Bragproof

← Reports

jupyterlab-collab-mcp

Starts with no setup0.15.0npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 3 of 5 tools tried
Contacts while installing and starting: nothing

44tools listed
0hosts contacted
0files written
0.2 sto start
133dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y jupyterlab-collab-mcp@0.15.0

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

5 tools that take no input and look read-only were called once with nothing. 3 returned a result.

list_filesReturned a result under 0.1 s · 327 characters
list_notebooksNo usable answer tool reported an error: Error: Not connected to JupyterLab. Use connect_jupyter tool first with your JupyterLab URL.
list_kernelsNo usable answer tool reported an error: Error: Not connected to JupyterLab. Use connect_jupyter tool first with your JupyterLab URL.
list_runsReturned a result under 0.1 s · 119 characters
notebook_guideReturned a result under 0.1 s · 7,680 characters

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

1 tool with commands in capitals or very long text
  • Gives the agent orders in save_notebook: s/skipped/failed). Use this to guarantee edits reach disk — NEVER edit the .ipynb file directly to 'save' it, as a direct file write is reverted by jupyter-collabora

Common and usually harmless: it is how many makers stress how a tool should be used.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

connect_jupyter url
Connect to JupyterLab for real-time sync and kernel execution. Without connecting, tools still work by reading .ipynb files directly.
list_files path
List files and directories. Use to discover notebooks.
list_notebooks
List notebooks with running kernels. Use list_files for all .ipynb files regardless of kernel state.
list_kernels
List available kernel types (e.g., python3, ir) and running instances.
troubleshoot path
Diagnose why notebook edits may not be syncing or persisting. Reports connection/RTC health and, for a given notebook, sync state, browser peers, a forced-save result, and a disk-vs-room round-trip check that detects split-brain (wrong/second server). Use when edits don't show up in the browser or on disk.
39 more tools
save_notebook path
Force a verified save of the notebook's live collaboration room to disk and report whether it persisted (success/skipped/failed). Use this to guarantee edits reach disk — NEVER edit the .ipynb file directly to 'save' it, as a direct file write is reverted by jupyter-collaboration and loses in-room edits.
open_notebook path, kernel_name
Open a notebook and start a kernel. Safe to call if already open. Required before executing cells.
create_notebook path, kernel_name, open, cells
Create a new notebook. Optionally open it with a kernel.
get_notebook_content path, cell_type, include_outputs, output_format, start_index, end_index, indices, cell_ids, max_output_chars
Read cells from a notebook. Returns source only (no outputs) by default. Set include_outputs=true to see results.
get_notebook_outline path
Condensed notebook structure: markdown headers by level + code cell previews. Use to find cell indices.
search_notebook path, pattern, search_in, case_sensitive, max_results, context_lines
Grep through notebook cells (regex). Returns matching cells with context.
replace_in_notebook path, search, replace, cell_type, case_sensitive, regex, indices, dry_run
Search and replace across cells. Returns replacement count per cell.
rename_symbol path, cell_index, line, character, new_name
Scope-aware Python rename across all cells. Won't rename in strings/comments.
get_diagnostics path, cell_index, cell_id
Static code diagnostics (errors, warnings) without executing. Uses LSP or Python syntax checking.
get_hover_info path, cell_index, line, character
Documentation/type info for code at a position. Uses LSP or kernel introspection.
get_user_focus path
Which cell the user is editing (cursor position via awareness protocol). Returns null if no active user.
insert_cell path, index, cell_id, source, cell_type, execute, timeout, max_images, include_images, handoff_after_ms, client_name
Insert a cell. Set execute=true to run it immediately and return its output — a single-call, durable alternative to execute_code (code+output are saved in the notebook and visible to the human). Supports handoff_after_ms for long runs.
update_cell path, index, cell_id, source, cell_type, force, execute, timeout, max_images, include_images, show_diff, handoff_after_ms, client_name
Update a cell's source. Set execute=true to run it after updating.
batch_update_cells path, updates, client_name
Update multiple cells atomically. More efficient than repeated update_cell.
batch_insert_cells path, inserts, client_name
Insert multiple cells at once, applied in order. Each `index` is the literal position in the notebook as it stands at that step (after earlier inserts in this batch). For a contiguous block, pass increasing indices (e.g. 20, 21, 22) or anchor with `cell_id`. Omit index to append.
