TRAECNclaw MCP
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:
Öffnen Sie einen Arbeitsbereich nur bei Bedarf.
Wählen Sie Modell oder Modus nur bei Bedarf.
Senden Sie eine Nachricht und geben Sie den Aufruferkontext frei.
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/traecnclawDas 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 \
-gOder 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 -> TraeCNDer 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 toolstraecn_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 TaskADestructive
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 ApprovalADestructive
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 ConversationADestructive
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 TaskARead-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 ConversationsARead-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 ModelsARead-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 OptionsARead-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 SettingsARead-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 SectionsARead-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 ModeAIdempotent
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 ModelAIdempotent
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 ToggleAIdempotent
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 GenerationADestructive
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.
8 tool updates
v0.7.1-glama.1- Changed
traecn_create_conversation5 fields changed- changed
Output schema / descriptionPrevious value: -"Created conversation operation outcome."New value: +"Fresh conversation or empty draft awaiting a native identity." - changed
Output schema / properties / conversationId / descriptionPrevious value: -"Stable TraeCN conversation identifier."New value: +"Native identity when allocated; null for an empty draft." - changed
Output schema / properties / conversationId / typePrevious value: -"string"New value: +[ + "string", + "null" +] - added
Output schema / properties / creationDeferredAdded value: +{ + "description": "True when TraeCN will allocate the conversation identity on its first message.", + "type": "boolean" +} - added
Output schema / properties / freshAdded value: +{ + "description": "Whether the active context is ready for a first message.", + "type": "boolean" +}
- Changed
traecn_get_task5 fields changed- changed
Output schema / properties / completedAt / descriptionPrevious 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." - added
Output schema / properties / completedAt / formatAdded value: +"date-time" - changed
Output schema / properties / completedAt / typePrevious value: -[ - "number", - "null" -]New value: +[ + "number", + "string", + "null" +] - changed
Output schema / properties / error / descriptionPrevious value: -"Error identifier or diagnostic when the operation failed."New value: +"Original task error, or null when no execution error was recorded." - changed
Output schema / properties / error / typePrevious value: -"string"New value: +[ + "string", + "null" +]
- Changed
traecn_list_models1 field changed- added
Output schema / properties / manualModelsHiddenAdded value: +{ + "description": "True when Auto mode hides manual models from the native picker.", + "type": "boolean" +}
- Changed
traecn_open_workspace4 fields changed- added
Output schema / properties / verifiedWorkspace / additionalPropertiesAdded value: +true - changed
Output schema / properties / verifiedWorkspace / descriptionPrevious value: -"Workspace path verified inside the TraeCN window."New value: +"Workspace identity detected in the TraeCN window, or a compatible gateway path string." - added
Output schema / properties / verifiedWorkspace / propertiesAdded 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" + ] + } +} - changed
Output schema / properties / verifiedWorkspace / typePrevious value: -"string"New value: +[ + "string", + "object" +]
- Changed
traecn_select_setting_option3 fields changed- added
Output schema / properties / controlTypeAdded value: +{ + "description": "UI control whose value was read back.", + "enum": [ + "toggle", + "option", + "text" + ], + "type": "string" +} - added
Output schema / properties / requestedValueAdded value: +{ + "description": "Value requested by the caller." +} - added
Output schema / properties / verifiedAdded value: +{ + "description": "True only when the observed UI value equals the requested value.", + "type": "boolean" +}
- Changed
traecn_send_message7 fields changed- changed
Output schema / descriptionPrevious value: -"Accepted task identity, or the gateway rejection with reason."New value: +"Accepted task identity, original terminal replay, or gateway rejection with reason." - changed
Output schema / properties / error / descriptionPrevious value: -"Error identifier or diagnostic when the operation failed."New value: +"Original task error on replay, or submission rejection diagnostic." - changed
Output schema / properties / error / typePrevious value: -"string"New value: +[ + "string", + "null" +] - added
Output schema / properties / resultAdded value: +{ + "description": "Original captured result on a terminal replay.", + "type": [ + "object", + "null" + ] +} - changed
Output schema / properties / status / descriptionPrevious value: -"Acceptance status reported by the gateway."New value: +"Accepted for new work, or the original terminal status on an idempotent replay." - changed
Output schema / properties / status / enumPrevious value: -[ - "accepted" -]New value: +[ + "accepted", + "done", + "error", + "cancelled", + "queue_timeout", + "review_rejected" +] - added
Output schema / properties / terminalAdded value: +{ + "description": "True when returning the original terminal task without submitting again.", + "type": "boolean" +}
- Changed
traecn_set_setting_text3 fields changed- added
Output schema / properties / controlTypeAdded value: +{ + "description": "UI control whose value was read back.", + "enum": [ + "toggle", + "option", + "text" + ], + "type": "string" +} - added
Output schema / properties / requestedValueAdded value: +{ + "description": "Value requested by the caller." +} - added
Output schema / properties / verifiedAdded value: +{ + "description": "True only when the observed UI value equals the requested value.", + "type": "boolean" +}
- Changed
traecn_set_setting_toggle3 fields changed- added
Output schema / properties / controlTypeAdded value: +{ + "description": "UI control whose value was read back.", + "enum": [ + "toggle", + "option", + "text" + ], + "type": "string" +} - added
Output schema / properties / requestedValueAdded value: +{ + "description": "Value requested by the caller." +} - added
Output schema / properties / verifiedAdded value: +{ + "description": "True only when the observed UI value equals the requested value.", + "type": "boolean" +}
20 tool updates
- First observed
traecn_answer_question - First observed
traecn_cancel_task - First observed
traecn_create_conversation - First observed
traecn_decide_approval - First observed
traecn_delete_conversation - First observed
traecn_get_task - First observed
traecn_list_conversations - First observed
traecn_list_models - First observed
traecn_list_setting_options - First observed
traecn_list_setting_sections - First observed
traecn_list_settings - First observed
traecn_open_workspace - First observed
traecn_select_conversation - First observed
traecn_select_mode - First observed
traecn_select_model - First observed
traecn_select_setting_option - First observed
traecn_send_message - First observed
traecn_set_setting_text - First observed
traecn_set_setting_toggle - First observed
traecn_stop_generation
TDQS
Scored across 20 tools
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.
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.
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.
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
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Hosted remote MCP for protected account access, permissions, activity history and supported undo.
Headless task management for bots, apps and AI agents. Remote MCP server, OAuth or access token.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables automation of native Windows desktop applications through screen capture, mouse/keyboard control, and waiting for UI changes, exposing them as MCP tools.1-
- AlicenseNot gradedqualityDmaintenanceProvides desktop automation capabilities (e.g., click, browser snapshot) as MCP tools for DSH agents, enabling computer use via natural language.215 npm5MIT
- AlicenseNot gradedqualityBmaintenanceEnables 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.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables 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 npmMIT