Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.ai-debugger-inc/aidb

PYPI · AI-DEBUGGER-INC · SCANNED SEP 13

Debug any supported language with breakpoints, variable/state inspection, and stepping.

Available components

0 this week 73 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 31 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency6
Schema Quality & AI Usability68
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2294 tokens (~191/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.ai-debugger-inc/aidb MCP server?

io.github.ai-debugger-inc/aidb runs locally as a PyPI package, launched with uvx ai-debugger-inc. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · ai-debugger-inc

# add to Claude Code
claude mcp add ai-debugger-inc-aidb -- uvx ai-debugger-inc
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-debugger-inc-aidb": {
      "command": "uvx",
      "args": [
        "ai-debugger-inc"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-debugger-inc-aidb": {
      "command": "uvx",
      "args": [
        "ai-debugger-inc"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ai-debugger-inc-aidb -- uvx ai-debugger-inc
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-debugger-inc-aidb": {
      "type": "local",
      "command": [
        "uvx",
        "ai-debugger-inc"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-debugger-inc-aidb --command uvx --arg ai-debugger-inc
# ~/.hermes/config.yaml
mcp_servers:
  ai-debugger-inc-aidb:
    command: "uvx"
    args: ["ai-debugger-inc"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-debugger-inc-aidb": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "ai-debugger-inc"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ai-debugger-inc-aidb -t stdio -c uvx -a ai-debugger-inc
// mcp.json
{
  "mcpServers": {
    "ai-debugger-inc-aidb": {
      "command": "uvx",
      "args": [
        "ai-debugger-inc"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 12 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 11 Sept 26 0
    • Stability: 0.97 → pass security
  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 4 Sept 26 0
    • Stability: 0.97 → pass security
  • 3 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 13 Sept 2026 · Analysed pypi/ai-debugger-inc@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 31 packages
Packages resolved 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 12 exposed · ~2,294 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
adapter ~199

Consolidated adapter management with action-based operations **Actions:** • `download`: Download and install a specific language adapter (requires language) • `download_all`: Download and install all available adapters (language ignored) • `list`: List installed adapters and status (language optional) **Management:** Downloads debug adapters from GitHub releases to ~/.aidb/adapters/. Versions match current project. Validates language support dynamically. **Aliases:** install→download, install_all→download_all, status/show→list **Usage:** Install missing adapters when encountering AdapterNotFoundError messages.

NameTypeReqDescription
actionstringAdapter management action
forcebooleanForce re-download if already installed (download/download_all actions). Use when adapters need updating or are corrupted
languagestringProgramming language (java, javascript, python)
versionstringSpecific version to download (download action only). Defaults to latest version matching current project

No output schema declared.

No examples provided.

breakpoint ~276

Manage breakpoints. Supports conditions (condition='x>5'), hit counts (hit_condition='>3' to skip first 3 hits), and logpoints (log_message='val={x}'). Actions: - 'set': Set a breakpoint (default) - 'remove': Remove a breakpoint - 'list': List all breakpoints - 'clear_all': Remove all breakpoints - 'watch': Set watchpoint (Java only) - 'unwatch': Remove watchpoint (Java only)

NameTypeReqDescription
access_typestringAccess type for watch action: 'read', 'write', or 'readWrite'
actionstringBreakpoint action
columnintegerColumn number for precise breakpoint placement (for minified code)
conditionstringConditional expression (e.g., 'x > 10')
hit_conditionstringHit count condition (e.g., '> 5' to break after 5 hits)
locationstringBreakpoint location (``file:line`` or ``file:line:column``)
log_messagestringLog message instead of pausing (logpoint)
namestringVariable name for watch action (e.g., 'user.email')
session_idstringOptional session ID

No output schema declared.

