Developer · MCP Server

Securing the Playwright MCP server

The Playwright MCP server gives an agent browser navigation, page reading, and interaction. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.

What the server hands your agent

Driving a real browser: navigating to URLs, reading rendered page content, filling forms, and clicking.

Why it is worth governing

Every page an agent visits is content someone else controls. This is the widest untrusted input surface of any MCP server.
If the browser profile carries a logged-in session, the agent acts as the authenticated user on any site it reaches.
Form submission and clicking are real actions with real effects, not a read.

Tag what the tools actually do

Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for Playwright:

Tool pattern	Tags	Why
mcp__playwright__navigate	untrusted_content	page content is attacker-controlled
mcp__playwright__snapshot	untrusted_content	rendered text enters context verbatim
mcp__playwright__click	critical_action	clicks act in an authenticated session
mcp__playwright__fill	critical_action	form submission is an external action

Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.

The policy

Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.

settings:
  tool_tags:
    enabled: true
    mode: observe            # switch to enforce once the log looks right
    tags:
      "mcp__playwright__*navigate*": [untrusted_content]
      "mcp__playwright__*snapshot*": [untrusted_content]
      "mcp__playwright__*click*": [critical_action]
      "mcp__playwright__*fill*": [critical_action]
    rules:
      - "untrusted_content then critical_action -> block"

Putting Playwright behind the gateway

You do not change the Playwright server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:

prismor mcp-gateway install    # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall  # restores the original, backup kept

Your agent sees the same Playwright tools, namespaced as mcp__playwright__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.

Frequently asked questions

Is the Playwright MCP server safe to give an AI agent?

It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine Playwright access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.

Does Prismor replace the Playwright MCP server?

No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.

Will this block work my team actually needs to do?

Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.

What about tool results, not just tool calls?

Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.

One gateway for every MCP server

Playwright is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.

Install Prismor How MCP security works

Other developer servers

GitHub

GitLab FIFilesystem

Sentry All servers

Playwright is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The Playwright MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.