Skip to main content
Glama

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tasks
{
  "list": {},
  "cancel": {},
  "requests": {
    "tools": {
      "call": {}
    }
  }
}
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
fetchA

Fetch a URL and convert to clean markdown for LLM consumption.

Content conversion (automatic by Content-Type):

  • HTML → clean markdown (boilerplate removed, links preserved)

  • PDF → markdown with headings and table detection (requires pdf feature)

  • JSON/plain text → passthrough

  • SPA data auto-extracted (NEXT_DATA, NUXT, APOLLO_STATE, etc.)

Network features:

  • HTTP/2 multiplexing, HTTP/3 (QUIC) with 0-RTT

  • TLS 1.3, Brotli/Zstd/Gzip decompression

  • Realistic browser fingerprints (Chrome/Firefox/Safari)

  • Browser cookie injection (Brave/Chrome/Firefox/Safari)

Diff mode (diff: true):

  • Compares current content against the previous snapshot for this URL

  • Returns only the changed sections (token-efficient for monitoring tasks)

  • First fetch caches the page; subsequent fetches return semantic diffs

  • Unchanged content returns a 5-token confirmation instead of full body

Focus mode (focus: query):

  • Keeps only sections relevant to the query (BM25 scoring)

  • Replaces dropped sections with '[N sections omitted]' markers

  • Diff markers are always preserved regardless of relevance

Token budget (max_tokens: N):

  • Structure-aware truncation preserving headings, code, and tables

  • Priority: title > code/tables > headings (30% cap) > body > blockquotes

Returns: Markdown-converted body with timing info (or diff when diff: true).

fetch_batchA

Fetch multiple URLs in parallel with HTTP/2 multiplexing.

Uses connection pooling and multiplexing for maximum efficiency. All URLs are fetched concurrently.

Returns: Results for each URL with timing.

submitA

Submit a web form with smart field extraction.

Fetches a page, parses all forms, extracts hidden fields and CSRF tokens, merges user-provided fields, and submits via POST.

Use for: login forms, search forms, API interactions behind HTML pages.

Returns: Response body (markdown-converted) after form submission.

loginA

Auto-login to a website using 1Password credentials.

Detects login form, retrieves credentials from 1Password, fills and submits, handles MFA/2FA with TOTP. Returns the authenticated page content.

Requires: 1Password CLI (op) installed and authenticated.

Returns: Final page content after login (markdown-converted).

auth_lookupA

Look up credentials in 1Password for a URL.

Searches 1Password for credentials matching the URL/domain. Returns credential info (username, TOTP availability) without exposing password.

Returns: Credential info if found.

fingerprintA

Generate realistic browser fingerprints.

Creates browser profiles for Chrome, Firefox, or Safari. Includes User-Agent, Sec-CH-UA headers, Accept-Language, platform info.

Returns: Generated fingerprint profiles.

validateA

Run validation tests against real websites.

Tests: HTTP/2, HTTP/3, compression, fingerprinting, TLS 1.3, 1Password.

Returns: Validation results with timing.

benchmarkB

Benchmark fetching URLs with timing statistics.

Measures min/avg/max response times over multiple iterations.

Returns: Benchmark results with timing statistics.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 8 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: auth_lookup for credential lookup, benchmark for timing, fetch for single URL conversion, fetch_batch for parallel fetching, fingerprint for browser profiles, login for automated authentication, submit for form submission, and validate for testing. No two tools serve the same function, and descriptions provide ample detail to differentiate.

Naming Consistency4/5

Tool names use snake_case and are generally descriptive, but there is inconsistency between verb-based names (fetch, fetch_batch, submit, validate) and noun-based names (auth_lookup, benchmark, fingerprint, login). However, the naming is still predictable and readable, with fetch_batch clearly extending fetch.

Tool Count5/5

With 8 tools, the server covers all core web interaction tasks without being overwhelming. The count is appropriate for the domain of web scraping, automation, and testing, and each tool adds clear value.

Completeness4/5

The tool set covers a wide range of web interactions: fetching, batch processing, form submission, authentication, benchmarking, and validation. Minor gaps exist, such as explicit session management or cookie manipulation, but the core workflow is well-served, and agents can accomplish most tasks without missing critical operations.

Maintenance

ActivityActive
ResponsivenessWithin a week