Coerce an arbitrary tool-call trace (an array of {name,args} entries or a partial Trace object) into the canonical agentsnap Trace shape. Returns the normalized trace plus a SHA-256 fingerprint hash computed over the canonical (key-sorted) JSON, so two runs can be byte-compared cheaply.
Part of the Agentsnap MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call normalize_trace to perform operations in Agentsnap. While the risk category is not fully classified, applying a rate limit gives you visibility into how often the tool is called and prevents unexpected bursts of activity from autonomous agents.
Applying a policy to normalize_trace gives you an audit trail of every call an AI agent makes. Even for low-risk tools, visibility into agent behaviour helps you debug issues, optimise workflows, and maintain compliance with your organisation's security requirements.
Apply a rate limit to control usage and monitor for unexpected behaviour.
tools:
normalize_trace:
rules:
- action: allow
rate_limit:
max: 60
window: 60See the full Agentsnap policy for all 3 tools.
Agents calling other-class tools like normalize_trace have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Other risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Coerce an arbitrary tool-call trace (an array of {name,args} entries or a partial Trace object) into the canonical agentsnap Trace shape. Returns the normalized trace plus a SHA-256 fingerprint hash computed over the canonical (key-sorted) JSON, so two runs can be byte-compared cheaply.. It is categorised as a Other tool in the Agentsnap MCP Server, which means it performs auxiliary operations.
Add a rule in your Intercept YAML policy under the tools section for normalize_trace. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agentsnap MCP server.
normalize_trace is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the normalize_trace rule in your Intercept 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 Intercept policy for normalize_trace. 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.
normalize_trace is provided by the Agentsnap MCP server (@mukundakatta/agentsnap-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.