{"report":"{\"v\":1,\"package\":\"nebula-notebook-mcp\",\"version\":\"0.4.105\",\"ranAt\":\"2026-11-16T11:40:49.972Z\",\"install\":{\"ok\":true,\"bin\":\"nebula-notebook-mcp\",\"integrity\":\"sha512-pARUsbK9LXnTrCuj/pym6ynpOj2dtVRiqtpJ+JA7Vy04LWxIzn8JcrYXft5sBHETi3WTvnIxTIPUbRYkRGvRMQ==\",\"deps\":140,\"scripts\":[\"sharp\"],\"bins\":[\"nebula-notebook-mcp\",\"nebula\"],\"license\":\"MIT\",\"engines\":\"node >=20\",\"repository\":\"https://github.com/jzhoulab/nebula-notebook.git\"},\"start\":{\"ok\":true,\"ms\":42,\"serverName\":\"nebula-notebook-mcp\",\"serverVersion\":\"0.1.0\",\"protocol\":\"2025-06-18\",\"stderr\":\"[Nebula MCP] Agent ID: 6e85d743\\n============================================================\\nNebula MCP Server Started\\nNo server connected yet.\\nCall connect_server(base_url=...) before using any other tool.\\nProtocol: Model Context Protocol (MCP) 2024-11-05 (supports 2025-06-18, 2024-11-05)\\n============================================================\\n[Nebula MCP] Initialize params: {\\n  \\\"protocolVersion\\\": \\\"2025-06-18\\\",\\n  \\\"capabilities\\\": {},\\n  \\\"clientInfo\\\": {\\n    \\\"name\\\": \\\"bragproof\\\",\\n    \\\"version\\\": \\\"0.1.0\\\"\\n  }\\n}\\n[Nebula MCP] Client identified: bragproof v0.1.0\\n[Nebula MCP] Executing tool: list_kernels\\n[Nebula MCP] Executing tool: list_directory\\n[Nebula MCP] Executing tool: compute_status\\n[Nebula MCP] Executing tool: list_compute_queues\\n[Nebula MCP] Executing tool: list_allocations\\n\"},\"tools\":[{\"name\":\"read_notebook\",\"description\":\"Read all cells from a notebook. Formats: \\\"content\\\" (full code, no outputs), \\\"detailed\\\" (full code + inline images, default), \\\"placeholder\\\" (full code + text placeholders for images, recommended for Gemini). Outputs are truncated (100 lines regular, 200 lines errors). MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"format\",\"include_outputs\",\"max_lines\",\"max_chars\",\"max_lines_error\",\"max_chars_error\"]},{\"name\":\"read_cell\",\"description\":\"Read a specific cell content and metadata (not outputs). Use read_output to get outputs. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_index\",\"cell_id\"]},{\"name\":\"read_output\",\"description\":\"Read cell outputs. By default waits for completion or max_wait timeout (returns once). Set wait_for_completion=false to return as soon as new output appears. Regular outputs truncated to 100 lines, errors get 200 lines. Use save_to_file=true for complete output. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_index\",\"cell_id\",\"output_offset\",\"max_wait\",\"wait_for_completion\",\"max_lines\",\"max_chars\",\"max_lines_error\",\"max_chars_error\",\"line_offset\",\"save_to_file\"]},{\"name\":\"insert_cell\",\"description\":\"Insert a new cell into the notebook. Use position=-1 or omit to append at end. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_id\",\"content\",\"cell_type\",\"position\"]},{\"name\":\"update_cell\",\"description\":\"Update an existing cell by its stable ID. Can update content and/or type. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_id\",\"content\",\"cell_type\"]},{\"name\":\"delete_cell\",\"description\":\"Delete a cell from a notebook MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_index\",\"cell_id\"]},{\"name\":\"clear_notebook\",\"description\":\"Clear all cells from a notebook. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\"]},{\"name\":\"create_notebook\",\"description\":\"Create a new empty notebook. If the notebook is open in the browser UI, it will attempt to open the new notebook in a new tab. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"overwrite\",\"kernel_name\",\"kernel_display_name\"]},{\"name\":\"move_cell\",\"description\":\"Move a cell from one position to another. Supports two modes: by index (from_index, to_index) or by ID (cell_id with after_cell_id or to_index=-1 for start). MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"from_index\",\"to_index\",\"cell_id\",\"after_cell_id\"]},{\"name\":\"duplicate_cell\",\"description\":\"Duplicate a cell, inserting the copy immediately after the original MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_index\"]},{\"name\":\"search_cells\",\"description\":\"Search notebook cells by keyword. Can search in cell source code and optionally in outputs. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"query\",\"include_outputs\",\"limit\"]},{\"name\":\"update_metadata\",\"description\":\"Update cell metadata (id, type, scrolled, scrolledHeight). Validates against schema. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_id\",\"changes\"]},{\"name\":\"connect_server\",\"description\":\"Connect to a Nebula server. REQUIRED: call this once at the start of every MCP session before any other tool call. base_url is required; the server does not assume a default. All subsequent operations will use this connection.\\n\\nRECOMMENDED WORKFLOW:\\n1. connect_server (required at session start)\\n2. For each response: start_agent_session → operations → end_agent_session\\n\\nstart_agent_session is required for notebook mutations; read-only operations do not require it.