@luckycat133/traecnclaw

MCPcommunity
v0.6.0io.github.Luckycat133MITUpdated 1mo agonpmGitHub

Focused MCP gateway and Agent Skill for TraeCN desktop automation, with a Web Control Console, CLI, and OpenClaw integration.

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
10Downloads/wk
1mo agoLast update
Reads these credentials
  • TRAECN_GATEWAY_TOKENAPI keyoptional

    Gateway bearer token.

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
Authorio.github.Luckycat133
LicenseMIT
Version0.6.0
Sourcenpm+mcp-registry
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 1 resolved · none vulnerable
Tool surface40 tools · 5 privileged
Security scan✓ Cleanv0.6.0 · 1mo agoHow well does this scan work?
EvalsNone
IndexedAug 26, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

40 tools · 5 privileged
Statically extracted from the published packagev0.6.0 · 1mo ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

traecn_capabilitiesReturn a compact agent-facing catalog of TraeCNclaw commands, HTTP endpoints, MCP surfaces, models, settings sections, and token-saving call order.

Return a compact agent-facing catalog of TraeCNclaw commands, HTTP endpoints, MCP surfaces, models, settings sections, and token-saving call order.

No input schema was published for this tool.

traecn_command_setprivilegedList the production command set OpenClaw can use to control TraeCN. Returns command names, summaries, and required/optional parameters.

List the production command set OpenClaw can use to control TraeCN. Returns command names, summaries, and required/optional parameters.

No input schema was published for this tool.

traecn_preflightReturn a compact one-call status/readiness/queue/dialog summary plus an optional command confirmation plan before side-effecting TraeCN work.

Return a compact one-call status/readiness/queue/dialog summary plus an optional command confirmation plan before side-effecting TraeCN work.

No input schema was published for this tool.

traecn_commandprivilegedNo description published

This tool published no description. Forge does not invent one.

traecn_vibe_workflowRun an unattended TraeCN vibe coding workflow: queue the initial task, auto-continue follow-up steps, survive model queues, and return a taskId for polling.

Run an unattended TraeCN vibe coding workflow: queue the initial task, auto-continue follow-up steps, survive model queues, and return a taskId for polling.

No input schema was published for this tool.

traecn_plan_operationCreate a compact side-effect and confirmation plan before executing a TraeCN command. This is a dry preflight and does not operate TraeCN.

Create a compact side-effect and confirmation plan before executing a TraeCN command. This is a dry preflight and does not operate TraeCN.

No input schema was published for this tool.

traecn_task_statusQuery the status of an async TraeCN task by taskId. Use after traecn_delegate returns a taskId with status "queued". Returns: done/queued/executing/error/cancelled/queue_timeout.

Query the status of an async TraeCN task by taskId. Use after traecn_delegate returns a taskId with status "queued". Returns: done/queued/executing/error/cancelled/queue_timeout.

No input schema was published for this tool.

traecn_cancel_taskCancel a queued TraeCN task. Only works for tasks in "queued" state.

Cancel a queued TraeCN task. Only works for tasks in "queued" state.

No input schema was published for this tool.

traecn_settings_actionPerform supported actions on the TraeCN settings panel through implemented gateway routes. Actions: navigate/clickTab, read, readAll/readTables, type/toggle/dropdown/set, back. Section names: general(通用), account(账号), agents(智能体), mcp(MCP), flow(对话流), model(模型), context(上下文), rules(规则和技能), beta(Bet…

Perform supported actions on the TraeCN settings panel through implemented gateway routes. Actions: navigate/clickTab, read, readAll/readTables, type/toggle/dropdown/set, back. Section names: general(通用), account(账号), agents(智能体), mcp(MCP), flow(对话流), model(模型), context(上下文), rules(规则和技能), beta(Bet…

No input schema was published for this tool.

traecn_settings_readRead settings from the TraeCN settings panel. Optionally specify a section (canonical names: general, account, agents, mcp, flow/models, context, rules, about). Returns the settings panel content as text.

Read settings from the TraeCN settings panel. Optionally specify a section (canonical names: general, account, agents, mcp, flow/models, context, rules, about). Returns the settings panel content as text.

