# browser-tools

> browser-tools is a community-maintained MCP server from AgentDesk. Anomity scores its risk at 40 out of 100 (medium).

- **Canonical URL:** https://catalog.anomity.ai/mcp/browser-tools
- **Kind:** MCP server
- **Publisher:** AgentDesk
- **Trust level:** community
- **Risk score:** 40/100 (medium)
- **Last updated:** 2026-11-01
- **JSON:** https://catalog.anomity.ai/api/entries/mcp/browser-tools

## Why it scored 40

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Established community project | -10 | trust offset |  |

Clamped result: **40/100**, band **medium**.

## Capabilities

| Capability | Name | Security implication |
| --- | --- | --- |
| `browser:control` | Browser control | Drives a browser session. Combined with credential access can impersonate the user on web services. |
| `network:outbound` | Outbound network | Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access. |

## Related MCP servers

- [browserbase](https://catalog.anomity.ai/mcp/browserbase) — risk 75 (high)
- [browserbase-server](https://catalog.anomity.ai/mcp/browserbase-server) — risk 75 (high)
- [firecrawl](https://catalog.anomity.ai/mcp/firecrawl) — risk 75 (high)
- [executeautomation-playwright](https://catalog.anomity.ai/mcp/executeautomation-playwright) — risk 50 (medium)
- [brightdata](https://catalog.anomity.ai/mcp/brightdata) — risk 45 (medium)
- [browserstack](https://catalog.anomity.ai/mcp/browserstack) — risk 45 (medium)

---

Source: Anomity Security Database (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json