\",\"params\":[\"base_url\"]},{\"name\":\"start_agent_session\",\"description\":\"Start an agent session for notebook write operations. Always call end_agent_session when done.\\n\\nSessions are COLLABORATIVE by default: the user can keep editing while you work. Your destructive writes (update_cell, delete_cell, …) are protected by per-cell optimistic concurrency — if the user changed a cell after you last read it, the write is rejected with the current content so you can re-apply your intent. Address cells by id (indices shift when the user edits), and re-read cells you haven't read recently.\\n\\nPass exclusive=true only for large multi-cell refactors that need atomicity: it locks the UI read-only for the duration (the legacy behavior). Prefer collaborative sessions otherwise.\\n\\nSee connect_server for required MCP workflow.\\n\\nThis call validates that the notebook path exists; it will error if the path is wrong or missing.\\n\\nIMPORTANT: Call this at the START of each response before any notebook operations, and call end_agent_session at the END of each response. This ensures the notebook is only locked while you're actively working on it.\\n\\nExample flow for each response:\\n  start_agent_session → insert_cell/update_cell/execute_cell/etc → end_agent_session\\n\\nFORCE OPTION (use only with explicit user permission):\\nIf a previous agent session was not properly ended (e.g., due to a crash or timeout), the notebook may remain locked. Use force=true ONLY when the user explicitly asks you to \\\"force\\\" or \\\"steal\\\" the lock. This will forcibly end any existing session and start a new one. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"agent_id\",\"force\",\"last_session_timestamp\",\"exclusive\"]},{\"name\":\"end_agent_session\",\"description\":\"End an agent session, unlocking the notebook for user edits. Always call this at the END of each response after completing all notebook operations.\\n\\nIMPORTANT: Always call this before finishing your response, even if operations failed. This ensures the notebook is unlocked for the user. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\"]},{\"name\":\"delete_cells\",\"description\":\"Delete multiple cells by ID in a single operation. More efficient than multiple single deletes. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_ids\"]},{\"name\":\"insert_cells\",\"description\":\"Insert multiple cells at a position in a single operation. More efficient than multiple single inserts. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cells\",\"position\"]},{\"name\":\"clear_outputs\",\"description\":\"Clear outputs from cells without re-executing. If no cell_ids provided, clears all cell outputs. Useful for cleanup before sharing notebooks. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_ids\"]},{\"name\":\"list_kernels\",\"description\":\"List available kernel specifications with display names (includes version info) MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"kernel_start\",\"description\":\"Start a new kernel session for the active notebook (requires start_agent_session) MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"kernel_name\"]},{\"name\":\"kernel_stop\",\"description\":\"Stop and shutdown the active notebook kernel (requires start_agent_session) MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"kernel_restart\",\"description\":\"Restart the active notebook kernel (clears all variables, requires start_agent_session) MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"kernel_interrupt\",\"description\":\"Interrupt execution in the active notebook kernel (requires start_agent_session) MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"execute_cell\",\"description\":\"Execute a notebook cell and return its output. Outputs are truncated by default (100 lines, 10000 chars). Outputs are saved incrementally during execution. Requires an active kernel session.\\n\\nFor long-running cells: If execution exceeds max_wait, returns with status=\\\"busy\\\" and partial output. Use read_output with max_wait to poll for more output. Set max_wait=0 for immediate \\\"background\\\" execution (returns right away, poll with read_output). MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"cell_index\",\"cell_id\",\"session_id\",\"max_wait\",\"save_outputs\",\"max_lines\",\"max_chars\"]},{\"name\":\"read_file\",\"description\":\"Read the contents of a text file from the server. Returns file content as string. For .ipynb notebooks, returns JSON string; .py/.qmd notebooks are plain text. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\"]},{\"name\":\"write_file\",\"description\":\"Write content to a file on the server. Creates the file and parent directories if they do not exist. Overwrites existing file. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\",\"content\"]},{\"name\":\"list_directory\",\"description\":\"List contents of a directory on the server. Returns file and directory names with types. