Skip to main content
Glama

debugger_start

Start a debugging session with auto-detection or specified debugger type to control program execution, examine memory, and analyze stack in GDB.

Instructions

Start a debugging session with auto-detection or specified debugger type.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
debugger_type_paramNo
debugger_pathNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • server.py:42-56 (handler)
    Main MCP tool handler for debugger_start. Registered with @mcp.tool() decorator, validates debugger availability, sets default path, and delegates to debugger_tools.start_session()
    @mcp.tool()
    def debugger_status() -> str:
        """Get status of available debuggers."""
        return DebuggerFactory.list_debuggers()
    
    @mcp.tool()
    def debugger_start(debugger_type_param: str = None, debugger_path: str = None) -> str:
        """Start a debugging session with auto-detection or specified debugger type."""
        if not debugger_tools:
            return "Error: No debuggers are available on this system"
        
        if debugger_path is None:
            debugger_path = "gdb"  # Default to gdb
        
        return debugger_tools.start_session(debugger_path)
  • GDB-specific implementation of start_session. Creates a GDB session via the session manager and returns session ID
    @handle_gdb_errors("starting GDB session")
    def start_session(self, gdb_path: str = "gdb") -> str:
        session_id = self.sessionManager.create_session(gdb_path)
        return f"GDB session started successfully. Session ID: {session_id}"
  • LLDB-specific implementation of start_session. Creates an LLDB session via the session manager and returns session ID
    @handle_lldb_errors("starting LLDB session")
    def start_session(self, debugger_path: Optional[str] = None) -> str:
        session_id = self.session_manager.create_session(debugger_path)
        return f"LLDB session started successfully. Session ID: {session_id}"
  • Abstract interface definition for start_session method that all debugger implementations must provide
    @abstractmethod
    def start_session(self, debugger_path: str = None) -> str:
        """Start a new debugging session."""
        pass
  • Low-level GDB session creation using GdbController with MI3 interpreter, generates UUID session ID
    def create_session(self, gdb_path: str = "gdb") -> str:
        session_id = str(uuid.uuid4())
        try:
            gdb_controller = GdbController(command=[gdb_path, "--interpreter=mi3"])
            self.sessions[session_id] = gdb_controller
            logger.info(f"Started GDB session: {session_id}")
            return session_id
        except Exception as e:
            logger.error(f"Failed to start GDB session: {e}")
            raise
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Start a debugging session' implies an initialization action, the description doesn't disclose what happens during startup, whether this creates persistent sessions, what permissions are needed, or what the expected outcomes are. The mention of 'auto-detection' hints at some intelligence but doesn't explain how it works or what happens when detection fails.

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

Conciseness4/5

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

The description is appropriately concise at just one sentence. It's front-loaded with the main action ('Start a debugging session') followed by the key capability ('with auto-detection or specified debugger type'). There's no wasted words, though it could benefit from slightly more detail given the complexity of the tool.

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?

Given that there's an output schema (which handles return values) and no annotations, the description is minimally complete for a tool with 2 parameters. However, for a debugging tool that likely has complex behavior and multiple sibling alternatives, the description should provide more context about when to use it, what debuggers it supports, and how it differs from gdb_start/lldb_start. The existence of an output schema helps but doesn't compensate for the lack of usage guidance.

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?

With 0% schema description coverage for both parameters, the description must compensate but fails to do so adequately. It mentions 'specified debugger type' which loosely relates to 'debugger_type_param' but doesn't explain what debugger types are supported or how to specify them. It doesn't mention 'debugger_path' at all. The description adds minimal value beyond what's implied by parameter names.

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

Purpose3/5

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

The description states the tool's purpose as 'Start a debugging session' which is clear but vague. It mentions 'auto-detection or specified debugger type' which adds some specificity, but doesn't distinguish it from sibling tools like gdb_start or lldb_start that also start debugging sessions. The description doesn't clarify what makes this debugger_start tool different from those specific debugger starters.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. With multiple debugger-related tools available (debugger_start, gdb_start, lldb_start), there's no indication of when this general debugger_start should be used instead of the specific debugger starters. No prerequisites, context requirements, or exclusions are mentioned.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smadi0x86/MDB-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server