snow_jwt_decode
Decode a JWT into its header and payload (base64-URL → JSON). Does NOT verify the signature — useful for inspecting claims, not for trusting them. Local operation, no ServiceNow call.
This record as markdown: /tools/serac/snow-jwt-decode.md
What snow_jwt_decode does on Serac
AI agents call snow_jwt_decode to retrieve information from Serac without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why snow_jwt_decode is rated Low
This tool performs a purely local, read-only decode of a JWT token. It makes no network calls, modifies no data, and explicitly notes it does not verify the signature. The only risk is that decoded JWT payloads may contain sensitive claims (user identity, roles, etc.), but misuse potential is low since no external systems are affected.
From the tool's definition Decode a JWT into its header and payload (base64-URL → JSON). Does NOT verify the signature. Local operation, no ServiceNow call.
Attacks that exploit this kind of access
The rule that runs snow_jwt_decode safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Serac, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For snow_jwt_decode, this is the rule to start with:
snow_jwt_decode is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Serac, apply this rule, and every snow_jwt_decode call is checked against it from then on.
Questions about snow_jwt_decode
Decode a JWT into its header and payload (base64-URL → JSON). Does NOT verify the signature — useful for inspecting claims, not for trusting them. Local operation, no ServiceNow call. It is categorised as a Read tool in the Serac MCP Server, which means it retrieves data without modifying state.
Register the Serac MCP server in PolicyLayer and add a rule for snow_jwt_decode: 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 Serac. Nothing to install.
snow_jwt_decode 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 snow_jwt_decode 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 snow_jwt_decode. 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.
snow_jwt_decode is provided by the Serac MCP server (serac-labs/serac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Serac, and thousands of servers like it.
This server
Across the catalogue