AI agents call chain_confirm_bundle to retrieve information from Satsignal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to open and extract data from a bundle file for confirmation/verification purposes. No mention of writing, deleting, executing external code, or financial transactions. The operation is reversible and read-only in nature, making it a Read category risk.
From the tool's definition 'open a local .mbnt bundle, extract' indicates reading and parsing a local file bundle without modification. The tool name prefix 'CHAIN-CONFIRM' and context of verification/lookup capabilities suggest read-only validation operations.
Attacks that exploit this kind of access
CHAIN-CONFIRM ONLY: open a local .mbnt bundle, extract. It is categorised as a Read tool in the Satsignal MCP Server, which means it retrieves data without modifying state.
Register the Satsignal MCP server in PolicyLayer and add a rule for chain_confirm_bundle: 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 Satsignal. Nothing to install.
chain_confirm_bundle 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 chain_confirm_bundle 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 chain_confirm_bundle. 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.
chain_confirm_bundle is provided by the Satsignal MCP server (steleet/satsignal-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 →