# io.github.browserbase/mcp-server-browserbase

> MCP server for AI web browser automation using Browserbase and Stagehand

- name: io.github.browserbase/mcp-server-browserbase
- version: 2.1.1
- connection class: L0 (run_local_package)
- trust: 70/100
- quality: –/100 (not scored)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.browserbase%2Fmcp-server-browserbase
- tools: https://api.protogrid.dev/v1/servers/io.github.browserbase%2Fmcp-server-browserbase/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": {
    "mcp-server-browserbase": {
      "command": "npx",
      "args": [
        "-y",
        "@browserbasehq/mcp-server-browserbase@2.1.1"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "${BROWSERBASE_API_KEY}",
        "BROWSERBASE_PROJECT_ID": "${BROWSERBASE_PROJECT_ID}",
        "GEMINI_API_KEY": "${GEMINI_API_KEY}"
      }
    }
  }
}
```

Placeholders to fill: `${BROWSERBASE_API_KEY}`, `${GEMINI_API_KEY}`.

## Trust

- hygiene: 100
- liveness: n/a
- freshness: 25
- provenance: 80
- drivers: +repository +namespace-matches-repo ~liveness-unmeasured -stale-403d
- 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: 33 (weight 15)

- fail `deps.known_vulns`: 4 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-j4fx-xxwh-2485 in jsondiffpatch@0.6.0 (indirect, fixed in 0.7.6), GHSA-35jh-r3h4-6jhm in lodash@4.17.19 (indirect, fixed in 4.17.21), GHSA-r5fr-rjxr-66jc in lodash@4.17.19 (indirect, fixed in 4.18.0), ...; 11 more of lower severity or without a fix
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or later
- pass `deps.resolvable`: @browserbasehq/mcp-server-browserbase@2.1.1 resolved: 489 packages

- tools: unknown
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.browserbase/mcp-server-browserbase.svg)](https://protogrid.dev/servers/io.github.browserbase/mcp-server-browserbase)
- 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

- npm @browserbasehq/mcp-server-browserbase@2.1.1: resolved, 488 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h
  - GHSA-j4fx-xxwh-2485 (high) in `` jsondiffpatch@0.6.0 ``, indirect, fixed in `` 0.7.6 ``, advisory summary: "jsondiffpatch patch APIs are vulnerable to prototype pollution" https://osv.dev/vulnerability/GHSA-j4fx-xxwh-2485
  - GHSA-35jh-r3h4-6jhm (high) in `` lodash@4.17.19 ``, indirect, fixed in `` 4.17.21 ``, advisory summary: "Command Injection in lodash" https://osv.dev/vulnerability/GHSA-35jh-r3h4-6jhm
  - GHSA-r5fr-rjxr-66jc (high) in `` lodash@4.17.19 ``, indirect, fixed in `` 4.18.0 ``, advisory summary: "lodash vulnerable to Code Injection via \`\_.template\` imports key names" https://osv.dev/vulnerability/GHSA-r5fr-rjxr-66jc
  - GHSA-ph9p-34f9-6g65 (high) in `` tmp@0.0.33 ``, indirect, fixed in `` 0.2.6 ``, advisory summary: "tmp has Path Traversal via unsanitized prefix/postfix that enables directory escape" https://osv.dev/vulnerability/GHSA-ph9p-34f9-6g65
  - GHSA-vfj7-8cjw-p6xm (high) in `` braces@3.0.3 ``, indirect, no fix yet, advisory summary: "braces vulnerable to stack-exhaustion denial of service through deeply nested patterns" https://osv.dev/vulnerability/GHSA-vfj7-8cjw-p6xm
  - GHSA-86w9-cpqp-85rv (high) in `` node-forge@1.4.0 ``, indirect, no fix yet, advisory summary: "node-forge RSA PKCS\#1 v1.5 signature verification accepts extra nested DigestAlgorithm elements" https://osv.dev/vulnerability/GHSA-86w9-cpqp-85rv
  - GHSA-2fw4-mgq9-39cx (high) in `` oauth2-server@3.1.1 ``, indirect, no fix yet, advisory summary: "Code Injection in oauth2-server" https://osv.dev/vulnerability/GHSA-2fw4-mgq9-39cx
  - GHSA-4rg6-fm25-gc34 (high) in `` oauth2-server@3.1.1 ``, indirect, no fix yet, advisory summary: "oauth2-server through 3.1.1 vulnerable to Open Redirect" https://osv.dev/vulnerability/GHSA-4rg6-fm25-gc34
  - GHSA-33vc-wfww-vjfv (moderate) in `` jsondiffpatch@0.6.0 ``, indirect, fixed in `` 0.7.2 ``, advisory summary: "jsondiffpatch is vulnerable to Cross-site Scripting (XSS) via HtmlFormatter::nodeBegin" https://osv.dev/vulnerability/GHSA-33vc-wfww-vjfv
  - GHSA-29mw-wpgm-hmr9 (moderate) in `` lodash@4.17.19 ``, indirect, fixed in `` 4.17.21 ``, advisory summary: "Regular Expression Denial of Service (ReDoS) in lodash" https://osv.dev/vulnerability/GHSA-29mw-wpgm-hmr9
  - GHSA-f23m-r3pf-42rh (moderate) in `` lodash@4.17.19 ``, indirect, fixed in `` 4.18.0 ``, advisory summary: "lodash vulnerable to Prototype Pollution via array path bypass in \`\_.unset\` and \`\_.omit\`" https://osv.dev/vulnerability/GHSA-f23m-r3pf-42rh
  - GHSA-xxjr-mmjv-4gpg (moderate) in `` lodash@4.17.19 ``, indirect, fixed in `` 4.17.23 ``, advisory summary: "Lodash has Prototype Pollution Vulnerability in \`\_.unset\` and \`\_.omit\` functions" https://osv.dev/vulnerability/GHSA-xxjr-mmjv-4gpg
  - GHSA-866g-f22w-33x8 (low) in `` @ai-sdk/provider-utils@2.2.8 ``, indirect, fixed in `` 3.0.28 ``, advisory summary: "@ai-sdk/provider-utils has an Uncontrolled Resource Consumption issue" https://osv.dev/vulnerability/GHSA-866g-f22w-33x8
  - GHSA-rwvc-j5jr-mgvh (low) in `` ai@4.3.19 ``, indirect, fixed in `` 5.0.52 ``, advisory summary: "Vercel’s AI SDK's filetype whitelists can be bypassed when uploading files" https://osv.dev/vulnerability/GHSA-rwvc-j5jr-mgvh
  - GHSA-52f5-9888-hmc6 (low) in `` tmp@0.0.33 ``, indirect, fixed in `` 0.2.4 ``, advisory summary: "tmp allows arbitrary temporary file / directory write via symbolic link \`dir\` parameter" https://osv.dev/vulnerability/GHSA-52f5-9888-hmc6

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

- npm @browserbasehq/mcp-server-browserbase@2.1.1 secrets: BROWSERBASE_API_KEY, GEMINI_API_KEY

## Tools (0)

_none observed_