No input schema was published for this tool.

traecn_settings_setChange a setting in the TraeCN settings panel. Specify the label text and new value. Optionally specify a section to navigate to first.

Change a setting in the TraeCN settings panel. Specify the label text and new value. Optionally specify a section to navigate to first.

No input schema was published for this tool.

traecn_statusCheck if TraeCNclaw gateway is reachable and TraeCN automation is ready.

Check if TraeCNclaw gateway is reachable and TraeCN automation is ready.

No input schema was published for this tool.

traecn_new_chatCreate a new chat in TraeCN and switch the UI to it.

Create a new chat in TraeCN and switch the UI to it.

No input schema was published for this tool.

traecn_delegateDelegate an IDE task to TraeCN desktop app and return the AI response. Queue-aware: if the model is busy/queued, returns { status: "queued", taskId, queueDetails } so you can use traecn_task_status to wait. If model is free, returns { status: "done", text, ... }. The taskId from a queued response l…

Delegate an IDE task to TraeCN desktop app and return the AI response. Queue-aware: if the model is busy/queued, returns { status: "queued", taskId, queueDetails } so you can use traecn_task_status to wait. If model is free, returns { status: "done", text, ... }. The taskId from a queued response l…

No input schema was published for this tool.

traecn_switch_modeSwitch TraeCN between SOLO and IDE modes.

Switch TraeCN between SOLO and IDE modes.

No input schema was published for this tool.

traecn_switch_modelSwitch the AI model used by TraeCN. Available models include: Doubao-Seed-2.0-Code, Doubao-Seed-1.8, GLM-5.1, DeepSeek-V3.1-Terminus, etc.

Switch the AI model used by TraeCN. Available models include: Doubao-Seed-2.0-Code, Doubao-Seed-1.8, GLM-5.1, DeepSeek-V3.1-Terminus, etc.

No input schema was published for this tool.

traecn_queue_statusCheck if the current TraeCN AI model is in a queued/busy state.

Check if the current TraeCN AI model is in a queued/busy state.

No input schema was published for this tool.

traecn_cleanup_queueFind and optionally delete accidental "wait for Trae queue" Solo conversations. With execute=true it stops running queue-probe chats before deleting them.

Find and optionally delete accidental "wait for Trae queue" Solo conversations. With execute=true it stops running queue-probe chats before deleting them.

No input schema was published for this tool.

traecn_cleanup_watch_statusRead local cleanup watcher lock/PID/stale status without contacting TraeCN or creating conversations.

Read local cleanup watcher lock/PID/stale status without contacting TraeCN or creating conversations.

No input schema was published for this tool.

traecn_long_queue_proof_startStart or dry-run the guarded GLM-5.2 long-queue proof. Defaults to dry-run; a new real submission requires execute=true and allowQuotaSpend=true.

Start or dry-run the guarded GLM-5.2 long-queue proof. Defaults to dry-run; a new real submission requires execute=true and allowQuotaSpend=true.

No input schema was published for this tool.

traecn_long_queue_proof_statusRead local GLM-5.2 proof status and recent evidence without sending any TraeCN prompt.

Read local GLM-5.2 proof status and recent evidence without sending any TraeCN prompt.

No input schema was published for this tool.

traecn_long_queue_proof_cancelCancel a local GLM-5.2 proof watcher/task tracking without submitting another TraeCN prompt.

Cancel a local GLM-5.2 proof watcher/task tracking without submitting another TraeCN prompt.

No input schema was published for this tool.

traecn_open_projectOpen a project in TraeCN. Set newInstance=true to open a separate window when TraeCN is already running.

Open a project in TraeCN. Set newInstance=true to open a separate window when TraeCN is already running.

No input schema was published for this tool.

traecn_chatQuickly trigger a task via trae-cn chat CLI (fire-and-forget, does not return AI response). Use traecn_delegate instead when you need to read the response.

Quickly trigger a task via trae-cn chat CLI (fire-and-forget, does not return AI response). Use traecn_delegate instead when you need to read the response.

No input schema was published for this tool.

traecn_update_selfUpdate the TraeCNclaw plugin to the latest version.

Update the TraeCNclaw plugin to the latest version.

