Skip to main content
Glama

TRAECNclaw MCP Skill

Generiert aus dem kanonischen TRAECNclaw 0.6.0 bei Commit 40bcf7707ed9b0ff7938aea8e511d0b87d300705.

TRAECNclaw ist ein lokal-first MCP-Server und eine Agent-Skill für die Bedienung der TraeCN-Desktop-App auf dem Mac des Benutzers. Dieses Repository ist der öffentliche Verteilungs-Spiegel: Es enthält die portable Skill, installierbare Server-Archive, Provenienz und Marktplatz-Metadaten, ohne die private kanonische Historie zu veröffentlichen.

TRAECNclaw stellt die MCP-Vertragsversion 5 mit genau 20 stabilen, einzieligen Tools bereit. Der normale Agent-Ablauf ist:

  1. Öffnen Sie einen Arbeitsbereich nur bei Bedarf.

  2. Wählen Sie Modell oder Modus nur bei Bedarf.

  3. Senden Sie eine Nachricht und geben Sie den Aufruferkontext frei.

  4. Legacy-MCP-Clients erhalten eine dauerhafte Benachrichtigung; moderne 2026-07-28-Hosts können Tasks aushandeln und die genaue zurückgegebene Task-ID abonnieren.

Warteschlangen, Warten, Wiederherstellung, routinemäßige Nicht-Befehlsfragen, Aufgabenbesitz und dauerhafte Fertigstellung bleiben Gateway-verwaltet.

Der lokale Server verwendet zeilengetrenntes stdio, implementiert MCP 2026-07-28 und bleibt mit initialisierungsbasierten 2025-11-25- und 2024-11-05-Clients kompatibel. Die TRAECNclaw-Vertragsversion 5 ist die Tool-Oberflächenversion, nicht die MCP-Protokollrevision. Die unabhängig ausgehandelte, Upstream-Entwurfs-Erweiterung io.modelcontextprotocol/tasks fügt keine Tools hinzu.

Server installieren

Installieren Sie die exakte Version über einen verifizierten Kanal:

npm install --global @luckycat133/traecnclaw@0.6.0
# or, after `brew info` reports 0.6.0
brew install Luckycat133/tap/traecnclaw

Das passende GitHub-Release bietet auch das vollständige, gescopte npm-Tarball und das deterministische MCPB-Bundle. Das nicht verwandte, ungescopte Paket traecnclaw@0.3.1 ist historisch und kein aktueller Installationspfad.

Related MCP server: nuphus-mcp

Agent-Skill installieren

Installieren Sie aus dem öffentlichen GitHub-Repository mit der offenen Skills-CLI:

npx skills add https://github.com/Luckycat133/traecnclaw-mcp-skill \
  --skill traecnclaw-mcp \
  -g

Oder laden Sie das passende Skill-Archiv vom GitHub-Release herunter. Die Skill befindet sich unter .codex/skills/traecnclaw-mcp und enthält assets/mcp-client-config.json, scripts/setup-mcp.js und den Server-Launcher. Starten Sie den Agent-Host nach der Installation oder Aktualisierung der Skill neu.

Verwenden Sie scripts/setup-mcp.js, um die Server-Erkennung zu validieren und den Host-Eintrag zu generieren. Der normale Laufzeitbetrieb ist:

Agent host -> local stdio server -> gateway on the same Mac -> TraeCN

Der Server und das Gateway laufen auf demselben benutzereigenen Mac wie TraeCN. Marktplatz-Container können das stdio-Schema inspizieren, aber ein Cloud-Container kann den lokalen TraeCN-Desktop des Benutzers nicht transparent steuern.

Vorbereitete offizielle Registry-Metadaten verwenden das gescopte Paket @luckycat133/traecnclaw@0.6.0 mit lokalem stdio-Transport. Smithery Local verwendet das passende verifizierte MCPB-Bundle; das ausgemusterte smithery.yaml-Format bleibt abwesend.

Konfiguration

Die Gateway-Standardwerte sind TRAECN_GATEWAY_HOST=127.0.0.1 und TRAECN_GATEWAY_PORT=8788. Nicht-Loopback-Bindungen erfordern TRAECN_GATEWAY_TOKEN. Es gibt keine MCP-Tool-Profil-Einstellung.

