Skip to main content
Glama

Search remote MCP servers

search_servers
Read-onlyIdempotent

Use when the user needs an MCP server for a task, or asks whether one exists, works today, or needs a key or sign-in. Do not use for general web search; for one server already known by name use get_server. Find remote MCP servers listed in the Official MCP Registry, with MCP Station's daily measurements. Turn the user's need into words (q) plus filters. Example: 'crypto market data, no API key, working' -> q='crypto market data', auth='none', reachable=true. Results are ordered by relevance first, then by published rank rules (measurements only, no paid placement). similar_to='' returns other working servers in the same categories with the same authentication.

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_servers"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords, max 200 characters
authNoAuthentication at the last check
riskNoDeclared by the server's tool hints
limitNoAsk only for as many results as needed (default 10)
offsetNo
categoryNoCategory ID, e.g. finance.crypto (see list_categories)
reachableNotrue = answered at the last check
transportNo
capabilityNoDeclared at initialize
similar_toNoRegistry name of a server to find alternatives for
min_success_7dNoDaily check success over 7 days

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / limit / description
      Added value: +"Ask only for as many results as needed (default 10)"
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds meaningful context beyond them: result ordering (relevance then published rank rules, 'measurements only, no paid placement') and that data comes from daily measurements, which tells the agent about freshness and ranking bias. It doesn't state pagination behavior or total counts, keeping it short of a 5.

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?

Front-loaded with the usage trigger and exclusion, then the data source, then an example. Dense but every sentence carries information. The example plus similar_to note add length, but both are operational guidance rather than filler.

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?

For an 11-parameter search tool with no output schema, the description covers intent, filtering strategy, ordering, and one alternative-lookup mode. Missing details an agent might want (what a result record contains, how to paginate through a large result set via offset) are the main gaps; annotations and the 82% schema coverage cover the rest.

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

Parameters4/5

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

Schema coverage is 82%, so the schema carries most parameter documentation and baseline would be 3. The description goes beyond it by showing how to compose q with filters ('crypto market data, no API key, working' -> auth='none', reachable=true) and by explaining similar_to semantics ('other working servers in the same categories with the same authentication') and result ordering related to limit/offset usage.

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?

States a specific verb+resource ('Find remote MCP servers listed in the Official MCP Registry') and adds the measurement data source. It explicitly contrasts with siblings: 'Do not use for general web search; for one server already known by name use get_server', making it distinguishable from search_tools, get_server, and list_categories.

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?

Gives explicit when-to-use triggers ('user needs an MCP server for a task, or asks whether one exists, works today, or needs a key or sign-in'), explicit when-not ('general web search'), and names the alternative for the known-name case (get_server). A worked example maps a natural-language need to parameter values.

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