No examples provided.

config ~200

Configuration and environment management. **Actions:** • `show`: Show current configuration (default) • `env`: Show/set environment variables • `launch`: Discover and manage VS Code launch.json configurations • `capabilities`: Show debugging capabilities for languages (replaces aidb.capabilities) • `adapters`: Check debug adapter installation status **Examples:** • config('env') - Show AIDB_* environment variables • config('launch') - List available launch configurations • config('adapters') - Show installed debug adapters • config('capabilities', language='python') - Python debugging features

NameTypeReqDescription
actionstringConfiguration action
config_namestringLaunch configuration name (for launch action)
keystringEnvironment variable key (for env action)
languagestringProgramming language (java, javascript, python)
valuestringEnvironment variable value (for env action)

No output schema declared.

No examples provided.

context ~88

Rich debugging context and intelligent next-step suggestions. Provides: - Current debugging state and session memory - Recent operations and their outcomes - Intelligent next-step recommendations - Cross-tool workflow suggestions - Debugging history and patterns

NameTypeReqDescription
detail_levelstringLevel of context detail
include_suggestionsbooleanInclude next-step suggestions
session_idstringOptional session ID

No output schema declared.

No examples provided.

execute ~156

Execute the program with different actions and capabilities. Actions: - 'run': Start execution from beginning - 'continue': Continue from current position (default) Enhanced features: - Smart execution until specific conditions - Output collection and analysis - Automatic breakpoint management

NameTypeReqDescription
actionstringExecution action
collect_outputbooleanCollect program output
jump_targetstringJump to this location (``file:line``) - for jump action
session_idstringOptional session ID
untilstringExecute until this location (``file:line``)
wait_for_stopbooleanWait for breakpoint/stop event. Auto-enabled when breakpoints exist (default: auto)

No output schema declared.

No examples provided.

init ~259

🚀 **REQUIRED FIRST STEP** - Initialize debugging context and get language-specific examples. This is the mandatory entry point for debugging. You MUST call this before any other debugging operation. It provides: - Language-specific examples (Python, JavaScript, TypeScript, Java) - Framework-aware patterns (pytest, jest, django, spring, etc.) - Workspace-aware configuration discovery - Clear usage examples with exact syntax

NameTypeReqDescription
frameworkstringOptional framework (pytest, jest, django, spring, etc.)
languagestringyesProgramming language (java, javascript, python)
launch_config_namestringName of VS Code launch configuration to reference
modestringDebug mode: 'launch' (start new process), 'attach' (attach to PID), 'remote_attach' (attach to host:port). Default: launch
verbosebooleanInclude educational content (key concepts, examples). Default: false for concise responses
workspace_rootstringRoot directory of the workspace for discovering launch.json and project context
workspace_rootsarrayMultiple workspace roots for multi-root workspaces (e.g., microservices). Use this instead of workspace_root when debugging across multiple projects.

No output schema declared.

No examples provided.

inspect ~121

Inspect program state during debugging. Available modes: - 'locals': Local variables (default) - 'globals': Global variables - 'stack': Call stack with frames - 'threads': All thread states - 'expression': Evaluate specific expression - 'all': Complete state snapshot

NameTypeReqDescription
detailedbooleanInclude detailed information
expressionstringExpression to evaluate
frameintegerStack frame to inspect (0 = current)
session_idstringOptional session ID
targetstringWhat to inspect

No output schema declared.

No examples provided.

run_until ~115

Run until a specific location with temporary breakpoints. Sets one-time breakpoints that are automatically removed after being hit. Useful for quickly running to specific locations without permanent breakpoints. Enhanced features: - Multiple target locations - Conditional temporary breakpoints - Automatic cleanup

NameTypeReqDescription
alternative_locationsarrayAlternative locations to stop at
conditionstringOptional condition for temporary breakpoint
locationstringyesPrimary target location (file.py:line or line number)
session_idstringOptional session ID

No output schema declared.

