko MCP server (rekko-ai/rekko-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 →