Skip to main content
Glama

Search the directory

search_tools
Read-onlyIdempotent

Find listed tools, APIs, MCP servers, models and data providers for a job, graded ones first with grade, price, auth and status. Use it when a user needs a tool or wants options narrowed by grade, price or auth.

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_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWhat you need, in a few words: 'send email', 'web search', 'uk company data'
dpaNoOnly listings with a data processing agreement
authNoHow it authenticates; pat is a personal access token
certNoCertifications every result holds, comma-separated, e.g. SOC2,ISO27001
kindNoWhat sort of listing; platform hosts other labs' models, weights are open weights you run
x402NoPayable per call with USDC and no account
limitNoHow many graded listings to return (default 10)
whereNoWhere it runs
noCardNoOnly listings that need no payment card before the first call
offsetNoSkip this many graded listings, for the next page (the answer's nextOffset)
regionNoWhere data is processed, any of US, EU, UK, CA, APAC, self-hosted, comma-separated
pricingNoHow it charges; freemium has a free tier, byo-plan is your own plan with the vendor
unknownNoListings not yet researched for a requirement filter: exclude (default) or include, marked
weightsNo0 to 10 per category (reliability, schema, ergonomics, security, payments, maintenance, transparency), 1 if left out. Ranks by yourScore
categoryNoA category slug, e.g. search or browser (list at /categories/)
minGradeNoLowest grade to include, AA best to F worst; BB and up is agent-ready
minRatingNoAverage panel rating at least this
agentAloneNoOnly listings an agent can start using with no human (keyless, x402 or programmatic signup)
agentReadyNoOnly agent-ready listings (grade BB or better)
capabilityNoA capability id from list_capabilities, e.g. web.search
noTrainingNoOnly listings whose vendor says it doesn't train on customers' data
maxToolTokensNoOnly listings whose MCP tool definitions cost at most this many tokens
zeroRetentionNoOnly listings with zero retention on some plan
includeRegistryNoAlso search the official MCP registry (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / cert / description
      Previous value: -"Certifications every result holds, comma-separated: SOC2, ISO27001, ISO27701, ISO42001, HIPAA, PCI, FedRAMP, CSA, GDPR"New value: +"Certifications every result holds, comma-separated, e.g. SOC2,ISO27001"
    • changedInput schema / properties / weights / description
      Previous value: -"0 to 10 per category, 1 if left out: reliability, schema, ergonomics, security, payments, maintenance, transparency (open weights: capability, reach, risk, interface, upkeep). Ranks by yourScore"New value: +"0 to 10 per category (reliability, schema, ergonomics, security, payments, maintenance, transparency), 1 if left out. Ranks by yourScore"
  2. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Skip this many graded listings, for the next page (the answer's nextOffset)",
      +  "minimum": 0,
      +  "type": "integer"
      +}
  3. Changed12 schema fields changed
    • changedInput schema / properties / agentAlone / description
      Previous value: -"Only listings an agent can start using with no human (keyless, x402 or programmatic signup). Researched for the top listings; others don't match"New value: +"Only listings an agent can start using with no human (keyless, x402 or programmatic signup)"
    • changedInput schema / properties / auth / description
      Previous value: -"How it authenticates: none, an API key, OAuth, a mix, or a personal access token"New value: +"How it authenticates; pat is a personal access token"
    • changedInput schema / properties / category / description
      Previous value: -"A category slug from the directory, e.g. search, browser or database (list at /categories/)"New value: +"A category slug, e.g. search or browser (list at /categories/)"
    • changedInput schema / properties / dpa / description
      Previous value: -"Only listings that offer a data processing agreement"New value: +"Only listings with a data processing agreement"
    • changedInput schema / properties / kind / description
      Previous value: -"What sort of listing: an MCP server, an HTTP API, an SDK, a model, a model router, a model platform hosting other labs' models, open model weights you run yourself, an agent framework, an agent harness or a protocol"New value: +"What sort of listing; platform hosts other labs' models, weights are open weights you run"
    • addedInput schema / properties / maxToolTokens
      Added value: +{
      +  "description": "Only listings whose MCP tool definitions cost at most this many tokens",
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / minRating / description
      Previous value: -"Average panel rating at least this (the panel's desk reviews)"New value: +"Average panel rating at least this"
    • changedInput schema / properties / pricing / description
      Previous value: -"How it charges: free, a free tier, per use, your own plan with the vendor, or paid only"New value: +"How it charges; freemium has a free tier, byo-plan is your own plan with the vendor"
    • addedInput schema / properties / unknown
      Added value: +{
      +  "description": "Listings not yet researched for a requirement filter: exclude (default) or include, marked",
      +  "enum": [
      +    "exclude",
      +    "include"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / weights
      Added value: +{
      +  "additionalProperties": {
      +    "maximum": 10,
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "description": "0 to 10 per category, 1 if left out: reliability, schema, ergonomics, security, payments, maintenance, transparency (open weights: capability, reach, risk, interface, upkeep). Ranks by yourScore",
      +  "type": "object"
      +}
    • changedInput schema / properties / where / description
      Previous value: -"Where it runs: a hosted endpoint, a local server, both, a library or a spec"New value: +"Where it runs"
    • changedInput schema / properties / zeroRetention / description
      Previous value: -"Only listings that offer zero retention (on any plan, including enterprise)"New value: +"Only listings with zero retention on some plan"
  4. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real value by disclosing result ordering ('graded ones first with grade, price, auth and status'), which the agent cannot infer from annotations; it leaves pagination and the default registry search to the schema.

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 the verb and resource, then the usage condition. Every clause carries information and nothing is repeated from the schema or annotations.

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 a 24-parameter, zero-required filter tool with no output schema, the description covers purpose, trigger, ordering and returned fields, which is most of what an agent needs. Pagination behavior and the interaction between unknown and other filters are only implied, keeping it from a 5.

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% across 24 parameters, including per-enum descriptions, so the schema does the heavy lifting and the baseline is 3. The description adds only the framing of grade, price and auth as the narrowing axes, and does not elaborate on ranking via the weights object or the unknown-filter default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Find listed tools, APIs, MCP servers, models and data providers') and adds scope details: rank order and the fields returned (grade, price, auth, status). It does not explicitly distinguish itself from siblings like get_tool or compare_tools, so it falls short of a 5.

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?

'Use it when a user needs a tool or wants options narrowed by grade, price or auth' gives a clear triggering context tied to the tool's filter dimensions. There are no explicit exclusions or routing to alternatives such as get_tool for a single known listing, so it stops short of a 5.

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