# me.openbrowser/openbrowser-ai

> AI browser automation. Write async Python to navigate, click, type, and extract data.

- name: me.openbrowser/openbrowser-ai
- version: 0.1.54
- connection class: L0 (run_local_package)
- trust: 89/100
- quality: –/100 (not scored)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/me.openbrowser%2Fopenbrowser-ai
- tools: https://api.protogrid.dev/v1/servers/me.openbrowser%2Fopenbrowser-ai/tools

**Runs on your machine: something must execute the package.** Only local packages are published (npm, PyPI, OCI, …). The registry never executes them, so tools are unknown until you run it.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "openbrowser-ai": {
      "command": "uvx",
      "args": [
        "openbrowser-ai==0.1.54",
        "--mcp"
      ],
      "env": {
        "OPENBROWSER_HEADLESS": "true",
        "OPENBROWSER_COMPACT_DESCRIPTION": "false",
        "OPENBROWSER_MAX_OUTPUT": "10000",
        "ANONYMIZED_TELEMETRY": "true"
      }
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: n/a
- freshness: 100
- provenance: 75
- drivers: +repository +dns-namespace ~liveness-unmeasured +updated-29d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality –/100 (not scored)

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: n/a (weight 30)

- n/a `tools.descriptions`, `tools.description_length`, `tools.schemas`, `tools.annotations`, `tools.directory_hints`, `tools.token_cost`, `tools.api_dump`: tool list unknown (behind auth, not probed, or empty)

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool list unknown

### dependencies: 67 (weight 15)

- fail `deps.known_vulns`: 11 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-2g87-pp6c-29x5 in aiohttp@3.14.3 (indirect, fixed in 3.14.4), GHSA-5wr8-gcqf-gqf3 in aiohttp@3.14.3 (indirect, fixed in 3.14.4), GHSA-4xpc-pv4p-pm3w in litellm@1.80.0 (direct, fixed in 1.84.0), ...; 15 more of lower severity or without a fix
- pass `deps.mcp_sdk_version`: mcp 1.30.0, no known advisory
- pass `deps.resolvable`: openbrowser-ai@0.1.54 resolved: 128 packages

