io.github.therealtimex/browser-use
PYPI · REALTIMEX-BROWSER-USE · SCANNED SEP 20
AI browser automation - navigate, click, type, extract content, and run autonomous web tasks
Available components
Recent critical change
CVE-2026-34520 affects this package (4 Aug 2026). See the changelog before you install this server.
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 Security22
- Malware scan not yet available for this package.Unverified
- CVE check failed: an unpatched critical CVE affects this package; the score is capped at 0. See how to fix → View diagnostics → Fail
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- Dependency health was assessed across the 200 of 262 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency33
- 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
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 353 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability0
- Schema quality not yet verified: this server's registry entry declares environment variables (an API key or similar) that our sandbox does not supply, so we have no schema to assess.Unverified
Stability & Change Management0
- Stability not yet verified: this server's registry entry declares environment variables (an API key or similar) that our sandbox does not supply, so we have no schema to compare.Unverified
Tool Coverage0
- Tool coverage not yet verified: this server's registry entry declares environment variables (an API key or similar) that our sandbox does not supply, so we have no tool definitions to assess.Unverified
Tool Safety0
- Tool safety not yet verified: this server's registry entry declares environment variables (an API key or similar) that our sandbox does not supply, so we have no tool text to scan.Unverified
Capabilities0
- Protocol version not yet verified: this server's registry entry declares environment variables (an API key or similar) that our sandbox does not supply, so we never saw its MCP handshake.Unverified
Unverified: 5 categories
Categories scored 0 because our sandbox run of this package has not given us the schema these checks need to read. That is a gap on our side rather than a finding about the package, and we only credit what we can confirm, so the score stands at 0 until the capture succeeds. We are working through the fleet, so this normally clears without any action from you. How we score packages →
How do I install the io.github.therealtimex/browser-use MCP server?
io.github.therealtimex/browser-use runs locally as a PyPI package, launched with uvx realtimex-browser-use. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · realtimex-browser-use
claude mcp add therealtimex-browser-use -- uvx realtimex-browser-use
{
"mcpServers": {
"therealtimex-browser-use": {
"command": "uvx",
"args": [
"realtimex-browser-use"
]
}
}
} {
"servers": {
"therealtimex-browser-use": {
"command": "uvx",
"args": [
"realtimex-browser-use"
]
}
}
} codex mcp add therealtimex-browser-use -- uvx realtimex-browser-use
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"therealtimex-browser-use": {
"type": "local",
"command": [
"uvx",
"realtimex-browser-use"
],
"enabled": true
}
}
} openclaw mcp add therealtimex-browser-use --command uvx --arg realtimex-browser-use
mcp_servers:
therealtimex-browser-use:
command: "uvx"
args: ["realtimex-browser-use"] {
"McpServers": {
"therealtimex-browser-use": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"realtimex-browser-use"
]
}
}
} assistant mcp add therealtimex-browser-use -t stdio -c uvx -a realtimex-browser-use
{
"mcpServers": {
"therealtimex-browser-use": {
"command": "uvx",
"args": [
"realtimex-browser-use"
]
}
}
} 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.
