Skip to main content
Glama
Sign In
gdbstub-mcp

gdbstub-mcp

by 0xmortuex
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

debug_symbol

Resolve addresses, symbols, and source lines from an ELF without touching the target. Query an address for symbol+offset and line, a symbol for address/size/line, or file.c:42 for its address.

Instructions

Look up symbols without touching the target.

query: an address (0x100abc) -> symbol+offset and source line; a symbol or symbol+off -> its address, size and source line; or file.c:42 -> address. Uses the session's ELF (name=) or a standalone ELF path (elf=).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "debug_symbol"
  }
}

Input Schema

NameRequiredDescriptionDefault
elfNo
nameNo
queryYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does address the highest-risk trait for a debugger tool: it is non-invasive and does not touch the target process. It also discloses how the ELF context is resolved (session ELF via name= or standalone path via elf=). It is silent on failure behavior when a symbol is not found or when neither name nor elf is supplied.

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?

Front-loaded purpose sentence followed by query-form mapping and ELF resolution source; no wasted wording. The arrow notation is dense but consistently applied, though it reads more telegraphic than natural prose.

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

Completeness4/5

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

For a three-parameter read-only lookup with an output schema present, the description covers inputs, resolution sources, and expected returns per query form. The remaining gap is what happens when both name and elf are omitted (both default to null) and how lookup failures surface.

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

Parameters5/5

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

Schema description coverage is 0%, yet the description documents all three parameters: query with three concrete input forms (address, symbol/symbol+off, file.c:42) and the result each yields, plus name= for the session ELF and elf= for a standalone ELF path. This fully compensates for the empty schema documentation.

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

Purpose5/5

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

States a specific verb+resource ("Look up symbols") and immediately scopes it with "without touching the target," which separates it from invasive siblings like debug_memory or debug_write_memory. The three query forms spell out exactly what kind of lookup is performed.

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

Usage Guidelines4/5

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

"Without touching the target" gives clear usage context: this is safe to call during a live session without mutating debuggee state. It does not explicitly name alternatives (e.g., debug_disassemble for instruction-level work) or state when not to use it, so it falls short of a full routing rule.

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