Erkennungskanäle

Dasselbe öffentliche Repository ist die kanonische Quelle für Skill- und MCP-Verzeichniseinreichungen. Ein Verzeichniseintrag ist nur dann vertrauenswürdig, wenn seine Version, der lokale stdio-Transport, die macOS-Anforderung, die 20-Tool-Anzahl und der generierte Installationsbefehl mit diesem Release übereinstimmen.

Ausgewählte Kanäle umfassen ClawHub, Glama, skills.sh, AwesomeSkills.dev, MCP.Directory, MCPB/Smithery Local und – sobald ein aktuelles öffentliches Paket existiert – die offizielle MCP-Registry und PulseMCP. Andere Verzeichnisse sollten dieselbe Provenienz und Installationskopie wiederverwenden, anstatt Forks zu pflegen.

Glama

glama.json und das generierte Root-Dockerfile unterstützen die Verzeichnisregistrierung, die Verifizierung des Maintainers, Sicherheits-/Qualitätsscans und die Tool-Schema-Inspektion. Das Dockerfile installiert das aktuelle öffentliche Release und enthält niemals ein Gateway-Token oder eine Mock-Bridge.

TRAECNclaw sollte als lokaler stdio-Server aufgeführt werden. Beschreiben Sie einen von Glama gehosteten Container nicht als automatische Remote-Verbindung zum Mac des Benutzers.

Siehe SOURCE_REVISION und release-manifest.json für Provenienz und Kanalbereitschaft.

Available Tools

20 tools
traecn_answer_questionAnswer TraeCN QuestionA

Resolve an exceptional question from TraeCN that the gateway could not handle mechanically by supplying the user's decision. The gateway routes the answer to the pending visible prompt and reports the outcome. Only call when a pending interaction exists.

Inputs: answer (required). Returns: Interaction resolution outcome with optionally resumed tasks.

traecn_cancel_taskCancel TraeCN TaskA
Destructive

Cancel one gateway-tracked task by ID. The gateway stops shepherding the work at its next control point and records the cancellation; results already produced remain in task history. Returns the task identity and post-cancellation status.

Inputs: taskId (required). Returns: Cancelled task identity and any visible-generation stop outcome.

traecn_create_conversationCreate TraeCN ConversationA

Prepare a fresh TraeCN conversation for a genuinely new context. Returns a native conversation identity when TraeCN has allocated it; an empty draft returns conversationId=null and creationDeferred=true until its first message. Reuses an already-empty draft; otherwise creates another context. Call once per new context.

Inputs: no named parameters. Returns: Fresh conversation or empty draft awaiting a native identity.

traecn_decide_approvalDecide TraeCN ApprovalA
Destructive

Approve or deny the unsafe or ambiguous command card currently visible in TraeCN. Approval revalidates the exact expectedCommand against the card and requires acknowledgeRisk plus an audit reason recorded locally; denial needs only the decision. Never approve beyond the scope the user authorized.

Inputs: decision (required), reason, acknowledgeRisk, expectedCommand. Returns: Approval decision outcome with optionally resumed tasks.

traecn_delete_conversationDelete TraeCN ConversationA
Destructive

Permanently delete one inactive TraeCN conversation by stable identifier. Requires the exact expectedTitle returned by traecn_list_conversations plus an explicit irreversible-deletion acknowledgement; there is no gateway recovery path.

Inputs: expectedTitle (required), conversationId (required), acknowledgePermanentDeletion (required). Returns: Deletion outcome, or title/active-state mismatch details.

traecn_get_taskGet TraeCN TaskA
Read-onlyIdempotent

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.

Inputs: taskId (required), detailLevel. Returns: Task status snapshot with final result or diagnostics.

traecn_list_conversationsList TraeCN ConversationsA
Read-onlyIdempotent

List the conversations available in the current TraeCN mode with stable identifiers accepted by conversation-scoped tools. Read-only; call when choosing or verifying conversation context.

