Skip to main content
Glama
saucelabs

Sauce Labs MCP Server

Official
by saucelabs

filter_har_data

Filter HAR data from Sauce Labs jobs with in-memory caching. Downloads and caches HAR data on first call, enabling instant filtering on subsequent queries by category, domain, resource type, or status code.

Instructions

    Filters HAR data with in-memory caching for efficient multiple queries.

    **Key difference from get_network_har_file**: This method caches the full HAR
    data in memory after the first call, making subsequent filtering operations
    instant without re-downloading from Sauce Labs.

    First call for a job_id downloads and caches the full HAR data.
    Subsequent calls filter the cached data instantly.

    :param job_id: The Sauce Labs Job ID
    :param filter_category: Predefined categories ("analytics", "social", "api", etc.)
    :param custom_domains: Domain patterns to include
    :param resource_types: Resource types to include (Script, XHR, Image, etc.)
    :param status_codes: HTTP status codes to include
    :return: Filtered HAR data with cache metadata

    Examples:
    - filter_har_data(job_id, filter_category="analytics") # First call: downloads + caches
    - filter_har_data(job_id, filter_category="social")    # Subsequent: instant filtering
    - filter_har_data(job_id, custom_domains=["facebook"]) # Also instant
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
job_idYes
filter_categoryNo
custom_domainsNo
resource_typesNo
status_codesNo
Behavior4/5

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

No annotations provided; description discloses caching behavior, first vs subsequent calls, and key difference. Lacks details on side effects or memory limits but adequate for a read-like filter.

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?

Well-structured with summary, key difference, behavior, parameters, and examples. Slightly verbose in repeating caching behavior, but every section adds value.

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

Completeness4/5

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

Covers purpose, usage, parameters, and caching behavior. Lacks return structure details, but examples and parameter descriptions provide enough context for correct invocation.

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

Parameters5/5

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

Schema coverage is 0%; description adds meaning by listing parameters with brief explanations, predefined categories, and examples, compensating fully for missing schema descriptions.

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?

Clearly states it filters HAR data with in-memory caching, distinguishes from sibling get_network_har_file by highlighting caching behavior.

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

Usage Guidelines5/5

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

Explicitly describes when to use (for multiple queries) vs when not (first call downloads), and names the alternative tool. Examples reinforce usage.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/saucelabs/sauce-api-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server