io.github.1shizaan/debugai-mcp
NPM · @DEBUGAI/MCP
MCP server for DebugAI. Browser sign-in, auto client setup, no key pasting.
Available components
Last scanned (4 hours ago)
Scores higher than 68% of npm servers
Category Developer Tools
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 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- 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 22 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability59
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2473 tokens (~824/item across 3 items; 3 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 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 Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
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.
- 3 Nov 26 0
- Stability: 0.97 → pass security
- 2 Nov 26 0
- Stability: pass → 0.97 functional
- 27 Oct 26 0
- Stability: 0.97 → pass security
- 26 Oct 26 0
- Stability: pass → 0.97 functional
- 24 Oct 26 +5
- Source repository: unverified → pass ▲ security
- 23 Oct 26 −5
- Provenance: pass → unverified ▼ security
- 17 Oct 26 +2
- Stability: 0.87 → pass security
- 15 Oct 26 −2
- Stability: pass → 0.83 functional
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 5 Nov 2026 · Analysed npm/@debugai/mcp@2.7.0
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 92 packages
| Packages resolved | 92 |
|---|---|
| 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 →
debug_error Debug Error ~761
Diagnose a failing command, error, exception, stack trace or failing test, and return a root cause plus ranked fixes. Call it the moment something fails, INCLUDING when you caused the failure yourself: a build or typecheck exiting non-zero (tsc, cargo, go build, mvn, dotnet), a linter reporting errors, a test suite going red, a script exiting non-zero, a runtime throwing, or the user pasting a traceback. Do not wait to be asked and do not skip it because you think you already know the fix: it answers from this project history, which is not derivable from the code in front of you, and a reported outcome on a known error is what makes the next answer better. Works for Python, JavaScript, TypeScript, Go, Rust, Java, C#, and more. Also takes a bug with NO error message: describe what you expected, what happened instead, and the code in between, and it is analysed like any other error. Pass the raw error text — this server runs locally and reads the source files the stack trace names, so you do not need to locate and paste the code first. Returns root cause plus up to 3 ranked fixes. Where an edit can be derived honestly a fix carries one, naming the file it belongs to; a fix that cannot be expressed as an exact replacement carries none rather than a guess, so read the root cause and write it yourself. Then call report_outcome.
| Name | Type | Req | Description |
|---|---|---|---|
| codeSnippet | string | – | Optional. Surrounding code near where the error was thrown. Usually unnecessary — the server reads the files the trace names off local disk. Supply it only when the relevant code is somewhere the tra… |
| errorText | string | yes | The full error message, exception, or stack trace text. |
| expected | string | – | What reproCommand should print or do once the bug is fixed. Used with reproCommand. |
| filePath | string | – | Absolute or relative path to the file that threw the error, if known. An ABSOLUTE path also tells DebugAI which repository the error belongs to. |
| language | string | – | Source language hint, one of: javascript, typescript, python, go, rust, java, csharp, cpp, c, php, ruby, kotlin, swift, lua, shell, powershell, sql, html, css, scala, dart, elixir, r, perl. Leave it… |
| projectRoot | string | – | Absolute path of the repository this error came from. Pass it when you were started somewhere other than that repository: project memory and local file reads are scoped to it (never your home directo… |
| reproCommand | string | – | The command that reproduces the failure, if you have one: a test, a script, a curl. DebugAI does not run it. Fix #1 is aimed at making it pass, and every fix's check becomes "run this, expect that" i… |
| snippetStartLine | integer | – | Optional, with codeSnippet. The line of the file that the FIRST line of codeSnippet is. Pass it when the snippet is a window from the middle of a file: without it the lines are counted from 1, and a… |
No output schema declared.
No examples provided.
lookup_error Look Up Error in Project Memory ~183
Check whether this project has seen an error before, instantly and for free: no model call, not counted against the debug limit. Returns how often it was seen, the fix that was confirmed for it (or one that stopped holding, so you do not repeat it), and fixes recently reported as failed in this project. Call it first on any failure, trivial ones included. With a confirmed fix, apply it and re-run what failed; otherwise call debug_error for a full analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| errorText | string | yes | The error message or stack trace, as you would pass it to debug_error. |
| filePath | string | – | An ABSOLUTE path inside the repository the error came from, if you have one. |
| projectRoot | string | – | Absolute path of the repository this error came from, when you were started somewhere else. Memory is scoped to it. |
No output schema declared.
No examples provided.
report_outcome Report Fix Outcome ~612
Report what happened after DebugAI answered, including when you did not use its fix. Call this ONCE per debug_error response, passing the debug_log_id from it. If you solved the problem another way, say so with result "unused" and put the real fix in actualFix: a case DebugAI got wrong is worth more to it than one it got right. A right diagnosis whose fix did not apply is "unused" as well, never "failed" - nothing of ours ran, and those two need opposite repairs. If the tool could have helped you more here, say that in toolFeedback. A confirmed fix is remembered for this project and returned to whoever hits the same error next: the fix you name in fixRank, or with "worked_modified" the code you send in finalFix.
| Name | Type | Req | Description |
|---|---|---|---|
| actualFix | string | – | What actually resolved the error, when it was not the fix DebugAI suggested. Free text. Say what the real cause turned out to be and what you changed, especially if the cause was in a different layer… |
| debugLogId | string | yes | The debug_log_id value from the debug_error response you are reporting on. |
| finalFix | string | – | Required with result "worked_modified", ignored otherwise: the code that actually worked, after your changes. It replaces DebugAI's suggestion in this project's memory, so the next person who hits th… |
| fixRank | integer | – | Which ranked fix you applied (1-3). The fix you name is the one remembered for this project. Omit for "unused". |
| newError | string | – | If result is "failed": the error observed AFTER applying the fix. An error message, not an explanation. |
| result | string | yes | "worked" = you applied a DebugAI fix and the error stopped. "worked_modified" = one of its fixes worked only after you changed it; finalFix is then required, and the code in it is what gets remembere… |
| toolFeedback | string | – | What would have made DebugAI more useful on THIS call. About the tool, not the bug: context it lacked, a question it should have asked, an input shape it rejected, a wrong assumption in its reasoning… |
No output schema declared.
No examples provided.
How do I install the io.github.1shizaan/debugai-mcp server?
io.github.1shizaan/debugai-mcp runs locally as an npm package, launched with npx -y @debugai/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @debugai/mcp
claude mcp add 1shizaan-debugai-mcp -- npx -y @debugai/mcp
What is the io.github.1shizaan/debugai-mcp server?
io.github.1shizaan/debugai-mcp is listed in the public MCP registry as io.github.1shizaan/debugai-mcp. MCP server for DebugAI. Browser sign-in, auto client setup, no key pasting. This page covers its npm package (@debugai/mcp).
Is the io.github.1shizaan/debugai-mcp server safe to use?
io.github.1shizaan/debugai-mcp scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 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.1shizaan/debugai-mcp server expose?
io.github.1shizaan/debugai-mcp exposes 3 tools: debug_error, report_outcome, lookup_error. Their descriptions and schemas cost roughly 1,556 tokens of context every time the server is loaded.
Is the io.github.1shizaan/debugai-mcp server still maintained?
io.github.1shizaan/debugai-mcp is still listed as active in the MCP registry. We last reached this channel on 5 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.1shizaan/debugai-mcp server under?
io.github.1shizaan/debugai-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.