Inputs: no named parameters. Returns: Conversations for the current mode with stable identifiers.

traecn_list_modelsList TraeCN ModelsA
Read-onlyIdempotent

List the model names currently offered in the TraeCN UI and the current selection. If Auto hides manual models, report manualModelsHidden without changing modes. Call before select_model whenever the model choice matters.

Inputs: no named parameters. Returns: Current model plus available model names.

traecn_list_setting_optionsList TraeCN Setting OptionsA
Read-onlyIdempotent

List the visible choices of one dropdown-style setting identified by section and label. Required before select_setting_option; never invent an option value.

Inputs: label (required), section (required). Returns: Selectable choices for one dropdown setting.

traecn_list_settingsList TraeCN Section SettingsA
Read-onlyIdempotent

List the individual settings and their control types within one section returned by traecn_list_setting_sections. Read-only discovery preceding any setting mutation; never guess a label.

Inputs: section (required). Returns: Settings and control types within one section.

traecn_list_setting_sectionsList TraeCN Settings SectionsA
Read-onlyIdempotent

List the settings sections currently visible in TraeCN's settings UI. Required first step for any settings operation; never guess a section name.

Inputs: no named parameters. Returns: Visible settings section names.

traecn_open_workspaceOpen TraeCN WorkspaceA

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.

Inputs: path (required). Returns: Opened workspace identity with launch and verification details.

traecn_select_conversationSelect TraeCN ConversationA

Make one existing conversation the active target for subsequent visible interaction. Returns the confirmed active conversation identity.

Inputs: conversationId (required). Returns: Confirmed active conversation identity.

traecn_select_modeSelect TraeCN ModeA
Idempotent

Switch TraeCN between Solo and IDE mode and confirm the resulting active mode. Switching to the current mode succeeds as a no-op. Call only when the requested mode differs.

Inputs: mode (required). Returns: Active mode after the switch.

traecn_select_modelSelect TraeCN ModelA
Idempotent

Select one model by exact name from traecn_list_models and confirm the picker state before returning. Selecting the already-active model succeeds as a no-op. Does not wait for model availability or capacity.

Inputs: model (required). Returns: Applied selection with before/after models and queue readiness.

traecn_select_setting_optionSelect TraeCN Setting OptionA

Select one previously listed option for a dropdown setting identified by section and label, and confirm the applied selection. Only values returned by traecn_list_setting_options are valid.

Inputs: label (required), value (required), section (required). Returns: Applied dropdown selection and driver outcome.

traecn_send_messageSend TraeCN TaskA

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 follow-up messages to probe progress — track the returned task instead.

Inputs: message (required), conversationId. Returns: Accepted task identity, original terminal replay, or gateway rejection with rea…

traecn_set_setting_textSet TraeCN Setting TextA

Enter one text value into the setting field identified by section and label, and confirm what the field contains afterwards.

Inputs: text (required), label (required), section (required). Returns: Applied text value and driver outcome.

traecn_set_setting_toggleSet TraeCN Setting ToggleA
Idempotent

Enable or disable one toggle setting identified by section and label, then read back the applied state. Applying the already-current state succeeds as a no-op.

Inputs: label (required), enabled (required), section (required). Returns: Applied toggle value and driver outcome.

traecn_stop_generationStop Visible GenerationA
Destructive

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.

