Skip to main content
Glama
mixophrygian

Browser History Analysis MCP

by mixophrygian
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
check_browser_statusA

Step 1: Check which browsers are available and which are locked. This is the first step in the workflow - run this to see if you need to close any browsers.

Returns a dictionary with:
- status: "ready", "browser_locked", or "error"
- error_message: Clear error message if there's an issue
- user_action_required: True if user needs to close browsers
- recommended_action: Specific instructions for the user
- available_browsers: List of detected browsers
- active_browsers: List of browsers that are currently running

IMPORTANT: If status is "browser_locked", you MUST tell the user to close the specified browser(s).
get_browser_historyA

Step 2: Get raw browser history data without analysis. This is the fastest way to retrieve browser history and should be used before any analysis.

Args:
    time_period_in_days: Number of days of history to retrieve (default: 7)
    browser_type: Browser type ('firefox', 'chrome', 'safari', or None for auto-detect)
    all_browsers: If True, get history from all available browsers (default: True)

Returns:
    Either a list of history entries or a dictionary with partial results and browser status
analyze_browser_historyB

Step 3: Analyze browser history with different levels of detail.

This is the main analysis tool that consolidates all analysis options.

Args:
    time_period_in_days: Number of days of history to analyze (default: 7)
    analysis_type: Type of analysis to perform:
        - "quick_summary": Basic stats only (fastest)
        - "basic": Domain analysis and categorization (not yet implemented)
        - "comprehensive": Full analysis with sessions and insights (default)
    fast_mode: If True, limits analysis for faster processing (default: True)
search_browser_historyB

Search browser history for specific queries. Use this after getting history data.

Args:
    query: Search term to look for in URLs and titles
suggest_categoriesA

Get uncategorized URLs for custom categorization. Use this after running analysis.

diagnose_safari_supportC

Diagnose Safari support and accessibility. Useful for debugging Safari integration.

health_checkA

Simple health check that returns immediately to test if the MCP server is working.

Prompts

Interactive templates invoked by user choice

NameDescription
productivity_analysisCreates a comprehensive productivity analysis prompt
learning_analysisCreates a deep learning pattern analysis prompt
research_topic_extractionExtract and summarize research topics from browsing history
generate_insights_reportGenerate a personalized insights report based on browsing patterns
export_visualizationExport your browsing data as interactive visualizations
compare_time_periodsCompare your browsing habits across different time periods

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 7 tools

Disambiguation4/5

Most tools have distinct purposes: check_browser_status verifies browser availability, get_browser_history retrieves raw data, analyze_browser_history performs analysis, search_browser_history searches, and suggest_categories handles categorization. However, analyze_browser_history's 'comprehensive' mode might overlap with other tools like suggest_categories, creating minor ambiguity in advanced workflows.

Naming Consistency5/5

All tool names follow a consistent snake_case pattern with clear verb_noun combinations (e.g., check_browser_status, get_browser_history, analyze_browser_history). This predictability makes it easy for agents to understand and select tools without confusion.

Tool Count5/5

With 7 tools, the server is well-scoped for browser history analysis, covering key steps from checking browser status to retrieving, analyzing, searching, and categorizing history. Each tool serves a specific role without unnecessary bloat or gaps in the workflow.

Completeness4/5

The toolset covers a complete workflow: status check, data retrieval, analysis, search, and categorization. A minor gap exists as analyze_browser_history's 'basic' mode is noted as 'not yet implemented,' which could limit some analysis options, but core operations are well-covered.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources