set_confidence
AI agents use set_confidence to create or update resources in Chronos MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chronos MCP environment.
This tool writes or modifies confidence metadata in the persistent knowledge graph. While not destructive (confidence values can be adjusted again) or financial, it alters stored state, making it Write category. Severity is medium because confidence manipulation could affect decision-making quality in downstream queries, but the impact is localized to metadata rather than data deletion or external operations.
From the tool's definition Tool name is 'set_confidence' which modifies a confidence value. Related tools on the server include 'boost_confidence' and 'consolidate_memories', indicating this tool updates stored metadata.
Attacks that exploit this kind of access
set_confidence. It is categorised as a Write tool in the Chronos MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chronos MCP server in PolicyLayer and add a rule for set_confidence: 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 Chronos MCP. Nothing to install.
set_confidence 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 set_confidence 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 set_confidence. 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.
set_confidence is provided by the Chronos MCP server (kodaxadev/chronosmcp). 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 →