Inputs: reason (required), conversationId (required), acknowledgeUntrackedWork (required). Returns: Verified scoped stop outcome, or the active-conversation mismatch details.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 8 tool updatesv0.7.1-glama.1
    • Changedtraecn_create_conversation5 fields changed
      • changedOutput schema / description
        Previous value: -"Created conversation operation outcome."New value: +"Fresh conversation or empty draft awaiting a native identity."
      • changedOutput schema / properties / conversationId / description
        Previous value: -"Stable TraeCN conversation identifier."New value: +"Native identity when allocated; null for an empty draft."
      • changedOutput schema / properties / conversationId / type
        Previous value: -"string"New value: +[
        +  "string",
        +  "null"
        +]
      • addedOutput schema / properties / creationDeferred
        Added value: +{
        +  "description": "True when TraeCN will allocate the conversation identity on its first message.",
        +  "type": "boolean"
        +}
      • addedOutput schema / properties / fresh
        Added value: +{
        +  "description": "Whether the active context is ready for a first message.",
        +  "type": "boolean"
        +}
    • Changedtraecn_get_task5 fields changed
      • changedOutput schema / properties / completedAt / description
        Previous value: -"Epoch milliseconds when the task completed."New value: +"Task completion time: epoch milliseconds, an ISO 8601 timestamp from persisted history, or null when unavailable."
      • addedOutput schema / properties / completedAt / format
        Added value: +"date-time"
      • changedOutput schema / properties / completedAt / type
        Previous value: -[
        -  "number",
        -  "null"
        -]New value: +[
        +  "number",
        +  "string",
        +  "null"
        +]
      • changedOutput schema / properties / error / description
        Previous value: -"Error identifier or diagnostic when the operation failed."New value: +"Original task error, or null when no execution error was recorded."
      • changedOutput schema / properties / error / type
        Previous value: -"string"New value: +[
        +  "string",
        +  "null"
        +]
    • Changedtraecn_list_models1 field changed
      • addedOutput schema / properties / manualModelsHidden
        Added value: +{
        +  "description": "True when Auto mode hides manual models from the native picker.",
        +  "type": "boolean"
        +}
    • Changedtraecn_open_workspace4 fields changed
      • addedOutput schema / properties / verifiedWorkspace / additionalProperties
        Added value: +true
      • changedOutput schema / properties / verifiedWorkspace / description
        Previous value: -"Workspace path verified inside the TraeCN window."New value: +"Workspace identity detected in the TraeCN window, or a compatible gateway path string."
      • addedOutput schema / properties / verifiedWorkspace / properties
        Added value: +{
        +  "folderName": {
        +    "description": "Folder name detected in the TraeCN window.",
        +    "type": "string"
        +  },
        +  "rootPath": {
        +    "description": "Detected absolute workspace root, or null when unavailable.",
        +    "type": [
        +      "string",
        +      "null"
        +    ]
        +  }
        +}
      • changedOutput schema / properties / verifiedWorkspace / type
        Previous value: -"string"New value: +[
        +  "string",
        +  "object"
        +]
    • Changedtraecn_select_setting_option3 fields changed
      • addedOutput schema / properties / controlType
        Added value: +{
        +  "description": "UI control whose value was read back.",
        +  "enum": [
        +    "toggle",
        +    "option",
        +    "text"
        +  ],
        +  "type": "string"
        +}
      • addedOutput schema / properties / requestedValue
        Added value: +{
        +  "description": "Value requested by the caller."
        +}
      • addedOutput schema / properties / verified
        Added value: +{
        +  "description": "True only when the observed UI value equals the requested value.",
        +  "type": "boolean"
        +}
    • Changedtraecn_send_message7 fields changed
      • changedOutput schema / description
        Previous value: -"Accepted task identity, or the gateway rejection with reason."New value: +"Accepted task identity, original terminal replay, or gateway rejection with reason."
      • changedOutput schema / properties / error / description
        Previous value: -"Error identifier or diagnostic when the operation failed."New value: +"Original task error on replay, or submission rejection diagnostic."
      • changedOutput schema / properties / error / type
        Previous value: -"string"New value: +[
        +  "string",
        +  "null"
        +]
      • addedOutput schema / properties / result
        Added value: +{
        +  "description": "Original captured result on a terminal replay.",
        +  "type": [
        +    "object",
        +    "null"
        +  ]
        +}
      • changedOutput schema / properties / status / description
        Previous value: -"Acceptance status reported by the gateway."New value: +"Accepted for new work, or the original terminal status on an idempotent replay."
      • changedOutput schema / properties / status / enum
        Previous value: -[
        -  "accepted"
        -]New value: +[
        +  "accepted",
        +  "done",
        +  "error",
        +  "cancelled",
        +  "queue_timeout",
        +  "review_rejected"
        +]
      • addedOutput schema / properties / terminal
        Added value: +{
        +  "description": "True when returning the original terminal task without submitting again.",
        +  "type": "boolean"
        +}
    • Changedtraecn_set_setting_text3 fields changed
      • addedOutput schema / properties / controlType
        Added value: +{
        +  "description": "UI control whose value was read back.",
        +  "enum": [
        +    "toggle",
        +    "option",
        +    "text"
        +  ],
        +  "type": "string"
        +}
      • addedOutput schema / properties / requestedValue
        Added value: +{
        +  "description": "Value requested by the caller."
        +}
      • addedOutput schema / properties / verified
        Added value: +{
        +  "description": "True only when the observed UI value equals the requested value.",
        +  "type": "boolean"
        +}
    • Changedtraecn_set_setting_toggle3 fields changed
      • addedOutput schema / properties / controlType
        Added value: +{
        +  "description": "UI control whose value was read back.",
        +  "enum": [
        +    "toggle",
        +    "option",
        +    "text"
        +  ],
        +  "type": "string"
        +}
      • addedOutput schema / properties / requestedValue
        Added value: +{
        +  "description": "Value requested by the caller."
        +}
      • addedOutput schema / properties / verified
        Added value: +{
        +  "description": "True only when the observed UI value equals the requested value.",
        +  "type": "boolean"
        +}
  2. 20 tool updates
    • First observedtraecn_answer_question
    • First observedtraecn_cancel_task
    • First observedtraecn_create_conversation
    • First observedtraecn_decide_approval
    • First observedtraecn_delete_conversation
    • First observedtraecn_get_task
    • First observedtraecn_list_conversations
    • First observedtraecn_list_models
    • First observedtraecn_list_setting_options
    • First observedtraecn_list_setting_sections
    • First observedtraecn_list_settings
    • First observedtraecn_open_workspace
    • First observedtraecn_select_conversation
    • First observedtraecn_select_mode
    • First observedtraecn_select_model
    • First observedtraecn_select_setting_option
    • First observedtraecn_send_message
    • First observedtraecn_set_setting_text
    • First observedtraecn_set_setting_toggle
    • First observedtraecn_stop_generation

