io.github.GuardBee/reverse-shield
NPM · @GUARDBEE/MCP-REVERSE-SHIELD
Audits shipped apps for how easily they can be reverse engineered
Available components
Last scanned (20 hours ago)
Scores higher than 87% of npm servers
Category Security
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 97 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to GuardBee/guardbee-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability74
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 587 tokens (~146/item across 4 items; 4 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 Management27
- Stability observed for 8 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
- We read all 4 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 current MCP spec version (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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 0
- Package version: 0.6.0 → 0.6.1 functional
- 2 Nov 26 +35
- Injection markers: unverified → pass ▲ security
- Known CVEs: partial → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.20 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Dependency health: partial → 0.87 functional
- Package version: 0.5.0 → 0.6.0 functional
- Package version: 0.4.0 → 0.5.0 functional
- 1 Nov 26 −34
- Stability: 0.13 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- Package version: 0.4.0 → 0.5.0 functional
- 31 Oct 26 +11
- Known CVEs: unverified → partial ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → partial ▲ functional
- Dependency health: unverified → 0.87 ▲ functional
- Package version: 0.3.1 → 0.4.0 functional
- 30 Oct 26 −10
- Malware scan: pass → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Dependency health: 0.86 → unverified ▼ functional
- MCP protocol: Implements a current MCP spec version (2026-07-28). functional
- Package version: 0.2.0 → 0.3.1 functional
- Package version: 0.2.0 → 0.3.0 functional
- 29 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 0
- Known CVEs: partial → pass ▲ security
- Schema quality: pass → fail ▼ functional
- Stability: unverified → 0.03 ▲ functional
- Schema quality: good → excellent functional
- Dependency health: partial → 0.86 functional
- Package version: 0.1.1 → 0.2.0 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 4 Nov 2026 · Analysed npm/@guardbee/mcp-reverse-shield@0.6.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | GuardBee/guardbee-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/GuardBee/guardbee-mcp/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 3664661846 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:ba717133e20311a5b769622b0b59224f9dcc15157cd023d16655b11e6abc401361739e384dbe19996b315a208bf9f35a58543f5c8bb1934900b9dd603 |
Background: How many MCP packages publish verified provenance →
Dependencies 97 packages
| Packages resolved | 97 |
|---|---|
| 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 →
list_checks ~47
List every reverse-engineering resistance check, grouped by target (web, electron, android, ios, native, dotnet, framework), with what each finding gives away and how to fix it
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
scan_artifact ~298
Audit a shipped build artifact for how easily it can be reverse engineered — the defensive counterpart to reverse-engineering MCPs. Accepts an APK, an Electron app (.app bundle, app folder or app.asar), a macOS/Linux/Windows binary (Mach-O, ELF, PE, .NET assembly), a JavaScript bundle or source map, or a build output directory containing any of these. Reports shipped source maps and source code, missing minification/R8/.NET obfuscation, debug info and unstripped symbols, debuggable flags and entitlements, Electron fuses that allow Node/inspector/ASAR tampering, missing code signing, embedded credentials and internal hosts, with an A–F grade.
| Name | Type | Req | Description |
|---|---|---|---|
| baseline | string | – | Path to a baseline written by `guardbee-reverse-shield scan --update-baseline`; the report then lists new and fixed findings |
| exclude | array | – | Skip files/dirs whose path contains one of these strings |
| ignore | array | – | Accepted findings to leave out: a rule id, or rule:path-substring (e.g. bundle_secret:firebase-config.js) |
| include | array | – | Only check files whose path contains one of these strings |
| maxFiles | integer | – | Maximum number of files to check in a directory (default: 5000) |
| path | string | yes | Absolute or relative path to the artifact or build output directory |
No output schema declared.
No examples provided.
scan_url ~116
Check a live website the way an analyst starts: fetch the page, read its same-site JavaScript bundles, follow sourceMappingURL comments and try <bundle>.map even when the comment was stripped. Reports publicly downloadable source maps (and whether they embed the original sources), unminified or development bundles, embedded credentials and internal hosts. Third-party scripts are not fetched.
| Name | Type | Req | Description |
|---|---|---|---|
| maxScripts | integer | – | Maximum number of same-site scripts to fetch (default: 25) |
| url | string | yes | Page URL (http or https) |
No output schema declared.
No examples provided.
suggest_fixes ~126
Read a project's build configuration (Vite, webpack, Next.js, Angular, Create React App, Android Gradle and manifest, React Native, electron-builder / Forge, .NET project files, Flutter) and propose the changes that close what scan_artifact reports: hidden source maps, minification, R8, debuggable and backup flags, Hermes, Electron fuses and ASAR, no embedded PDB. Returns unified diffs to review and apply (git apply); it never modifies files.
| Name | Type | Req | Description |
|---|---|---|---|
| projectPath | string | yes | Project source directory (not the build output) |
No output schema declared.
No examples provided.
How do I install the io.github.GuardBee/reverse-shield MCP server?
io.github.GuardBee/reverse-shield runs locally as an npm package, launched with npx -y @guardbee/mcp-reverse-shield. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @guardbee/mcp-reverse-shield
claude mcp add guardbee-reverse-shield -- npx -y @guardbee/mcp-reverse-shield
What is the io.github.GuardBee/reverse-shield MCP server?
io.github.GuardBee/reverse-shield is an MCP server listed in the public MCP registry as io.github.GuardBee/reverse-shield. Audits shipped apps for how easily they can be reverse engineered. This page covers its npm package (@guardbee/mcp-reverse-shield).
Is the io.github.GuardBee/reverse-shield MCP server safe to use?
io.github.GuardBee/reverse-shield scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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.GuardBee/reverse-shield MCP server expose?
io.github.GuardBee/reverse-shield exposes 4 tools: scan_artifact, scan_url, suggest_fixes, list_checks. Their descriptions and schemas cost roughly 587 tokens of context every time the server is loaded.
Is the io.github.GuardBee/reverse-shield MCP server still maintained?
io.github.GuardBee/reverse-shield is still listed as active in the MCP registry. We last reached this channel on 4 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.GuardBee/reverse-shield MCP server under?
io.github.GuardBee/reverse-shield declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.