smart-xdebug-mcp
Connects AI assistants like Claude to PHP's XDebug debugger for runtime inspection, breakpoint control, and variable tracking, enabling natural language debugging of PHP applications.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
wallter
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
start_debug_sessionStarts a new PHP debugging session by listening for XDebug connections and executing a trigger command. WORKFLOW - Call tools in this order: 1. get_session_status - Check if a session is already active 2. set_breakpoint - Set breakpoints at locations you want to inspect 3. start_debug_session - Sta…
set_breakpointSets a breakpoint at a specific file and line. Breakpoints persist until the session ends. WHEN TO USE: - BEFORE calling start_debug_session to set initial breakpoints - DURING a paused session to add additional breakpoints PATH FORMAT - Use LOCAL paths relative to your project root: - Correct: "a…
inspect_variableInspects a PHP variable's value at the current breakpoint. Only works when session is PAUSED. WHEN TO USE: - After hitting a breakpoint (status="paused") - To examine specific values causing bugs - To understand object structure before filtering CONTEXT EFFICIENCY - Full dumps are expensive. Use J…
control_executionControls the debugger's execution flow. Use to step through code or end sessions. ACTIONS: step_over: Execute current line, pause at next line in same scope. Use when: Line calls a function you don't need to debug. Example: Skip framework internals, focus on your logic. step_into: Step INTO t…
get_session_statusReturns the current debug session status. Call this FIRST before starting a new session. WHEN TO USE: - Before start_debug_session: Check if a session is already active - During debugging: See current location and available actions - After errors: Diagnose session state RETURNS: - active: Whether …
query_historyQuery past variable values from the session recorder (time-travel debugging). WHEN TO USE: - To see how a variable changed over execution steps - To compare values between steps without re-running - To understand state progression leading to a bug DOES NOT REQUIRE PAUSED STATE - can query history …
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
fast-xml-parser has an entity encoding bypass via regex injection in DOCTYPE entity names
JSONPath Plus Remote Code Execution (RCE) Vulnerability
When Vitest UI server is listening, arbitrary file can be read and executed
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
fast-xml-parser affected by numeric entity expansion bypassing all entity expansion limits (incomplete fix for CVE-2026-26278)
LOG_LEVELXDEBUG_MCP_DATA_DIRXDEBUG_MCP_PATH_MAPPINGSXDEBUG_MCP_PORT9003 XDebug listener portXDEBUG_MCP_PROJECT_ROOTXDEBUG_MCP_TIMEOUT30000 Connection timeout (ms)XDEBUG_MCP_WATCHDOG_TIMEOUT300000 Auto-terminate idle sessions (5 min)Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
6/6 tools missing one or more hints — start_debug_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); set_breakpoint (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); inspect_variable (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 0/6 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
2 critical, 4 high severity in production deps — fast-xml-parser@4.5.0 (critical), jsonpath-plus@10.0.0 (critical)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/wallter/smart-xdebug-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check