compat_compare

Compare browser compatibility across multiple web platform features side by side. Useful for choosing between alternative APIs or understanding support differences. Args: - features (string[]): 2-5 BCD feature identifiers to compare (e.g., [

Server Web Compat shuji-bonji/web-compat-mcp
Category Read
Risk class Low
Parameters 00 required

What compat_compare does on Web Compat

AI agents call compat_compare to retrieve information from Web Compat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why compat_compare needs a policy

This tool retrieves and queries browser compatibility data for comparison purposes. It has no side effects—it does not create, modify, delete, or execute anything. It purely reads compatibility information to help developers make informed decisions about API choices. This is a straightforward Read category tool.

From the tool's definition Tool description states it 'Compare[s] browser compatibility across multiple web platform features side by side' and is 'Useful for choosing between alternative APIs or understanding support differences.' The arguments accept feature identifiers for…

Questions about compat_compare

What does the compat_compare tool do? +

Compare browser compatibility across multiple web platform features side by side. Useful for choosing between alternative APIs or understanding support differences. Args: - features (string[]): 2-5 BCD feature identifiers to compare (e.g., [. It is categorised as a Read tool in the Web Compat MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on compat_compare? +

Register the Web Compat MCP server in PolicyLayer and add a rule for compat_compare: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Web Compat. Nothing to install.

What risk level is compat_compare? +

compat_compare is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit compat_compare? +

Yes. Add a rate_limit block to the compat_compare rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block compat_compare completely? +

Set action: deny in the PolicyLayer policy for compat_compare. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides compat_compare? +

compat_compare is provided by the Web Compat MCP server (shuji-bonji/web-compat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.