developer-tools Static interface comparison
mcp-debugger
0.25.1 0.26.0
2 new unknown capabilities require explicit review.
View the upgrade review as Markdown
A shareable summary of this comparison for an issue, pull request or ticket. Select the text and copy it.
INTERFACE DIFF
What changed, tool by tool
- 2Added tools
- 1Removed tools
- 11Modified tools
- 4Input-schema changes
- 0Output-schema changes
- 2Declared authority changes
14 tools with recorded changes
attach_to_processModifiedWhat changed
- attach_to_process — Schema change: input property host changed: description "Host to attach to … → "Host to attach to;….
- attach_to_process — Schema change: input property timeout changed: description "Connection timeout… → "Connection timeout….
- attach_to_process: description changed.
Why it could matter
- Calls or consumers built for the earlier schema may need to change.
- Models choose and call tools partly from their descriptions.
What to verify
- Validate representative existing tool calls against the new argument schema.
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousAttach to a running process for debugging. After the handshake the target is verified by polling for threads; if none are reported within verifyTimeout (~20s default) the attach fails and the proxy is torn down. When a requested post-attach pause is accepted but no stopped event arrives within its bounded wait, returns state "running" with pending:true; the late event alone changes the session to "paused"
- CurrentAttach to a running process for debugging. After the handshake the target is verified by polling for threads; if none are reported within verifyTimeout (~20s default) the attach fails and the proxy is torn down. When a requested post-attach pause is accepted but no stopped event arrives within its bounded wait, returns state "running" with pending:true; the late event alone changes the session to "paused" — call wait_for_stop to block until it does
Input schema
Property Previous (0.25.1) Current (0.26.0) Change hoststringoptional stringoptional - Description changed
timeoutnumberoptional numberoptional - Description changed
11 unchanged entries
(schema root)adapterConfigbreakOnExceptionsjustMyCodeportprocessIdsessionIdsourcePathssourcePaths › [items]stopOnEntryverifyTimeout
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
continue_executionModifiedWhat changed
- continue_execution: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousContinue execution. Returns immediately after the adapter acknowledges; does not wait for the next stop. When the program stops again the session state becomes "paused" — check list_debug_sessions or get_stack_trace, whose lastStop/stopReason tells you why it stopped (e.g. "breakpoint" vs "exception"). Use get_output to read the program's stdout/stderr
- CurrentContinue execution. Returns immediately after the adapter acknowledges; does not wait for the next stop. Call wait_for_stop to block until the program stops again or ends — it reports why (lastStop, e.g. "breakpoint" vs "exception") and where; list_debug_sessions and get_stack_trace show the same without waiting. Use get_output to read the program's stdout/stderr
Input schema
Input schema unchanged.
2 unchanged entries
(schema root)sessionId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
create_debug_sessionModifiedWhat changed
- create_debug_session — Schema change: input property added: breakOnExceptions.
- create_debug_session — Schema change: input property added: justMyCode.
- create_debug_session — Schema change: input property added: processId.
- create_debug_session — Schema change: input property added: sourcePaths.
- create_debug_session — Schema change: input property adapterConfig changed: description "Attach mode only: … → "Attach mode only: ….
- create_debug_session — Schema change: input property host changed: description "Host to attach to … → "Attach mode only: ….
- create_debug_session — Schema change: input property language changed: enum ["javascript","pyth… → ["javascript","pyth….
- create_debug_session — Schema change: input property port changed: description "Debug port to atta… → "Debug port to atta….
- create_debug_session — Schema change: input property timeout changed: description "Connection timeout… → "Attach mode only: ….
- create_debug_session: description changed.
Why it could matter
- Calls or consumers built for the earlier schema may need to change.
- Models choose and call tools partly from their descriptions.
What to verify
- Validate representative existing tool calls against the new argument schema.
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousCreate a new debugging session. Provide host and port to attach to a running process; omit them for launch mode. Attaching pauses the target unless stopOnEntry is false
- CurrentCreate a new debugging session. Passing port, processId or an adapterConfig that names a target (a debugger URI: vmServiceUri, websocketAddress, vmServiceInfoFile; or a Flutter deviceId, for an app running on an Android device) attaches to a running process in the same call, with every attach argument attach_to_process takes (host alone does not); omit them for launch mode. Attaching pauses the target unless stopOnEntry is false
Input schema
Property Previous (0.25.1) Current (0.26.0) Change adapterConfigobject, additionalProperties=trueoptional object, additionalProperties=trueoptional - Description changed
breakOnExceptionsnot present string, enum (3)optional - Added
hoststringoptional stringoptional - Description changed
justMyCodenot present booleanoptional - Added
languagestring, enum (10)required string, enum (11)required - Constraint: enum
enum: ["javascript","python","mock","ruby","go","rust","java","dotnet","cpp","cobol"] → ["javascript","python","mock","ruby","go","rust","java","dotnet","cpp","cobol","dart"]portnumberoptional numberoptional - Description changed
processIdnot present number | stringoptional - Added
sourcePathsnot present arrayoptional - Added
sourcePaths › [items]not present string - Added
timeoutnumberoptional numberoptional - Description changed
5 unchanged entries
(schema root)executablePathnamestopOnEntryverifyTimeout
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
get_stack_traceModifiedWhat changed
- get_stack_trace: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousGet stack trace. The response includes stopReason — why the session is paused. For an implicit frameless stopped thread, a sibling with policy-recognized user frames is preferred and adopted, with the switch disclosed in note. Internal/runtime frames are filtered by default; when any are hidden the response carries hiddenFrames and a note. When the frame the program is paused in is itself internal, pausedFrame names it (kept: whether it was retained as stackFrames[0]) and the note says so
- CurrentGet stack trace. The response includes stopReason — why the session is paused. For an implicit frameless stopped thread, a sibling with policy-recognized user frames is preferred and adopted, with the switch disclosed in note. Internal/runtime frames are filtered by default; when any are hidden the response carries hiddenFrames and a note. When the frame the program is paused in is itself internal, pausedFrame names it (kept: whether it was retained as stackFrames[0]) and the note says so. The note also says when the top frame's file is newer than the compiled file the debugger binds it through (a stale build)
Input schema
Input schema unchanged.
4 unchanged entries
(schema root)includeInternalssessionIdthreadId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
hot_reloadAddedWhat changed
- New tool hot_reload, declared with unknown effect.
Why it could matter
- Valyd could not determine this tool’s effect from its declared interface, so its authority is not known.
What to verify
- Read the tool’s documentation and schema before allowing agents to use it.
- Declared effect
- — → unknown
Input schema
Property Previous (0.25.1) Current (0.26.0) Change (schema root)not present object - Added
classesDirnot present stringoptional - Added
sessionIdnot present stringrequired - Added
sinceTimestampnot present numberoptional - Added
timeoutnot present numberoptional - Added
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
pause_executionModifiedWhat changed
- pause_execution: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousPause a running program. Waits briefly for the stop; if the program cannot stop within ~5s (e.g. blocked in native code, or an idle server waiting for input), returns success with pending:true and the session reports "paused" the next time the program runs code. Fails with an actionable error if the session has no debuggable target to pause (e.g. a js attach whose target session was never adopted or has ended)
- CurrentPause a running program. Waits briefly for the stop; if the program cannot stop within ~5s (e.g. blocked in native code, or an idle server waiting for input), returns success with pending:true and the session reports "paused" the next time the program runs code (call wait_for_stop to block until then). An observed stop answers with stopReason, the first visible frame as location (with its source context), and note when the stop was reported on a thread with no program frame — a sibling thread in program code is shown instead, or, when none has one, the note says no program frame is active. Fails with an actionable error if the session has no debuggable target to pause (e.g. a js attach whose target session was never adopted or has ended)
Input schema
Input schema unchanged.
3 unchanged entries
(schema root)sessionIdthreadId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
redefine_classesRemovedWhat changed
- Tool redefine_classes was removed.
Why it could matter
- Integrations, prompts or agent configurations that call this tool will not find it in this release.
What to verify
- Check whether existing integrations still reference this tool.
- Declared effect
- unknown → —
Input schema
Property Previous (0.25.1) Current (0.26.0) Change (schema root)object not present - Removed
classesDirstringrequired not present - Removed
sessionIdstringrequired not present - Removed
sinceTimestampnumberoptional not present - Removed
timeoutnumberoptional not present - Removed
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
restart_debuggingModifiedWhat changed
- restart_debugging: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousRestart the debuggee: terminate the current program (if still running) and relaunch it with the same configuration as the last start_debugging. All current breakpoints are re-applied automatically. The get_output buffer starts fresh — read from since=0 after a restart. Works while running, paused, or after the program has exited. Not available for attach sessions or sessions never launched. Answers like start_debugging, including "running" with pending:true when the relaunch has not stopped within its readiness window
- CurrentRestart the debuggee: terminate the current program (if still running) and relaunch it with the same configuration as the last start_debugging. All current breakpoints are re-applied automatically. The get_output buffer starts fresh — read from since=0 after a restart. Works while running, paused, or after the program has exited. Not available for attach sessions or sessions never launched. Answers like start_debugging, including "running" with pending:true when the relaunch has not stopped within the same short hold (then call wait_for_stop)
Input schema
Input schema unchanged.
2 unchanged entries
(schema root)sessionId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
set_breakpointModifiedWhat changed
- set_breakpoint — Schema change: input property function changed: description "Address by symbol … → "Address by symbol ….
- set_breakpoint — Schema change: input property logMessage changed: description "Create a logpoint:… → "Create a logpoint:….
Why it could matter
- Calls or consumers built for the earlier schema may need to change.
What to verify
- Validate representative existing tool calls against the new argument schema.
- Declared effect
- unknown → unknown
Input schema
Property Previous (0.25.1) Current (0.26.0) Change functionstringoptional stringoptional - Description changed
logMessagestringoptional stringoptional - Description changed
9 unchanged entries
(schema root)conditionexpectedContentfilelinenearLinesessionIdstatementsuspendPolicy
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
start_debuggingModifiedWhat changed
- start_debugging — Schema change: input property added: testRunner.
- start_debugging — Schema change: input property added: testTarget.
- start_debugging — Schema change: input property dapLaunchArgs changed: +description="DAP launch argumen…, properties {"justMyCode":{"des… → {"justMyCode":{"des….
- start_debugging — Schema change: input property dryRunSpawn changed: +description="Check the launch w….
- start_debugging: description changed.
Why it could matter
- Calls or consumers built for the earlier schema may need to change.
- Models choose and call tools partly from their descriptions.
What to verify
- Validate representative existing tool calls against the new argument schema.
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousStart 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"
- CurrentStart debugging a script. Answers when the launched program stops, when it ends, or after a short hold — whichever comes first, and the same way in every language: "paused" with a reason and, as wait_for_stop answers a stop, the location, its source context and a note (a breakpoint reached as the program starts is answered here), "stopped" with the exit code, or "running" with pending:true when the program has not stopped yet; the message says what is armed. The hold is not a limit on the program — nothing is cancelled when it passes and breakpoints stay armed: call wait_for_stop to block until the program stops or ends (for a server, after sending the request that reaches your breakpoint). A stopOnEntry launch is answered at its entry stop
Input schema
Property Previous (0.25.1) Current (0.26.0) Change dapLaunchArgsobject, additionalProperties=trueoptional object, additionalProperties=trueoptional - Description changed
dapLaunchArgs › noDebugbooleanoptional booleanoptional - Description changed
dryRunSpawnbooleanoptional booleanoptional - Description changed
testRunnernot present stringoptional - Added
testTargetnot present stringoptional - Added
9 unchanged entries
(schema root)adapterLaunchConfigargsargs › [items]breakOnExceptionsdapLaunchArgs › justMyCodedapLaunchArgs › stopOnEntryscriptPathsessionId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
step_intoModifiedWhat changed
- step_into: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousStep into the current call. Waits briefly for the program to stop; if the step is still executing after ~5s, returns success with state "running" and pending:true — the session becomes "paused" when the step completes
- CurrentStep into the current call. Waits briefly for the program to stop; if the step is still executing after ~5s, returns success with state "running" and pending:true — the session becomes "paused" when the step completes (call wait_for_stop to block until then)
Input schema
Input schema unchanged.
2 unchanged entries
(schema root)sessionId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
step_outModifiedWhat changed
- step_out: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousStep out of the current function. Waits briefly for the program to stop; if the step is still executing after ~5s (e.g. the rest of the function is long-running), returns success with state "running" and pending:true — the session becomes "paused" when the step completes
- CurrentStep out of the current function. Waits briefly for the program to stop; if the step is still executing after ~5s (e.g. the rest of the function is long-running), returns success with state "running" and pending:true — the session becomes "paused" when the step completes (call wait_for_stop to block until then)
Input schema
Input schema unchanged.
2 unchanged entries
(schema root)sessionId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
step_overModifiedWhat changed
- step_over: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- unknown → unknown
- Description
- PreviousStep over the current line. Waits briefly for the program to stop; if the step is still executing after ~5s (e.g. stepping over a long-running call), returns success with state "running" and pending:true — the session becomes "paused" when the step completes (check list_debug_sessions, or call pause_execution to interrupt)
- CurrentStep over the current line. Waits briefly for the program to stop; if the step is still executing after ~5s (e.g. stepping over a long-running call), returns success with state "running" and pending:true — the step is still in effect and the session becomes "paused" when it completes (call wait_for_stop to block until then, or pause_execution to interrupt)
Input schema
Input schema unchanged.
2 unchanged entries
(schema root)sessionId
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
wait_for_stopAddedWhat changed
- New tool wait_for_stop, declared with unknown effect.