delete_cell path, index, cell_id, indices, cell_ids, start_index, end_index, force, client_name
Delete cells. Single: index or cell_id. Batch: indices[], cell_ids[], or start_index+end_index.
change_cell_type path, index, cell_id, new_type, force
Convert cell type (code <-> markdown) in place.
copy_cells source_path, dest_path, start_index, end_index, cell_ids, dest_index, dest_cell_id, delete_source, client_name
Copy or move cells between notebooks. Set delete_source=true to move.
execute_cell path, index, cell_id, end_index, cell_ids, timeout, max_images, include_images, handoff_after_ms
Execute notebook cells. Single cell: use index/cell_id. Range: add end_index. By IDs: use cell_ids[]. Skips non-code cells in range mode.
execute_code path, code, timeout, max_images, include_images, handoff_after_ms
Run throwaway code in the kernel without modifying the notebook — for quick probes whose output you don't need to keep. Output is NOT saved and only briefly retained. For anything worth keeping or showing a human, prefer insert_cell(execute=true): same single call, but code+output are saved in the notebook.
get_cell_run_output run_id, kernel_id, max_images, include_images
Fetch output for a run started by execute_cell/execute_code (typically one that handed off via handoff_after_ms). Works for runs still executing AND completed runs — also the right tool to call when a <channel source="jupyter"> notification fires.
list_runs kernel_id, limit
List recent kernel runs (from execute_cell/execute_code) and their states (queued/running/handed_off/completed/failed), most-recent-first. Use this to discover a run_id or check whether a handed-off run is still executing vs. finished vs. evicted, instead of blindly holding an id that may be gone.
clear_outputs path, index, cell_id, force
Clear execution outputs. Omit index to clear all cells.
get_cell_outputs path, index, end_index, indices, cell_ids, max_images, include_images
Read cell outputs without source code. Supports single cell, range, or non-contiguous selection.
filter_output path, execution_id, grep, tail, head, max_lines, max_images, include_images
Filter cached execution output with grep/head/tail. Use after execute_cell or execute_code — avoids re-executing.
cell_metadata path, index, end_index, indices, cell_ids, metadata
Get or set cell metadata. Omit 'metadata' to GET, provide to SET (merges, null deletes keys).
cell_tags path, action, index, end_index, indices, cell_ids, tags, match_all, include_preview
Add, remove, or find tags on cells. Common: 'hide-input', 'hide-output', 'parameters'.
notebook_metadata path, metadata
Get or set notebook-level metadata. Omit 'metadata' to GET, provide to SET.
kernel path, action
Kernel control: status, interrupt, or restart.
kernel_variables path, names, detail, filter, include_private, max_variables, max_items, max_name_length
List or inspect kernel variables. Without 'names': lists all. With 'names': deep inspect (columns, dtypes, shapes).
rename_notebook path, new_path
Rename a notebook file.
diff_notebooks path1, path2, include_outputs, summary_only, max_diffs
Compare two notebooks cell by cell. Returns unified diff.
get_cell_history path, cell_id, limit
Change history for a cell: who, when, old/new content. Session-scoped.
get_notebook_changes path, since_version, limit
Changes since a version number (polling pattern). Use since_version=0 for all.
recover_cell path, cell_id, index, client_name
Re-insert a deleted cell from change history. Session-scoped.
snapshot path, action, name, description
Notebook snapshots: save, restore, list, or diff against current.
cell_locks path, action, cell_ids, owner, ttl_minutes, force
Advisory cell locks: acquire, release, or list.
report_issue category, summary, tool_name, path, details
Report a tool bug, hang, or suggestion about this MCP server. Logs locally and returns a structured GitHub-issue draft (title + sectioned body) for ianhi/jupyterlab-collab-mcp. This project accepts fully agent-drafted issues.
notebook_guide topic
Best practices for working with notebooks via this server. Call this FIRST when starting notebook work (or when unsure which tool to use) — returns guidance on reading, editing, executing, collaborating, and troubleshooting. Optionally pass a topic to get just one section.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseBSD-3-Clause
Needsnode >=18.0.0
Sourcegithub.com/ianhi/jupyterlab-collab-mcp
Install scriptsleveldown declare them. This runner does not run them.
Tarballsha512-5/P9agGy0Y8c3KIrz1vcM7iURz2ywUkr+h5xXpeqhnjjrIufmdHfhORM14KIrJhm6aZVD6Ky5105bpbuT3te1g==

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/jupyterlab-collab-mcp.svg)](https://bragproof.smaverk.com/r/jupyterlab-collab-mcp)

New version out? Ask for a fresh report.