Skip to main content
Glama

start_remote_control

Start or resume a native Claude Code session with Remote Control enabled, allowing Codex to manage persistent conversations across refreshes. Uses per-user broker on Windows, tmux on Linux/macOS.

Instructions

Start or resume a native Claude Code session with Remote Control enabled. Windows sessions are owned by a persistent per-user broker so Codex tasks can reconnect after refresh; Linux/macOS sessions use tmux.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoProject directory. If RAIL_CONNECTOR_ALLOWED_ROOTS is set, cwd must be inside one of those roots./root
bareNoStart Claude with --bare. This may bypass normal keychain/OAuth configuration.
modelNoOptional Claude model alias or full model name passed as --model.
toolsNoOptional Claude --tools list. This controls the available built-in tool set.
effortNoOptional Claude effort passed as --effort.
safeModeNoStart Claude with --safe-mode for troubleshooting.
sessionIdNoExisting Claude session id to resume. Omit to start a fresh session.
ultracodeNoRequest session-scoped Ultracode. The MCP prefers an advertised effort value; generic settings are experimental and unverified. Do not combine with effort or safeMode.
remoteNameNoRemote Control display name. This does not rename the Claude conversation.Rail-Connector
forkSessionNoFork when resuming or continuing, using Claude's --fork-session. Requires sessionId or continueLatest.
tmuxSessionNoDeprecated alias for managedSession.
allowedToolsNoOptional Claude --allowedTools list. This pre-approves tools; it does not replace --tools.
killExistingNoKill an existing managed session with this name before starting.
newSessionIdNoOptional UUID to assign to a new Claude conversation. Do not combine with sessionId or continueLatest.
resumeChoiceNoIf Claude asks how to resume a large session, optionally choose summary, full, or don't ask again.none
sessionTitleNoOptional title for a new Claude conversation. Use rename_claude_session after launch for later changes.
axScreenReaderNoStart Claude with --ax-screen-reader for flatter terminal output when supported.
continueLatestNoResolve the latest local conversation for this cwd to an exact UUID, then resume it.
managedSessionNoManaged terminal session name.rail-connector-managed
permissionModeNoSemantic Claude permission mode. default resolves to the installed CLI's default/manual alias. bypassPermissions also requires confirmBypassPermissions and an acknowledged RAIL_CONNECTOR_ALLOW_BYPASS_PERMISSIONS policy.default
trustWorkspaceNoAccept Claude's workspace trust prompt only when that prompt is detected. Defaults to false.
disallowedToolsNoOptional Claude --disallowedTools list. This denies specific tools.
confirmUltracodeNoRequired with ultracode=true to acknowledge xhigh effort and dynamic workflow orchestration.
forceKillExistingNoPermit replacement of a busy session and force termination if graceful exit fails.
resumeSessionNameNoExact Claude conversation title to resolve to a UUID before launch.
confirmBypassPermissionsNoPer-call acknowledgement required with bypassPermissions; the MCP process must separately acknowledge either local-host or isolated use through RAIL_CONNECTOR_ALLOW_BYPASS_PERMISSIONS.
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It does reveal a meaningful behavioral trait: sessions are persistent per-user on Windows and use tmux on Linux/macOS. However, it does not disclose other important behaviors such as potential session termination via killExisting/forceKillExisting, the need for confirmations with bypassPermissions, or the long-running nature of sessions. The description adds some context but is not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary action. Every sentence earns its place: the first states the purpose, the second provides a key platform nuance. No redundant or vague language.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with 26 parameters, no annotations, and no output schema. The description covers the core purpose and platform persistence but does not provide an overview of key behaviors like session killing, permission modes, or parameter interactions. Given the richness of the schema, the description is adequate but not complete for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each of the 26 parameters having detailed descriptions (e.g., permissionMode, killExisting, ultracode). The tool description itself does not add parameter-level semantics, but the schema already does the heavy lifting. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Start or resume') and the resource ('native Claude Code session with Remote Control enabled'). It distinguishes itself from sibling tools like stop_remote_control and capture_remote_control by focusing on session lifecycle initiation. The platform-specific detail (Windows broker vs tmux) adds additional clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: to start a new or resume an existing remote-controlled session. It provides context about platform-specific behavior (Windows broker vs tmux) that informs usage. However, it does not explicitly mention alternatives or when not to use it, but the context is clear enough for the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SNComrade/Rail-Connector-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server