No examples provided.

session ~108

Comprehensive session lifecycle management. **Actions:** • `status`: Show current session status (default) • `list`: List all active sessions • `stop`: Stop current/specified session • `restart`: Restart session with same configuration • `switch`: Switch to different session

NameTypeReqDescription
actionstringSession management action
keep_breakpointsbooleanKeep existing breakpoints on restart
session_idstringTarget session ID (for stop/restart/switch)

No output schema declared.

No examples provided.

session_start ~501

🚀 Create and start a debug session (requires init to be called first). Supports launch/attach modes for debugging.

NameTypeReqDescription
argsarrayCommand line arguments (for launch mode)
breakpointsarrayInitial breakpoints as objects with 'file' and 'line' fields. Can be in ANY files, often DIFFERENT from the target. The target starts execution, breakpoints pause where you want to debug. Ex: [{'file…
cwdstringWorking directory (for launch mode)
envobjectEnvironment variables (for launch mode)
hoststringHost to connect to (for remote attach mode)
languagestringProgramming language (java, javascript, python)
launch_config_namestringVS Code launch configuration name
pidintegerProcess ID to attach to (for local attach mode)
portintegerPort to connect to (for remote attach mode)
runtime_pathstringPath to the language runtime/interpreter. For Python: path to python executable (e.g., /path/to/venv/bin/python). For JavaScript: path to node executable. For Java: JAVA_HOME path. If not provided, a…
session_idstringOptional session ID (generated if not provided)
source_pathsarrayAdditional source directories for resolving file paths. Used for remote debugging where debug adapter returns paths that don't exist locally (e.g., JAR-internal paths like 'trino-main.jar!/io/trino/F…
subscribe_eventsarrayEvents to subscribe to for notifications. 'terminated' and 'breakpoint' are always auto-subscribed. Options: 'exception' (any exception occurred)
targetstringENTRYPOINT file/exec that starts execution and triggers the codepath you want to debug. This is NOT where you set breakpoints - use the 'breakpoints' parameter for those. Example: target='main.py' st…
workspace_rootstringWorkspace root directory

No output schema declared.

No examples provided.

step ~72

Step through code execution. Actions: - 'over': Execute line without entering functions (default) - 'into': Enter function calls - 'out': Complete current function

NameTypeReqDescription
actionstringStep action
countintegerNumber of steps
session_idstringOptional session ID

No output schema declared.

No examples provided.

variable ~199

Enhanced variable operations with live patching capabilities. Actions: - 'get': Evaluate expression (default) - 'set': Set variable value - 'patch': Live code patching for rapid iteration (replaces aidb.fix) Examples: - variable('get', expression='user.name') - variable('set', name='debug_mode', value='True') - variable('patch', name='calculate_tax', code='return amount * 0.08')

NameTypeReqDescription
actionstringVariable operation type
codestringNew code (for 'patch' action)
expressionstringExpression to evaluate (for 'get' action)
frameintegerStack frame context (0 = current)
namestringVariable/function name (for 'set'/'patch' actions)
session_idstringOptional session ID
valuestringNew value (for 'set' action)

No output schema declared.

No examples provided.

Common questions

What is the io.github.ai-debugger-inc/aidb MCP server?

io.github.ai-debugger-inc/aidb is an MCP server listed in the public MCP registry as io.github.ai-debugger-inc/aidb. Debug any supported language with breakpoints, variable/state inspection, and stepping. This page covers its PyPI package (ai-debugger-inc).

Is the io.github.ai-debugger-inc/aidb MCP server safe to use?

io.github.ai-debugger-inc/aidb scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 13 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.ai-debugger-inc/aidb MCP server expose?

io.github.ai-debugger-inc/aidb exposes 12 tools: init, session_start, execute, step, inspect, and 7 more. Their descriptions and schemas cost roughly 2,294 tokens of context every time the server is loaded.

Is the io.github.ai-debugger-inc/aidb MCP server still maintained?

io.github.ai-debugger-inc/aidb is still listed as active in the MCP registry. We last reached this channel on 13 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.