- tools: unknown
- badge: [![protogrid quality](https://protogrid.dev/badge/me.openbrowser/openbrowser-ai.svg)](https://protogrid.dev/servers/me.openbrowser/openbrowser-ai)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- pypi openbrowser-ai@0.1.54: resolved, 127 dependencies, MCP SDK mcp 1.30.0
  - GHSA-4xpc-pv4p-pm3w (critical) in `` litellm@1.80.0 ``, direct, fixed in `` 1.84.0 ``, advisory summary: "LiteLLM: Authentication Bypass via Host Header Injection" https://osv.dev/vulnerability/GHSA-4xpc-pv4p-pm3w
  - GHSA-6wvf-77m9-58rm (critical) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.7 ``, advisory summary: "LiteLLM vulnerable to server-side template injection in the /prompts/test endpoint" https://osv.dev/vulnerability/GHSA-6wvf-77m9-58rm
  - GHSA-jjhc-v7c2-5hh6 (critical) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.0 ``, advisory summary: "LiteLLM: Authentication bypass via OIDC userinfo cache key collision" https://osv.dev/vulnerability/GHSA-jjhc-v7c2-5hh6
  - GHSA-2g87-pp6c-29x5 (high) in `` aiohttp@3.14.3 ``, indirect, fixed in `` 3.14.4 ``, advisory summary: "aiohttp: Multiple instances of excessive or unbounded memory/CPU use" https://osv.dev/vulnerability/GHSA-2g87-pp6c-29x5
  - GHSA-5wr8-gcqf-gqf3 (high) in `` aiohttp@3.14.3 ``, indirect, fixed in `` 3.14.4 ``, advisory summary: "aiohttp server lacks an initial request/header timeout" https://osv.dev/vulnerability/GHSA-5wr8-gcqf-gqf3
  - GHSA-53mr-6c8q-9789 (high) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.0 ``, advisory summary: "LiteLLM: Privilege escalation via unrestricted proxy configuration endpoint" https://osv.dev/vulnerability/GHSA-53mr-6c8q-9789
  - GHSA-69x8-hrgq-fjj8 (high) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.0 ``, advisory summary: "LiteLLM: Password hash exposure and pass-the-hash authentication bypass" https://osv.dev/vulnerability/GHSA-69x8-hrgq-fjj8
  - GHSA-7488-6r32-c95q (high) in `` litellm@1.80.0 ``, direct, fixed in `` 1.84.0 ``, advisory summary: "LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback" https://osv.dev/vulnerability/GHSA-7488-6r32-c95q
  - GHSA-qrc4-49gv-mv9m (high) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.14 ``, advisory summary: "LiteLLM allows an authenticated internal\_user to create API keys with access to routes that their role does not permit" https://osv.dev/vulnerability/GHSA-qrc4-49gv-mv9m
  - GHSA-v4p8-mg3p-g94g (high) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.7 ``, advisory summary: "LiteLLM: Authenticated command execution via MCP stdio test endpoints" https://osv.dev/vulnerability/GHSA-v4p8-mg3p-g94g
  - GHSA-wpfp-gwwc-vwq6 (high) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.10 ``, advisory summary: "LiteLLM allows a user to modify their own user\_role via the /user/update endpoint" https://osv.dev/vulnerability/GHSA-wpfp-gwwc-vwq6
  - GHSA-3cv6-jpf6-8222 (moderate) in `` litellm@1.80.0 ``, direct, fixed in `` 1.88.6 ``, advisory summary: "LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters" https://osv.dev/vulnerability/GHSA-3cv6-jpf6-8222
  - GHSA-4jcj-7x88-m979 (moderate) in `` litellm@1.80.0 ``, direct, fixed in `` 1.84.0 ``, advisory summary: "LiteLLM: MCP Proxy Has Improper Authentication" https://osv.dev/vulnerability/GHSA-4jcj-7x88-m979
  - GHSA-5jmr-gcrj-2c9q (moderate) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.7 ``, advisory summary: "LiteLLM: Arbitrary file write via path traversal in Skills archive extraction" https://osv.dev/vulnerability/GHSA-5jmr-gcrj-2c9q
  - GHSA-hx8v-g79f-8w5f (moderate) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.9 ``, advisory summary: "LiteLLM Proxy has server-side request forgery via the \`user\_config\` request parameter" https://osv.dev/vulnerability/GHSA-hx8v-g79f-8w5f
  - GHSA-j37q-q7p9-vpwm (moderate) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "LiteLLM: SSO Debug Flow Has Improper Authentication" https://osv.dev/vulnerability/GHSA-j37q-q7p9-vpwm
  - GHSA-494j-54xm-rwp3 (low) in `` aiohttp@3.14.3 ``, indirect, fixed in `` 3.14.4 ``, advisory summary: "AIOHTTP: Secure attribute not enforced for shared cookie" https://osv.dev/vulnerability/GHSA-494j-54xm-rwp3
  - GHSA-r7w7-9xr2-qq2r (low) in `` langchain-openai@1.1.9 ``, direct, fixed in `` 1.1.14 ``, advisory summary: "langchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding" https://osv.dev/vulnerability/GHSA-r7w7-9xr2-qq2r
  - GHSA-4g5m-c9r5-49xf (low) in `` litellm@1.80.0 ``, direct, fixed in `` 1.83.10 ``, advisory summary: "LiteLLM: Local file read via request-supplied OIDC file references" https://osv.dev/vulnerability/GHSA-4g5m-c9r5-49xf
  - GHSA-72m8-9m7m-h278 (low) in `` litellm@1.80.0 ``, direct, fixed in `` 1.82.0 ``, advisory summary: "LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks" https://osv.dev/vulnerability/GHSA-72m8-9m7m-h278
  - GHSA-c693-x898-5g4h (low) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "BerriAI litellm has SSRF via Unvalidated spec\_path URL in MCP OpenAPI Spec Loader" https://osv.dev/vulnerability/GHSA-c693-x898-5g4h
  - GHSA-m2v5-74w2-qhcj (low) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "BerriAI litellm: UI User Enumeration leads to System-Wide Information Disclosure" https://osv.dev/vulnerability/GHSA-m2v5-74w2-qhcj
  - GHSA-mf52-j94g-746m (low) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "LiteLLM: PROXY\_ADMIN database API Key Generator Has Insufficient Session Expiration" https://osv.dev/vulnerability/GHSA-mf52-j94g-746m
  - GHSA-p897-vf7j-f5h8 (low) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call\_type Mismatch on Async Endpoints" https://osv.dev/vulnerability/GHSA-p897-vf7j-f5h8
  - GHSA-qmf3-4767-5fg3 (low) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "LiteLLM: M2M JWT Handler Has Improper Authorization" https://osv.dev/vulnerability/GHSA-qmf3-4767-5fg3
  - GHSA-w2mh-qq9q-453x (low) in `` litellm@1.80.0 ``, direct, no fix yet, advisory summary: "BerriAI litellm: SSO Login Does Not Invalidate Previous UI Session Tokens" https://osv.dev/vulnerability/GHSA-w2mh-qq9q-453x

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

_none_

## Packages

- pypi openbrowser-ai@0.1.54

## Tools (0)

_none observed_