me.openbrowser/openbrowser-ai
PYPI · OPENBROWSER-AI · SCANNED SEP 20
AI browser automation. Write async Python to navigate, click, type, and extract data.
Available components
Recent critical change
CVE-2026-37004 affects this package (9 Sept 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 Security24
- 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 139 of 140 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
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 me.openbrowser/openbrowser-ai MCP server?
me.openbrowser/openbrowser-ai runs locally as a PyPI package, launched with uvx openbrowser-ai. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · openbrowser-ai
claude mcp add me-openbrowser-openbrowser-ai -- uvx openbrowser-ai
{
"mcpServers": {
"me-openbrowser-openbrowser-ai": {
"command": "uvx",
"args": [
"openbrowser-ai"
]
}
}
} {
"servers": {
"me-openbrowser-openbrowser-ai": {
"command": "uvx",
"args": [
"openbrowser-ai"
]
}
}
} codex mcp add me-openbrowser-openbrowser-ai -- uvx openbrowser-ai
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"me-openbrowser-openbrowser-ai": {
"type": "local",
"command": [
"uvx",
"openbrowser-ai"
],
"enabled": true
}
}
} openclaw mcp add me-openbrowser-openbrowser-ai --command uvx --arg openbrowser-ai
mcp_servers:
me-openbrowser-openbrowser-ai:
command: "uvx"
args: ["openbrowser-ai"] {
"McpServers": {
"me-openbrowser-openbrowser-ai": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"openbrowser-ai"
]
}
}
} assistant mcp add me-openbrowser-openbrowser-ai -t stdio -c uvx -a openbrowser-ai
{
"mcpServers": {
"me-openbrowser-openbrowser-ai": {
"command": "uvx",
"args": [
"openbrowser-ai"
]
}
}
} 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.
- 20 Sept 26 0
- Package version: 0.1.50 → 0.1.51 functional
- 13 Sept 26 0
- Malware scan: fail → unverified ▼ security
- 12 Sept 26 0
- Malware scan: unverified → fail ▼ security
- 10 Sept 26 0
- Security disclosure: unverified → fail ▼ functional
- 9 Sept 26 0
- CVE-2026-37004 affects this package: high ▼ critical
- Security disclosure: fail → unverified ▼ functional
- 8 Sept 26 0
- Malware scan: fail → unverified ▼ security
- 4 Sept 26 0
- Malware scan: unverified → fail ▼ security
- 3 Sept 26 0
- Malware scan: fail → unverified ▼ 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 20 Sept 2026 · Analysed pypi/openbrowser-ai@0.1.51
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 32 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-4g5m-c9r5-49xf | CVE-2026-59819 | low | yes | |
| GHSA-4jcj-7x88-m979 | CVE-2026-12773 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L | yes |
| GHSA-4xpc-pv4p-pm3w | CVE-2026-49468 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-53mr-6c8q-9789 | CVE-2026-35029 | high | yes | |
| GHSA-5jmr-gcrj-2c9q | CVE-2026-59820 | medium | yes | |
| GHSA-69x8-hrgq-fjj8 | high | yes | ||
| GHSA-6wvf-77m9-58rm | CVE-2026-37004 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-72m8-9m7m-h278 | CVE-2026-59821 | low | yes | |
| GHSA-7488-6r32-c95q | CVE-2026-59822 | high | yes | |
| GHSA-c693-x898-5g4h | CVE-2026-12798 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L | no |
| GHSA-hx8v-g79f-8w5f | CVE-2026-59823 | medium | yes | |
| GHSA-j37q-q7p9-vpwm | CVE-2026-12795 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L | no |
| GHSA-jjhc-v7c2-5hh6 | CVE-2026-35030 | critical | yes | |
| GHSA-m2v5-74w2-qhcj | CVE-2026-12799 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N | no |
| GHSA-mf52-j94g-746m | CVE-2026-12772 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L | no |
| GHSA-p897-vf7j-f5h8 | CVE-2026-12797 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L | no |
| GHSA-qmf3-4767-5fg3 | CVE-2026-12771 | medium | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L | no |
| GHSA-qrc4-49gv-mv9m | CVE-2026-47101 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-v4p8-mg3p-g94g | CVE-2026-42271 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-w2mh-qq9q-453x | CVE-2026-12796 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L | no |
| GHSA-wpfp-gwwc-vwq6 | CVE-2026-47102 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| PYSEC-2026-2597 | CVE-2026-35029 | none | yes | |
| PYSEC-2026-2598 | CVE-2026-47101 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| PYSEC-2026-2599 | CVE-2026-42271 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| PYSEC-2026-2600 | CVE-2026-47102 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | yes |
| PYSEC-2026-3476 | CVE-2026-59819 | none | yes | |
| PYSEC-2026-3477 | CVE-2026-59820 | none | yes | |
| PYSEC-2026-3478 | CVE-2026-59821 | none | yes | |
| PYSEC-2026-3479 | CVE-2026-59822 | none | yes | |
| PYSEC-2026-3861 | CVE-2026-37004 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| PYSEC-2026-388 | CVE-2026-49468 | none | yes | |
| PYSEC-2026-390 | CVE-2026-35030 | none | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 139 packages
| Packages resolved | 139 |
|---|---|
| Deprecated | 1 |
| Stale | 11 |
| No linked repository | 2 |
| 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.