- 7 Sept 26 0
- Malware scan: pass → unverified ▼ security
- 5 Sept 26 0
- Malware scan: unverified → pass ▲ security
- 1 Sept 26 0
- Malware scan: pass → unverified ▼ security
- 29 Aug 26 0
- Malware scan: unverified → pass ▲ security
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 9 Aug 26 0
- Malware scan: unverified → pass ▲ security
- 8 Aug 26 0
- Security disclosure: fail → pass ▲ 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 20 Sept 2026 · Analysed pypi/realtimex-browser-use@0.7.10
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Vulnerabilities 64 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-2fqr-mr3j-6wp8 | CVE-2026-54279 | low | yes | |
| GHSA-2vrm-gr82-f7m5 | CVE-2026-34514 | low | yes | |
| GHSA-3wq7-rqq7-wx6j | CVE-2026-34517 | low | yes | |
| GHSA-4fvr-rgm6-gqmc | CVE-2026-54273 | medium | yes | |
| GHSA-4m7w-qmgq-4wj5 | CVE-2026-54275 | low | yes | |
| GHSA-54jq-c3m8-4m76 | CVE-2025-69226 | low | yes | |
| GHSA-63hf-3vf5-4wqf | CVE-2026-34520 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:H | yes |
| GHSA-63hw-fmq6-xxg2 | CVE-2026-54277 | medium | yes | |
| GHSA-69f9-5gxw-wvc2 | CVE-2025-69224 | low | yes | |
| GHSA-6jhg-hg63-jvvf | CVE-2025-69228 | medium | yes | |
| GHSA-6mq8-rvhq-8wgg | CVE-2025-69223 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-966j-vmvw-g2g9 | CVE-2026-34518 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N | yes |
| GHSA-9x8q-7h8h-wcw9 | CVE-2026-54280 | low | yes | |
| GHSA-c427-h43c-vf67 | CVE-2026-34525 | medium | yes | |
| GHSA-cq5v-8q36-5273 | CVE-2026-69244 | high | yes | |
| GHSA-fh55-r93g-j68g | CVE-2025-69230 | low | yes | |
| GHSA-g3cq-j2xw-wf74 | CVE-2026-54278 | medium | yes | |
| GHSA-g84x-mcqj-x9qq | CVE-2025-69229 | medium | yes | |
| GHSA-hcc4-c3v8-rx92 | CVE-2026-34513 | low | yes | |
| GHSA-hg6j-4rv6-33pg | CVE-2026-47265 | medium | yes | |
| GHSA-hpj7-wq8m-9hgp | CVE-2026-54276 | medium | yes | |
| GHSA-jg22-mg44-37j8 | CVE-2026-34993 | medium | CVSS:3.1/AV:L/AC:H/PR:H/UI:R/S:C/C:L/I:H/A:L | yes |
| GHSA-jj3x-wxrx-4x23 | CVE-2025-69227 | medium | yes | |
| GHSA-m5qp-6w8w-w647 | CVE-2026-34516 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-m6qw-4cw2-hm4m | CVE-2026-50269 | low | yes | |
| GHSA-mfx4-hv73-q22v | CVE-2026-69243 | medium | yes | |
| GHSA-mq44-7p77-q5h7 | CVE-2026-59881 | medium | yes | |
| GHSA-mqqc-3gqh-h2x8 | CVE-2025-69225 | low | yes | |
| GHSA-mwh4-6h8g-pg8w | CVE-2026-34519 | low | yes | |
| GHSA-p998-jp59-783m | CVE-2026-34515 | medium | yes | |
| GHSA-w2fm-2cpv-w7v5 | CVE-2026-22815 | medium | yes | |
| GHSA-xcgm-r5h9-7989 | CVE-2026-54274 | medium | yes | |
| PYSEC-2026-1097 | CVE-2025-69226 | none | yes | |
| PYSEC-2026-1099 | CVE-2025-69224 | none | yes | |
| PYSEC-2026-1100 | CVE-2025-69228 | none | yes | |
| PYSEC-2026-1101 | CVE-2025-69223 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-1105 | CVE-2025-69230 | none | yes | |
| PYSEC-2026-1106 | CVE-2025-69229 | none | yes | |
| PYSEC-2026-1107 | CVE-2025-69227 | none | yes | |
| PYSEC-2026-1109 | CVE-2025-69225 | none | yes | |
| PYSEC-2026-2094 | CVE-2026-22815 | none | yes | |
| PYSEC-2026-2095 | CVE-2026-34513 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| PYSEC-2026-2096 | CVE-2026-34514 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| PYSEC-2026-2097 | CVE-2026-34515 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
| PYSEC-2026-2098 | CVE-2026-34516 | none | yes | |
| PYSEC-2026-2099 | CVE-2026-34517 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| PYSEC-2026-2100 | CVE-2026-34518 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N | yes |
| PYSEC-2026-2101 | CVE-2026-34519 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| PYSEC-2026-2102 | CVE-2026-34520 | none | yes | |
| PYSEC-2026-2103 | CVE-2026-34525 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
Showing 50 of 64 vulnerabilities.
Background: What a vulnerability scan can and cannot prove →
Dependencies 200 packages
| Packages resolved | 200 |
|---|---|
| Deprecated | 1 |
| Stale | 8 |
| No linked repository | 1 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
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 →
Tools for package channels are captured by running the package in an isolated sandbox. The most recent sandbox run could not capture a tool list from this package.