Skip to main content
Glama
debugmcp

MCP Debugger

by debugmcp
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

start_debugging

Launch a debug session for a script and return its initial state—paused, stopped, or running—so you can inspect breakpoints, exit codes, or pending execution.

Instructions

Start debugging a script. Answers with the session as it is after the program's first stop, its exit, or a readiness window: "paused" with a reason (a launch with breakpoints answers at the first one), "stopped" with the exit code, or "running" with pending:true when the program is still running — after ~5s when nothing is armed to stop it (no breakpoints, no entry stop, no caught-exception filter; the "uncaught" default does not count), after 30s when something is; the message says what was or was not reached. A later stop shows in list_debug_sessions as the state flips to "paused"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argsNo
sessionIdYes
scriptPathYesPath to the script to debug. Use absolute paths or paths relative to your current working directory
dryRunSpawnNo
dapLaunchArgsNo
breakOnExceptionsNoBreak when exceptions are thrown: "uncaught" pauses at uncaught exceptions at the crash site instead of terminating the session; "all" also pauses on caught/raised exceptions (language-dependent). Launch sessions default to "uncaught" (Ruby is the exception — rdbg has no uncaught-only filter, so it stays "none"); pass "none" to opt out and let crashing scripts run to termination
adapterLaunchConfigNoOptional adapter-specific launch configuration overrides

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.25.1
    • addedInput schema / properties / breakOnExceptions
      Added value: +{
+  "description": "Break when exceptions are thrown: \"uncaught\" pauses at uncaught exceptions at the crash site instead of terminating the session; \"all\" also pauses on caught/raised exceptions (language-dependent). Launch sessions default to \"uncaught\" (Ruby is the exception — rdbg has no uncaught-only filter, so it stays \"none\"); pass \"none\" to opt out and let crashing scripts run to termination",
+  "enum": [
+    "uncaught",
+    "all",
+    "none"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / dapLaunchArgs / properties / justMyCode / description
      Added value: +"Only debug user code (default true). JavaScript launch: true blackboxes node_modules via skipFiles and keeps js-debug's smart-stepper on, so a pause or step that lands in skipped code (Node internals, node_modules) is stepped through and may never land; false drops node_modules from skipFiles and turns the stepper off, so pauses and steps land inside dependencies"
    • addedInput schema / properties / dapLaunchArgs / properties / noDebug
      Added value: +{
+  "description": "DAP's launch-without-debugging flag (default false). Where the adapter honours it (js-debug, debugpy, Delve and CodeLLDB) no breakpoint binds, no exception filter arms, no entry stop lands and no breakpoint, exception or entry stop ever arrives (a pause may still land where the runtime allows one) — the response warns when breakpoints, an explicit breakOnExceptions or stopOnEntry are set alongside it, and while the launch runs the session reports debuggerDisabled and every later surface says the debugger is off. rdbg, netcoredbg and the Java bridge ignore the flag, and the rust launch never forwards it: their debugger stays on and the response says so",
+  "type": "boolean"
+}
    • addedInput schema / properties / dapLaunchArgs / properties / stopOnEntry / description
      Added value: +"Pause at the first line before running. Default false — the opposite of attach, which pauses unless stopOnEntry is false"
  2. First observed

TDQS

B3.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and largely delivers: it discloses the three terminal states of the first stop, the ~5s vs 30s readiness windows, the condition that selects each, and that debuggerDisabled can be set via nested launch args. It omits auth/permission needs and whether the session persists, but the return-state and timing disclosure is substantive context beyond any structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in sentence one, which is good, but the remainder is a single dense, em-dash-heavy paragraph that buries the 5s/30s distinction and the debuggerDisabled caveat mid-sentence. Every clause conveys real information, but the lack of structure hurts readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does describe return states and timing well, covering the main post-call expectation. But it leaves the multi-param surface (7 params, 2 required) unexplained and gives no routing relative to the many sibling session tools, so it is adequate but not complete for a launch tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 43% and the description adds no parameter meaning at all — args, sessionId, dryRunSpawn, and adapterLaunchConfig are undocumented in both places. All parameter detail lives in nested schema descriptions the top-level text never references, so it does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb+resource ("Start debugging a script"), so an agent knows the operation. However, it never distinguishes itself from close siblings like create_debug_session, restart_debugging, or attach_to_process, so the agent cannot confidently choose between them from the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the description explains what happens once launched (paused/stopped/running), which indirectly signals this is the launch entry point. It never states when to prefer this over create_debug_session or attach_to_process, nor any prerequisites, so guidance is inferential rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools