io.github.Digital-Defiance/mcp-debugger
NPM · @AI-CAPABILITIES-SUITE/MCP-DEBUGGER-SERVER
Node.js and TypeScript debugging with 25+ tools for AI agents
Available components
Last scanned (6 hours ago)
Scores higher than 74% of npm servers
Category Testing and QA
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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency43
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 329 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1623 tokens (~55/item across 29 items; 29 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
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 Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "debugger_step_over" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 29 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
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 4 Nov 26 +1
- Stability: 0.97 → pass security
- 3 Nov 26 −1
- Stability: pass → 0.97 functional
- 28 Oct 26 0
- Stability: 0.97 → pass security
- 27 Oct 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.
- 26 Oct 26 −1
- Stability: pass → 0.93 functional
- 17 Oct 26 +2
- Stability: 0.87 → pass security
- 15 Oct 26 −2
- Stability: pass → 0.83 functional
- 14 Oct 26 0
- Stability: 0.97 → pass security
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 7 Nov 2026 · Analysed npm/@ai-capabilities-suite/mcp-debugger-server@1.1.8
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
debugger_add_watch ~61
Add an expression to the watch list. The expression will be evaluated each time the process pauses.
| Name | Type | Req | Description |
|---|---|---|---|
| expression | string | yes | The expression to watch (e.g., "x", "obj.prop") |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_continue ~35
Resume execution of a paused debug session until the next breakpoint or program termination.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_detect_hang ~123
Run a command and detect if it hangs or enters an infinite loop. Returns hang status, location, and stack trace if hung.
| Name | Type | Req | Description |
|---|---|---|---|
| args | array | – | Command arguments (e.g., ["test.js"]) |
| command | string | yes | The command to execute (e.g., "node", "npm") |
| cwd | string | – | Working directory for the process |
| sampleInterval | number | – | Sample interval in milliseconds for infinite loop detection (e.g., 100) |
| timeout | number | yes | Timeout in milliseconds (e.g., 5000) |
No output schema declared.
No examples provided.
debugger_get_global_variables ~39
Get global variables accessible from the current scope with their names, values, and types.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_get_local_variables ~39
Get all local variables in the current scope with their names, values, and types.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_get_performance_metrics ~73
Get performance metrics including current memory usage, performance timeline, and leak detection.
| Name | Type | Req | Description |
|---|---|---|---|
| includeLeakDetection | boolean | – | Whether to run memory leak detection (takes 10 seconds) |
| includePerformanceTimeline | boolean | – | Whether to include performance timeline data |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_get_stack ~40
Get the current call stack with function names, file locations (absolute paths), and line numbers.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_get_watches ~39
Get all watched expressions with their current values. Reports value changes since the last pause.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_inspect ~61
Evaluate a JavaScript expression in the current execution context and return the result with type information.
| Name | Type | Req | Description |
|---|---|---|---|
| expression | string | yes | The JavaScript expression to evaluate (e.g., "x + 1") |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_inspect_object ~81
Inspect an object by its object reference, returning properties with values. Handles nested objects and arrays up to a specified depth.
| Name | Type | Req | Description |
|---|---|---|---|
| maxDepth | number | – | Maximum depth to traverse (default: 2) |
| objectId | string | yes | The object ID (from a previous inspection or evaluation) |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_list_breakpoints ~42
Get all breakpoints for a debug session with their file, line, condition, and enabled state.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_pause ~32
Pause a running debug session and return the current execution location.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_remove_breakpoint ~43
Remove a breakpoint from the debug session.
| Name | Type | Req | Description |
|---|---|---|---|
| breakpointId | string | yes | The breakpoint ID to remove |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_remove_watch ~45
Remove an expression from the watch list.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
| watchId | string | yes | The watch ID (expression) to remove |
No output schema declared.
No examples provided.
debugger_set_breakpoint ~86
Set a breakpoint at a specific file and line number. Optionally provide a condition.
| Name | Type | Req | Description |
|---|---|---|---|
| condition | string | – | Optional condition expression (e.g., "x > 10") |
| file | string | yes | The file path (absolute or relative) |
| line | number | yes | The line number (1-indexed) |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_set_exception_breakpoint ~86
Set an exception breakpoint to pause on caught and/or uncaught exceptions.
| Name | Type | Req | Description |
|---|---|---|---|
| breakOnCaught | boolean | yes | Whether to break on caught exceptions |
| breakOnUncaught | boolean | yes | Whether to break on uncaught exceptions |
| exceptionFilter | string | – | Optional regex pattern to filter exceptions by type/message |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_set_function_breakpoint ~54
Set a function breakpoint to pause when a function with the given name is called.
| Name | Type | Req | Description |
|---|---|---|---|
| functionName | string | yes | Function name or regex pattern to match |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_set_hit_count_condition ~91
Set a hit count condition for a breakpoint. The breakpoint will only pause when the condition is met.
| Name | Type | Req | Description |
|---|---|---|---|
| breakpointId | string | yes | The breakpoint ID |
| operator | string | yes | Hit count operator (==, >, >=, <, <=, % for modulo) |
| sessionId | string | yes | The debug session ID |
| value | number | yes | Hit count value to compare against |
No output schema declared.
No examples provided.
debugger_set_logpoint ~96
Set a logpoint that logs a message without pausing execution. Use {variable} syntax for interpolation.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | yes | The file path (absolute or relative) |
| line | number | yes | The line number (1-indexed) |
| logMessage | string | yes | Log message template with {variable} interpolation (e.g., "Value is {x}") |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_start ~92
Start a new debug session with a Node.js process. The process will be paused at the start.
| Name | Type | Req | Description |
|---|---|---|---|
| args | array | – | Command arguments (e.g., ["test.js"]) |
| command | string | yes | The command to execute (e.g., "node", "npm") |
| cwd | string | – | Working directory for the process |
| timeout | number | – | Timeout in milliseconds (default: 30000) |
No output schema declared.
No examples provided.
debugger_start_cpu_profile ~39
Start CPU profiling for a debug session. Collects CPU profile data for performance analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_step_into ~36
Execute the current line and pause at the first line inside any called function.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_step_out ~34
Execute until the current function returns and pause at the calling location.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_step_over ~36
Execute the current line and pause at the next line in the same scope.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_stop_cpu_profile ~35
Stop CPU profiling and return the profile data with bottleneck analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_stop_session ~38
Stop a debug session, cleanup all resources, and kill the process if still running.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_switch_stack_frame ~68
Switch the execution context to a specific stack frame by index. Frame 0 is the top frame (current location).
| Name | Type | Req | Description |
|---|---|---|---|
| frameIndex | number | yes | The frame index (0 = top frame, 1 = caller, etc.) |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_take_heap_snapshot ~35
Take a heap snapshot for memory analysis. Returns memory usage report.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
debugger_toggle_breakpoint ~44
Toggle a breakpoint between enabled and disabled states.
| Name | Type | Req | Description |
|---|---|---|---|
| breakpointId | string | yes | The breakpoint ID to toggle |
| sessionId | string | yes | The debug session ID |
No output schema declared.
No examples provided.
How do I install the io.github.Digital-Defiance/mcp-debugger server?
io.github.Digital-Defiance/mcp-debugger runs locally as an npm package, launched with npx -y @ai-capabilities-suite/mcp-debugger-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @ai-capabilities-suite/mcp-debugger-server
claude mcp add digital-defiance-mcp-debugger -- npx -y @ai-capabilities-suite/mcp-debugger-server
What is the io.github.Digital-Defiance/mcp-debugger server?
io.github.Digital-Defiance/mcp-debugger is listed in the public MCP registry as io.github.Digital-Defiance/mcp-debugger. Node.js and TypeScript debugging with 25+ tools for AI agents. This page covers its npm package (@ai-capabilities-suite/mcp-debugger-server).
Is the io.github.Digital-Defiance/mcp-debugger server safe to use?
io.github.Digital-Defiance/mcp-debugger scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 7 November 2026. It declares no install or post-install scripts. 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.Digital-Defiance/mcp-debugger server expose?
io.github.Digital-Defiance/mcp-debugger exposes 29 tools: debugger_start, debugger_set_breakpoint, debugger_continue, debugger_step_over, debugger_step_into, and 24 more. Their descriptions and schemas cost roughly 1,623 tokens of context every time the server is loaded.
Is the io.github.Digital-Defiance/mcp-debugger server still maintained?
io.github.Digital-Defiance/mcp-debugger is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.Digital-Defiance/mcp-debugger server under?
io.github.Digital-Defiance/mcp-debugger declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.Digital-Defiance/mcp-debugger server?
VerifyMCP ran 16 checks on io.github.Digital-Defiance/mcp-debugger, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.