No input schema was published for this tool.

traecn_approveDetect and approve/dismiss dialogs in TraeCN. Use when TraeCN shows a restricted mode, permission request, or confirmation dialog. Auto-detects the dialog type and clicks the appropriate button (trust, allow, confirm). Also supports deny/cancel actions.

Detect and approve/dismiss dialogs in TraeCN. Use when TraeCN shows a restricted mode, permission request, or confirmation dialog. Auto-detects the dialog type and clicks the appropriate button (trust, allow, confirm). Also supports deny/cancel actions.

No input schema was published for this tool.

traecn_dialog_statusCheck if there is a pending dialog (restricted mode, permission request, confirmation) in TraeCN. Returns hasDialog, dialogType (restricted_mode/approval/permission/command_execution/file_operation), question, and available buttons.

Check if there is a pending dialog (restricted mode, permission request, confirmation) in TraeCN. Returns hasDialog, dialogType (restricted_mode/approval/permission/command_execution/file_operation), question, and available buttons.

No input schema was published for this tool.

traecn_layered_commandprivilegedBuilds a layered prompt for precise TraeCN app control.

Builds a layered prompt for precise TraeCN app control.

No input schema was published for this tool.

commandprivilegedPreset command name

Preset command name

No input schema was published for this tool.

taskUser task or instruction text

User task or instruction text

No input schema was published for this tool.

projectPathOptional project path context

Optional project path context

No input schema was published for this tool.

traecn_skill_authoringCreates a concise, progressively disclosed skill plan for extending TraeCNclaw.

Creates a concise, progressively disclosed skill plan for extending TraeCNclaw.

No input schema was published for this tool.

skillNameNew skill module name

New skill module name

No input schema was published for this tool.

capabilityCapability the skill adds

Capability the skill adds

No input schema was published for this tool.

layered-architectureLayer order, capability model, and extension rules for TraeCN prompts.

Layer order, capability model, and extension rules for TraeCN prompts.

No input schema was published for this tool.

command-catalogprivilegedStable command names and command-specific capability profiles.

Stable command names and command-specific capability profiles.

No input schema was published for this tool.

traecn_send_messageSubmit one user instruction to TraeCN as durable background work and return its stable taskId immediately; the gateway owns queueing, retries, recovery, and result persistence. Use this for every delegated coding request, optionally targeting an existing conversation via conversationId. Do not send…

Submit one user instruction to TraeCN as durable background work and return its stable taskId immediately; the gateway owns queueing, retries, recovery, and result persistence. Use this for every delegated coding request, optionally targeting an existing conversation via conversationId. Do not send…

No input schema was published for this tool.

traecn_get_taskRead one known gateway task by ID: status plus final result, or the full execution trace with detailLevel 'trace' for diagnosis. Call once when notified of completion or once later when resuming after a disconnect. Not a progress primitive — do not poll in a tight loop.

Read one known gateway task by ID: status plus final result, or the full execution trace with detailLevel 'trace' for diagnosis. Call once when notified of completion or once later when resuming after a disconnect. Not a progress primitive — do not poll in a tight loop.

No input schema was published for this tool.

traecn_stop_generationStop only the generation currently visible in the named active TraeCN conversation. Visible output may belong to the user or another agent, so this requires acknowledgeUntrackedWork=true plus an audit reason. Prefer cancel_task whenever a gateway task ID exists.

Stop only the generation currently visible in the named active TraeCN conversation. Visible output may belong to the user or another agent, so this requires acknowledgeUntrackedWork=true plus an audit reason. Prefer cancel_task whenever a gateway task ID exists.

No input schema was published for this tool.

traecn_open_workspaceOpen one absolute local folder path as the active TraeCN workspace and verify it became active before returning. Call before submitting work that depends on a specific project; afterwards do not repeat the path inside the task message.

Open one absolute local folder path as the active TraeCN workspace and verify it became active before returning. Call before submitting work that depends on a specific project; afterwards do not repeat the path inside the task message.

No input schema was published for this tool.

39 of 40 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Focused MCP gateway and Agent Skill for TraeCN desktop automation, with a Web Control Console, CLI, and OpenClaw integration.

Keywords
traecntrae-cnelectroncdpautomationopenclawapiskillaimcp
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-08-30 — observed resolution, not a publisher declaration.

1 packages resolved · 1 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.