io.github.Savvy-Tech-Sphere/usable-browser-agent
NPM · USABLE-BROWSER-AGENT
MCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier.
Available components
Last scanned (22 hours ago)
Scores higher than 50% 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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- 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
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 42 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability81
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 3771 tokens (~71/item across 53 items; 53 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 Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 64% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "browser_workflow_forget" implies "remove" 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 53 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.
- 2 Nov 26 +1
- Stability: 0.97 → pass security
- 1 Nov 26 −1
- Stability: pass → 0.97 functional
- 26 Oct 26 +1
- Stability: 0.97 → pass security
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.
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/usable-browser-agent@0.7.1
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 →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| 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 94 packages
| Packages resolved | 94 |
|---|---|
| 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 →
browser_workflow_forget ~78
Remove a stale, sensitive, or incorrect workflow memory by id. This appends a local tombstone; normal recall will stop returning that memory.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Workflow memory id, e.g. wm_20260604123000_ab12cd34. |
| reason | string | – | Optional short reason for the deletion. |
No output schema declared.
No examples provided.
browser_workflow_recall ~133
Search local workflow memory BEFORE starting any multi-step or repeated browser task. Use this first for changing sites like app stores, admin consoles, checkout flows, dashboards, or any task you may have done before.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Maximum matches to return (1-10, default 5). |
| query | string | – | Task objective or memory id, e.g. 'create a new app in Google Play Console'. |
| site | string | – | Site name or domain, e.g. 'Google Play Console' or 'play.google.com'. |
| tags | array | – | Optional tags to narrow recall. |
No output schema declared.
No examples provided.
browser_workflow_remember ~298
Save the verified reusable workflow after discovering or completing a browser task. Store durable UI labels, decisions, and pitfalls; do not store passwords, one-time codes, or transient [ref=eN] handles.
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | string | – | Confidence that the workflow is reusable. |
| domain | string | – | Domain, e.g. 'play.google.com'. |
| lastVerified | string | – | Verification date, default today. |
| notes | string | – | Short extra context for future agents. |
| outcome | string | – | What succeeded or what state was reached. |
| pitfalls | array | – | Things that were wrong, surprising, changed, or easy to miss. |
| selectors | array | – | Durable UI cues: visible labels, section names, field names. Avoid transient refs. |
| site | string | – | Human site name, e.g. 'Google Play Console'. |
| steps | array | yes | Ordered durable steps that worked. Use visible labels and page names, not transient refs. |
| supersedes | array | – | Workflow memory ids this record replaces because they are stale or incomplete. |
| tags | array | – | Search tags such as 'android', 'play-store', 'release'. |
| task | string | yes | Reusable task objective, e.g. 'Create a new Android app in Google Play Console'. |
| title | string | – | Page title where the workflow starts or was verified. |
| url | string | – | Useful starting URL if stable. |
No output schema declared.
No examples provided.
How do I install the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server?
io.github.Savvy-Tech-Sphere/usable-browser-agent runs locally as an npm package, launched with npx -y usable-browser-agent. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · usable-browser-agent
claude mcp add savvy-tech-sphere-usable-browser-agent -- npx -y usable-browser-agent
What is the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server?
io.github.Savvy-Tech-Sphere/usable-browser-agent is an MCP server listed in the public MCP registry as io.github.Savvy-Tech-Sphere/usable-browser-agent. MCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier. This page covers its npm package (usable-browser-agent).
Is the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server safe to use?
io.github.Savvy-Tech-Sphere/usable-browser-agent scores 75 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 4 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.Savvy-Tech-Sphere/usable-browser-agent MCP server expose?
io.github.Savvy-Tech-Sphere/usable-browser-agent exposes 53 tools: browser_workflow_recall, browser_workflow_remember, browser_workflow_forget, browser_native_status, browser_os_type, and 48 more. Their descriptions and schemas cost roughly 3,771 tokens of context every time the server is loaded.
Is the io.github.Savvy-Tech-Sphere/usable-browser-agent MCP server still maintained?
io.github.Savvy-Tech-Sphere/usable-browser-agent 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.