io.github.Sahib-Sawhney-WH/looking-glass-mcp
NPM · LOOKING-GLASS-MCP
AI-native browser for agents. 71 tools with self-healing, semantic extraction, vault CLI.
Available components
Last scanned (3 hours ago)
Scores higher than 41% of npm servers
Category Browser Automation
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 Security80
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects uuid 9.0.1, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 32 of 97 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency65
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Cryptographically verified build provenance (signed, bound to Sahib-Sawhney-WH/LookingGlass). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Maintenance check failed: the publisher has marked this version as deprecated on the registry, telling users to stop installing it. See how to fix → Fail
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability47
- AI-judged instruction clarity (poor).Fail
- Tool/resource definitions use about 1870 tokens (~26/item across 71 items; 71 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 Coverage33
- 0% of tools have a non-trivial description (not blank, and not just the tool's name).Fail
- 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 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "vault_delete" implies "delete" 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 71 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.
- 4 Nov 26 +1
- Stability: 0.97 → pass security
- 3 Nov 26 −1
- Stability: pass → 0.97 functional
- 28 Oct 26 +1
- Stability: 0.97 → pass security
- 27 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 0
- CVE-2023-54404 affects this package: high ▼ security
- 21 Oct 26 +1
- Stability: 0.97 → pass security
- 20 Oct 26 −1
- Stability: pass → 0.97 functional
- 17 Oct 26 +3
- Stability: 0.83 → 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 5 Nov 2026 · Analysed npm/looking-glass-mcp@3.1.1
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 | Sahib-Sawhney-WH/LookingGlass |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Sahib-Sawhney-WH/LookingGlass/.github/workflows/publish.yml@refs/tags/v3.1.1 |
| Rekor log index | 1199806681 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:9b3b39e3f7cbd5960c9675d1f0a63a5d210c83f8039476a78152472a29aa0775e68586c0a954b4b0ffab47ae22221dec9e40e5914ae4a963f4e4ddf53 |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 2 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-w5hq-g745-h8pq | CVE-2026-41907 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N | yes |
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 97 packages
| Packages resolved | 97 |
|---|---|
| Deprecated | 1 |
| Stale | 31 |
| 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 →
session_export_playwright ~43
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| outputPath | string | – | Custom output path for the .spec.ts file |
| sessionId | string | yes | Session ID to export (use session_list to find IDs) |
No output schema declared.
No examples provided.
session_list ~5
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
session_replay ~24
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | Session ID (first 8 chars or full UUID) |
No output schema declared.
No examples provided.
session_start ~15
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional session name |
No output schema declared.
No examples provided.
test_accessibility_audit ~8
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
test_assert ~47
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| attribute | string | – | Attribute name (for hasAttribute) |
| expected | string|number | – | Expected value |
| selector | string | – | CSS selector |
| type | string | yes | Assertion type |
No output schema declared.
No examples provided.
test_auth_flow ~108
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| passwordSelector | string | yes | CSS selector for password input |
| passwordValue | string | yes | Password |
| submitSelector | string | yes | CSS selector for submit/login button |
| url | string | yes | Login page URL |
| usernameSelector | string | yes | CSS selector for username/email input |
| usernameValue | string | yes | Username or email |
| waitForSelector | string | – | Wait for this element after login |
| waitForUrl | string | – | Wait for URL to match after login |
No output schema declared.
No examples provided.
test_chaos ~59
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| delayMs | number | – | Max delay for random-delays profile (default: 2000ms) |
| profile | string | yes | Chaos condition to apply |
| urlPattern | string | – | URL pattern for block-api profile (default: /api/) |
No output schema declared.
No examples provided.
test_chaos_clear ~8
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
test_fill_form ~19
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| fields | array | yes | Array of form fields to fill |
No output schema declared.
No examples provided.
test_generate_assertions ~7
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
test_scenario_run ~89
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| baseUrl | string | – | Base URL (e.g., http://localhost:3000) |
| dataSets | array | – | Data sets for parameterized testing. The scenario runs once per data set with {{variable}} substitution. |
| name | string | yes | Scenario name |
| steps | array | yes | Array of test steps to execute. Steps can use {{variable}} placeholders when dataSets is provided. |
No output schema declared.
No examples provided.
test_scenario_status ~7
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
test_stop_watch ~6
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
test_watch_events ~49
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| events | array | yes | Event types to watch |
| maxEvents | number | – | Maximum events to capture (default: 1000) |
| urlPattern | string | – | Filter network events by URL pattern |
No output schema declared.
No examples provided.
vault_delete ~16
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | string | yes | Profile name to delete |
No output schema declared.
No examples provided.
vault_inject ~24
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | string | yes | Vault profile whose fields to inject into the current page form |
No output schema declared.
No examples provided.
vault_list ~5
No description provided.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
vault_login ~33
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | string | yes | Vault profile to use for login |
| url | string | – | URL to navigate to before login (optional) |
No output schema declared.
No examples provided.
visual_baseline ~26
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Baseline name (e.g., "homepage", "login-form") |
No output schema declared.
No examples provided.
visual_compare ~18
No description provided.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Baseline name to compare against |
No output schema declared.
No examples provided.
How do I install the io.github.Sahib-Sawhney-WH/looking-glass-mcp server?
io.github.Sahib-Sawhney-WH/looking-glass-mcp runs locally as an npm package, launched with npx -y looking-glass-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 · looking-glass-mcp
claude mcp add sahib-sawhney-wh-looking-glass-mcp -- npx -y looking-glass-mcp
What is the io.github.Sahib-Sawhney-WH/looking-glass-mcp server?
io.github.Sahib-Sawhney-WH/looking-glass-mcp is listed in the public MCP registry as io.github.Sahib-Sawhney-WH/looking-glass-mcp. AI-native browser for agents. 71 tools with self-healing, semantic extraction, vault CLI. This page covers its npm package (looking-glass-mcp).
Is the io.github.Sahib-Sawhney-WH/looking-glass-mcp server safe to use?
io.github.Sahib-Sawhney-WH/looking-glass-mcp scores 71 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 5 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.Sahib-Sawhney-WH/looking-glass-mcp server expose?
io.github.Sahib-Sawhney-WH/looking-glass-mcp exposes 71 tools: browser_navigate, browser_go_back, browser_go_forward, browser_click, browser_type, and 66 more. Their descriptions and schemas cost roughly 1,870 tokens of context every time the server is loaded.
Is the io.github.Sahib-Sawhney-WH/looking-glass-mcp server still maintained?
io.github.Sahib-Sawhney-WH/looking-glass-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.Sahib-Sawhney-WH/looking-glass-mcp server under?
io.github.Sahib-Sawhney-WH/looking-glass-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.