Skip to main content
Glama
kqlio67

Fast Browser MCP

by kqlio67
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

browser_cdp_send

Send raw Chrome DevTools Protocol commands directly with custom parameters, enabling low-level browser control and debugging outside prebuilt actions.

Instructions

UNIVERSAL RAW CDP (GOD MODE): Send any raw Chrome DevTools Protocol command directly with custom parameters (e.g. 'DOM.getBoxModel', 'CSS.enable', 'Memory.getDOMCounters', 'Tracing.start', 'Fetch.enable').

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
methodYesCDP method name (e.g. 'DOM.getBoxModel', 'Page.printToPDF')
paramsNoOptional parameters dictionary for the CDP command
timeoutNoCommand timeout in seconds
session_idNoOptional child target session ID (e.g. for cross-origin iframes)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.0
    • addedInput schema / properties / session_id
      Added value: +{
+  "description": "Optional child target session ID (e.g. for cross-origin iframes)",
+  "type": "string"
+}
  2. First observedv0.8.0

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only says 'send any raw CDP command directly' and 'GOD MODE', but it does not disclose that this is an advanced/powerful operation that could break the browser, lack validation, or have unexpected side effects. The 'raw' mention hints at risk but is not explicit enough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with a memorable 'GOD MODE' hook and concrete examples. It's front-loaded and gets the point across without wasted words, though it lacks a structured breakdown or warnings.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a raw, universal tool with no output schema and no annotations, the description is too sparse. It doesn't mention that the agent must know CDP method names, that results may be unstructured, or that misuse could destabilize the browser. More context is needed for safe and correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters (method, params, timeout, session_id) are documented in the schema. The description adds examples and emphasizes 'raw' and 'directly', but these are more about the tool's nature than parameter meaning, adding marginal value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sends raw CDP commands with custom parameters, giving concrete examples like 'DOM.getBoxModel'. This distinguishes it from specialized sibling tools (e.g., browser_navigate, browser_screenshot) by explicitly framing it as the universal raw access.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'GOD MODE' implies it's the ultimate fallback for anything not covered by other tools, but there is no explicit guidance on when to use it versus the specialized siblings, nor any exclusions or warnings. It's implied but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools