MCP Path
Secret-Read Policy Upgrade
Secret-Read Policy Upgrade is a public reference for sensitive browser, identity, or session data. It names the signal, policy, or flow an agent should understand before choosing a concrete tool.
Reference page for a documented MCP capability path.
- Type
- MCP path
- Family
- Site Data Management (Cookies, Storage, Cache)
- Effect
- sensitive
- Status
- Reference
- Path
- 52.33
Purpose
What this entry explains
What it does
This reference explains Secret-Read Policy Upgrade for sensitive browser, identity, or session data. It is kept as a named reference so agents can cite the flow without inventing a tool name.
Use when
- Use this entry when an agent needs to handle the sensitive path "Secret-Read Policy Upgrade" for sensitive browser, identity, or session data.
- Use it as a reference path when the catalog describes a capability but no single public tool name is explicit.
- Use it before chaining follow-up tools so the next step is based on current evidence.
Reference Use
How agents should cite and apply this area
Examples are maintained at family level and use only public tool names or reference paths already present in the catalog.
Secret-Read Policy Upgrade describes a gate for sensitive browser, identity, or session data. The path shows which signal, gate, behavior, or boundary must be checked before choosing a concrete tool.
An agent cites this path when it needs Secret-Read Policy Upgrade as context for a decision, block, target check, or follow-up tool choice.
The public source does not name one callable tool for this path. The documentation therefore keeps it as a reference path and does not invent a callable name.
Relevant response signals: HighImpact, SensitiveRead. Safety axes: Read current state, Sensitive, User confirmation. The reference path alone is not permission to execute. Before acting, check current MCP discovery, visible target, scope, and the actual response.
Family example
A task in sensitive browser, identity, or session data can trigger powerful execution and therefore needs target, approval, and result check before the step.
The agent starts with nova.tools_bundle, reads the current response or reference, and only then chooses the concrete next tool.
Current discovery, target, user control, warning signals, and result check come before execution.Contract
Inputs and important response fields
This page is a public reference. Agents and integrators should still read current MCP tool discovery before execution, because schemas can be gated by settings or version.
Inputs
No stable public input field is derived from the catalog source for this path. Read current MCP discovery before execution.
| Response field | Explanation |
|---|---|
HighImpact | Response field named by the catalog source. Treat it as current evidence for the next decision. |
SensitiveRead | Response field named by the catalog source. Treat it as current evidence for the next decision. |
Safety
Boundary before execution
May touch sensitive data, permissions, credentials, identity, or external connection paths. Use only with explicit scope and visible user control.
Require explicit purpose and current context, avoid exposing secrets in prompts or logs, and stop when permission or identity state is unclear.
For humans, this entry marks the sensitive surface in sensitive browser, identity, or session data and keeps permission, credential, or external-connection handling explicit.
High-Impact Review
Execution boundary and recheck hints
Review category: Vault/credentials
Credentials, tokens, and secrets may be used only for the named purpose and current target context.
False assumption: a stored value may be copied into prompts, logs, or third-party tool chains.
Purpose, target site, identity context, and approval must be reviewable by the user.
Do not guess, display, log, or forward secrets; use only protected fill or check paths with current scope.
Stop when identity, domain, approval, or expected input location is not unambiguously visible.
Safety Axes
How this path can affect work
Axes are stable catalog signals for humans, agents, and LLM discovery. One path can carry several axes.
read_current_state
Reads current state, response signals, or evidence without treating that alone as permission for a follow-up action.
Use the signal as current evidence and re-check target, scope, and visible state before any follow-up action.sensitive_data
Touches cookies, storage, clipboard, credentials, tokens, user content, identity, or private data.
Use only with bounded purpose and visible user control; do not guess, log, or forward sensitive values.user_confirmation
Requires visible confirmation, target review, approval, or deliberate user control.
Do not proceed until the required confirmation is visible or unambiguous in the current context.