jupyter-mcp-server

Security Findings (47)

• CriticalAS-006

  💻Arbitrary Code Execution ×2

  heuristic signal

  tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)

  execute_codeinsert_execute_code_cell

  Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

• HighAS-003

  🔀Scope Mismatch

  read_notebook:tool name "read_notebook" implies read-only operation but declares exec permission

  Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.

• LowAS-011

  ℹ️Missing Rate-Limit / Timeout ×5

  tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

  clear_cell_outputconnect_to_jupyterread_notebookrestart_notebookuse_sandbox

  Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

• LowAS-002

  ⚠️Excessive Permissions

  launch_sandbox:input schema exposes 12 properties (threshold: 10)

  Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

• InfoAS-002

  ⚠️Excessive Permissions ×13

  declared capabilities: code/command execution

  clear_cell_outputexecute_cellexecute_codeinsert_execute_code_cellread_notebookuse_sandbox

  declared capabilities: network access, filesystem access, HTTP requests

  connect_to_jupyter

  declared capabilities: filesystem access

  delete_celllist_filesoverwrite_cell_sourceuse_notebook

  declared capabilities: code/command execution, network access, environment variables

  launch_sandbox

  declared capabilities: HTTP requests

  restart_notebook

  Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

• InfoAS-014

  ℹ️Dependency Inventory Unavailable ×22

  Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

  clear_cell_outputconnect_to_jupyterdelete_celledit_cell_sourceexecute_cellexecute_codeinsert_cellinsert_execute_code_celllaunch_sandboxlist_fileslist_kernelslist_notebookslist_sandboxesmove_celloverwrite_cell_sourceread_cellread_notebookrestart_notebookterminate_sandboxunuse_notebookuse_notebookuse_sandbox

  Fix: Review and remediate the identified issue.

• InfoAS-010

  🔑Insecure Secret Handling ×3

  input parameter "jupyter_token" accepts a credential (informational; not evidence of insecure handling)

  connect_to_jupyter

  input parameter "proxy_token" accepts a credential (informational; not evidence of insecure handling)

  launch_sandbox

  input parameter "token" accepts a credential (informational; not evidence of insecure handling)

  launch_sandbox

  Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.