Skip to main content
Glama

Find SaaS websites

search_sites
Read-onlyIdempotent

Find real SaaS marketing websites to use as design references. Filter by category, page section (e.g. sites with a captured pricing page), visual style, tech stack, font or brand colour, and/or a free-text query (product name or industry). Returns each site's website URL, category, style, stack, colour palette, fonts, captured sections, and a link to its screenshots.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_sites"
  }
}

Input Schema

NameRequiredDescriptionDefault
fontNoFont family used on the site, e.g. "Inter".
colorNoHex colour; matches sites with a close colour in their palette, e.g. "#5e6ad2".
limitNoMaximum number of sites to return, 1–20 (default 8).
queryNoFree text, e.g. "developer tools", "linear", "video editing".
stackNoTech stack of the marketing site, e.g. "Next.js", "Webflow", "Framer".
styleNoVisual style: "dark", "light", "colorful" or "minimal".
sectionNoOnly sites with this section captured, e.g. "pricing", "heroes", "faq", "footers".
categoryNoProduct category, e.g. "AI", "Engineering & Infrastructure". See list_filters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of sites to return, 1–20 (default 8)."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered; the description adds useful behavioral detail beyond that, notably that the colour filter is fuzzy ("matches sites with a close colour") and that section filtering means only sites with that section captured. It doesn't mention result ordering or behavior on zero matches, which is the remaining gap.

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

Conciseness5/5

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

Two sentences, front-loaded with purpose, then filters, then return shape. Every clause carries information and there is no filler or repetition of the title.

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?

With no output schema, the description usefully enumerates the returned fields (URL, category, style, stack, palette, fonts, sections, screenshot link), so the agent knows what it gets back. Minor omissions are result ordering and what happens when filters match nothing, but nothing essential to calling the tool correctly is missing.

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 coverage is 100%, so the schema already documents all eight parameters with examples; baseline 3 applies. The description adds modest value by reframing query as "product name or industry" and section as "sites with a captured pricing page", but contributes no format or matching semantics beyond what the schema states.

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?

A specific verb ("Find") plus a precisely scoped resource ("real SaaS marketing websites ... as design references"), which also distinguishes it from the singular sibling get_site. The second sentence enumerates the filterable facets, so an agent knows exactly what kind of lookup this is.

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

Usage Guidelines4/5

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

Usage context is clear: discovery of design references filtered by category, section, style, stack, font, colour or free text, and it points to list_filters for the category vocabulary. It stops short of stating when to prefer get_site or list_site_links instead, so no explicit alternatives or exclusions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources