MCP Path
Codex Sidecar start
Codex Sidecar start is a public reference for embedded agent runtimes and runtime communication. 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
- Sidecar Agent Orchestration (Embedded Runtimes)
- Effect
- changes state
- Status
- Reference
- Path
- 47.2
Purpose
What this entry explains
What it does
This reference explains Codex Sidecar start for embedded agent runtimes and runtime communication. 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 carry out the bounded step "Codex Sidecar start" for embedded agent runtimes and runtime communication.
- 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.
Codex Sidecar start describes a behavior for embedded agent runtimes and runtime communication. 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 Codex Sidecar start 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: current discovery and actual response status. Safety axes: Browser state. The reference path alone is not permission to execute. Before acting, check current MCP discovery, visible target, scope, and the actual response.
Family example
An agent prepares a bounded run in embedded agent runtimes and runtime communication and must keep scope, progress, and stop condition visible.
The agent starts with Claude Sidecar start, reads the current response or reference, and only then chooses the concrete next tool.
Scope, budget, progress, stop condition, and terminal status remain part of the run.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 fields
No fixed public response field is derived from the catalog source for this path. Use current tool discovery and the actual response before chaining the next step.
Safety
Boundary before execution
Can change browser, page, or workflow state. The target and expected result must be clear before execution.
Confirm the current target first, perform only the intended bounded action, and verify the resulting page or workflow state afterwards.
For humans, this entry names the browser or workflow state in embedded agent runtimes and runtime communication that may change, so the action can be reviewed before and after execution.
High-Impact Review
Execution boundary and recheck hints
Review category: Plugin runtime
Plugin code and runtime calls stay limited to explicitly approved tools, permissions, and target contexts.
False assumption: an installed or loaded plugin may use all available browser data.
Approval, active tab, permission, and test result must remain visible user controls.
Execute plugin capabilities only after current tool discovery and permission checks; do not blindly chain external runtime output.
Recheck when permissions are missing, a plugin is unknown, or runtime status diverges from expected scope.
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.
browser_state_change
Changes tab, navigation, focus, claim, scroll position, window state, or browser environment.
Confirm the target context visibly before execution and verify that the expected browser state was reached afterwards.