TDQS

A4.1/5.0

Scored across 20 tools

Disambiguation4/5

The tool set is largely cleanly partitioned: tasks, conversations, settings, models/modes, workspace, and interaction handling each have their own verbs. The only genuinely fuzzy pair is cancel_task vs stop_generation, but the description explicitly tells the agent to prefer cancel_task when a task ID exists, and the settings trio (toggle/option/text) is distinguished by control type. A few tools (list_settings vs list_setting_options vs list_setting_sections) are close cousins but the descriptions establish a clear required ordering.

Naming Consistency5/5

Every tool uses the uniform traecn_<verb>_<noun> snake_case pattern (list_, select_, set_, create_, delete_, get_, cancel_, stop_, send_, open_, answer_, decide_). Verbs are used semantically consistently: list_ for read-only discovery, select_ for choosing from a listed set, set_ for applying a value. No camelCase or style mixing anywhere.

Tool Count4/5

Twenty tools is on the heavy side, but the server spans several distinct sub-domains (task lifecycle, conversation lifecycle, settings discovery/mutation, model/mode selection, approvals, workspace), so most tools earn their place. It is borderline rather than bloated, and consolidation of the four settings tools would make it tighter.

Completeness4/5

Coverage is strong across most lifecycles: tasks (send/get/cancel), conversations (list/select/create/delete), settings (sections/list/options/set/select), models and mode, workspace opening, and interactive prompts (answer_question, decide_approval). Minor gaps remain — there is no list_tasks to enumerate tracked work, no conversation rename, and no workspace listing/current-workspace read — but agents can work around these using the returned taskId.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables automation of native Windows desktop applications through screen capture, mouse/keyboard control, and waiting for UI changes, exposing them as MCP tools.
    1
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to perform deterministic Windows desktop and browser automation through MCP, using pre-validated UI Automation and DOM locators for fast, stable execution of ERP and business workflows.
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables MCP clients to automate live browser sessions by having an LLM plan one outcome at a time while a hosted decision model picks elements, actions, values, and completion status. It exposes tools for navigation, direct actions, page reading/snapshots, checks/choices, screenshots, and calling WebMCP tools registered by pages.
    1,461 npm
    MIT