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\"]},{\"name\":\"delete_file\",\"description\":\"Delete a file or directory from the server. Directories are deleted recursively. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"path\"]},{\"name\":\"rename_file\",\"description\":\"Rename or move a file or directory on the server. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"old_path\",\"new_path\"]},{\"name\":\"download_file\",\"description\":\"Download a file from the server to a local path. Supports both text and binary files. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"server_path\",\"local_path\"]},{\"name\":\"upload_file\",\"description\":\"Upload a local file to the server. Supports both text and binary files. Fails if the destination file already exists unless on_conflict says otherwise. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"local_path\",\"server_path\",\"on_conflict\"]},{\"name\":\"compute_status\",\"description\":\"Check whether scheduler-backed cluster compute (allocations) is available on this Nebula server. Returns enabled + scheduler name. Call this before any other compute tool — the feature is absent on servers without a scheduler (e.g. laptops). MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"list_compute_queues\",\"description\":\"List cluster partitions and QoS with live load: idle/total CPUs, idle GPUs by type, queue backlog (pending/running jobs), and which partitions/QoS the user may submit to. Use it to pick a partition before request_allocation. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"request_allocation\",\"description\":\"Request a compute allocation from the cluster scheduler. Allocations consume REAL cluster resources — only request one when the user's task actually needs it, request modest sizes, and cancel_allocation when done. Set wait_for_active=true to block until the allocation is usable (state=active), then bind a notebook with use_allocation. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"partition\",\"qos\",\"cpus\",\"mem_gb\",\"gpus\",\"gpu_type\",\"walltime_minutes\",\"name\",\"idle_timeout_minutes\",\"wait_for_active\",\"max_wait\"]},{\"name\":\"list_allocations\",\"description\":\"List compute allocations on the server with state (pending/running/active/ended/failed/cancelled), resources, and the serverId/node once active. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[]},{\"name\":\"cancel_allocation\",\"description\":\"Cancel a compute allocation and free its cluster nodes. Cancel allocations you created once the task completes; never cancel allocations you did not create. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"allocation_id\"]},{\"name\":\"use_allocation\",\"description\":\"Bind a notebook's kernels to an active compute allocation: starts (or reuses) the notebook's kernel on the allocation's server and saves it as the notebook's kernel preference. After this, execute_cell on that notebook runs on the allocation. Requires the allocation to be state=active. MCP: call connect_server first (see connect_server for workflow).\",\"params\":[\"allocation_id\",\"path\",\"kernel_name\"]}],\"toolsHash\":\"50078b0b82e5b56b858c1c79f03c0365fe18ebd6bf68aa314f5ab0ac52e81cab\",\"wrote\":[],\"callsAt\":\"2026-11-16T11:41:02.808Z\",\"calls\":[{\"tool\":\"list_kernels\",\"ok\":false,\"ms\":1,\"bytes\":0,\"error\":\"tool reported an error: Error: connect_server(base_url=...) must be called once at the start of every MCP session before any other tool call.\"},{\"tool\":\"list_directory\",\"ok\":false,\"ms\":1,\"bytes\":0,\"error\":\"tool reported an error: Error: connect_server(base_url=...) must be called once at the start of every MCP session before any other tool call.\"},{\"tool\":\"compute_status\",\"ok\":false,\"ms\":0,\"bytes\":0,\"error\":\"tool reported an error: Error: connect_server(base_url=...) must be called once at the start of every MCP session before any other tool call.\"},{\"tool\":\"list_compute_queues\",\"ok\":false,\"ms\":0,\"bytes\":0,\"error\":\"tool reported an error: Error: connect_server(base_url=...) must be called once at the start of every MCP session before any other tool call.\"},{\"tool\":\"list_allocations\",\"ok\":false,\"ms\":1,\"bytes\":0,\"error\":\"tool reported an error: Error: connect_server(base_url=...) must be called once at the start of every MCP session before any other tool call.\"}],\"host\":{\"commit\":\"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c\",\"run\":\"https://github.com/itsHaddad/bragproof/actions/runs/43857070216\"},\"network\":{\"names\":[\"registry.npmjs.org\"],\"conns\":[],\"callNames\":[],\"callConns\":[]}}","token":"eyJhbGciOiJSUzI1NiIsImtpZCI6IjM4ODI2YjE3LTZhMzAtNWY5Yi1iMTY5LThiZWI4MjAyZjcyMyIsInR5cCI6IkpXVCIsIng1dCI6InlrTmFZNHFNX3RhNGsyVGdaT0NFWUxrY1lsQSJ9.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.igalUAl3j-L6ZFSF_j7V7iMmWo1XdGTavxVYn5MNba8KNfbGRI676V1MGI08-YEJWKjoivUzepojYVBzl8WZDAs92X5epkZ-zDygh2haE6VpKoaz7692vnLSqelviyCr9AnYp95nW3aXAor-k96z7SuLx-U1kLFtbRK2bCeHPm2NwHjW_rDjZh9fEv0x1qtOPcUaWkk6CB7SVCj0N4e0pr0t0juC0kM7QAS44MLXuK_dHeJbxsCBWW3cZOgXH3p8OqbVI5mTKVAE5xU71jwiaX0XmS6Lu_33-wkwFeTmG4IXlvCOB7ahVyz4W5gJ-FI6J2PETlAeZAM-CUHLZPJYug"}