Why it could matter
- Valyd could not determine this tool’s effect from its declared interface, so its authority is not known.
What to verify
- Read the tool’s documentation and schema before allowing agents to use it.
- Declared effect
- — → unknown
Input schema
Property Previous (0.25.1) Current (0.26.0) Change (schema root)not present object - Added
sessionIdnot present stringrequired - Added
timeoutnot present numberoptional - Added
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
No tools match these filters.
16 tools with no recorded change
clear_breakpointsclose_debug_sessiondetach_from_processevaluate_expressionexpose_sessionget_local_variablesget_outputget_scopesget_source_contextget_variableslist_breakpointslist_debug_sessionslist_supported_languageslist_threadsremove_breakpointunexpose_session
Evidence and provenance
- Static findings
- FAIL from Modelara’s automated analysis of the two declared interfaces. A policy outcome, not a security rating or a runtime test.
- Human review
- Pending human review. No reviewer decision is recorded for this comparison.
- Published evidence
- Part of Valyd’s published data generation listed in valyd-data-source.json. Published records are not rewritten.
Show provenance and exact files
- Comparison
debugmcp-mcp-debugger/0.25.1~0.26.0The published comparison identifier.- Analyzer
modelara v0.1.8Policy version not recorded.Analyzed Nov 16, 2026, 9:50 PM UTC.- Distribution
npm- Previous release
@debugmcp/mcp-debugger@0.25.128 tools · published by the registry Sep 30, 2026, 10:36 PM UTCArtifact integritysha512-qz6mhmIF8INIzP86Dwyl61kUfl8XjLHrR6r2Ksgzci9+nYvtc58RF4JO1Pbl1Cs54g3RzaDt9tV+OQZF4BSHAw==Interface fingerprintsha256:b60dfbfde9842ff4088c280976c54853e0a176e1c667ca38b53fd6aa9451e9b9Exact interface snapshot (JSON)- Current release
@debugmcp/mcp-debugger@0.26.029 tools · published by the registry Oct 31, 2026, 3:14 AM UTCArtifact integritysha512-Wx1AmdzxyRS900l4syNGcffeshdvvfH8+MdcW0ydMrrQUdDv2Q/h3evN4WY99HhK3vsKpqZCI9Va/e7E4dIeWg==Interface fingerprintsha256:84609e2fbc5f78d0eb1f5e29d16eb872f2326814bfe2871b01f74f504c1fb58aExact interface snapshot (JSON)- Comparison record
- Exact comparison record (JSON)
The integrity value or digest identifies the exact artifact that was inspected; it does not show that the package is safe. The interface fingerprint identifies the declared tools and schemas Modelara recorded for that release.
MODELARA ANALYSIS OUTPUT
Interface findings
Policy failures
2 findingshot_reloadFAILAddedwait_for_stopFAILAdded
Requires review
5 findingsredefine_classesREVIEWRemovedattach_to_processREVIEWChangedShow details
input property host changed: description "Host to attach to … → "Host to attach to;…input property timeout changed: description "Connection timeout… → "Connection timeout…
create_debug_sessionREVIEWChangedShow details
input property added: breakOnExceptionsinput property added: justMyCodeinput property added: processIdinput property added: sourcePathsinput property adapterConfig changed: description "Attach mode only: … → "Attach mode only: …input property host changed: description "Host to attach to … → "Attach mode only: …input property language changed: enum ["javascript","pyth… → ["javascript","pyth…input property port changed: description "Debug port to atta… → "Debug port to atta…input property timeout changed: description "Connection timeout… → "Attach mode only: …
set_breakpointREVIEWChangedShow details
input property function changed: description "Address by symbol … → "Address by symbol …input property logMessage changed: description "Create a logpoint:… → "Create a logpoint:…
start_debuggingREVIEWChangedShow details
input property added: testRunnerinput property added: testTargetinput property dapLaunchArgs changed: +description="DAP launch argumen…, properties {"justMyCode":{"des… → {"justMyCode":{"des…input property dryRunSpawn changed: +description="Check the launch w…
Informational
10 findingsattach_to_processINFOChangedcontinue_executionINFOChangedcreate_debug_sessionINFOChangedget_stack_traceINFOChangedpause_executionINFOChangedrestart_debuggingINFOChangedstart_debuggingINFOChangedstep_intoINFOChangedstep_outINFOChangedstep_overINFOChanged
What do these results mean?
- PASS
- No policy-significant interface change detected.
- REVIEW
- Interface changes require inspection.
- FAIL
- A policy-significant change was detected.
- INVALID
- The comparison could not be evaluated reliably.