Skip to main content
Glama

Search businesses (start here)

search_businesses
Read-onlyIdempotent

Use when the user asks how much revenue, MRR or ARR an AI agent, AI startup or AI tool makes, or wants real examples of AI businesses in a niche (support, coding, voice, sales, automation...). Returns AI-agent businesses with sourced, dated revenue (start here). Example: {"query":"coding","limit":3} -> 3 coding agents with their sourced revenue. Use it to find or filter businesses (keyword, category, tier, verified_only) when you have no slug; for a pure top-N use leaderboard, for one full record get_business. Each brief: slug, name, category, tier, one_liner, annualized_revenue_usd, basis, confidence, verification_label ("reported, not payment-verified" unless processor-verified), url_profile; + total + next page (offset/cursor, limit max 50). Empty query = all, highest revenue first. Cost: free (100 calls/day without a key).

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_businesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoFunding-based, not size-based: venture = raised outside venture money (even if small), indie = bootstrapped/founder-funded, experiment = agent-run or research project.
limitNoResults per page. Default 10, max 50.
queryNoKeyword, e.g. "coding", "voice", "sales". Empty = all businesses.
cursorNoOpaque page token: page.next_cursor from the previous call with the same query and filters.
offsetNoSkip this many matches (page start). Default 0. Use page.next_offset from the previous call.
categoryNoCategory slug, e.g. coding-agents, customer-support (see list_categories).
verified_onlyNoKeep only businesses whose headline figure is payment-processor verified (headline_verification not null).

Output Schema

NameRequiredDescriptionDefault
pageNoPagination: call again with offset = next_offset (or cursor = next_cursor) while has_more.
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"Keyword, e.g. \"support\", \"coding\", \"voice\". Empty = all businesses."New value: +"Keyword, e.g. \"coding\", \"voice\", \"sales\". Empty = all businesses."
  2. Changed6 schema fields changed
    • addedInput schema / properties / category / description
      Added value: +"Category slug, e.g. coding-agents, customer-support (see list_categories)."
    • addedInput schema / properties / cursor
      Added value: +{
      +  "description": "Opaque page token: page.next_cursor from the previous call with the same query and filters.",
      +  "type": "string"
      +}
    • addedInput schema / properties / limit / description
      Added value: +"Results per page. Default 10, max 50."
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Skip this many matches (page start). Default 0. Use page.next_offset from the previous call.",
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedInput schema / properties / query / description
      Added value: +"Keyword, e.g. \"support\", \"coding\", \"voice\". Empty = all businesses."
    • addedOutput schema / properties / page
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Pagination: call again with offset = next_offset (or cursor = next_cursor) while has_more.",
      +  "properties": {
      +    "has_more": {
      +      "type": "boolean"
      +    },
      +    "limit": {
      +      "type": "number"
      +    },
      +    "next_cursor": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "next_offset": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "offset": {
      +      "type": "number"
      +    },
      +    "returned": {
      +      "type": "number"
      +    },
      +    "total": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "total",
      +    "returned",
      +    "offset",
      +    "limit",
      +    "has_more",
      +    "next_offset",
      +    "next_cursor"
      +  ],
      +  "type": "object"
      +}
  3. Changed5 schema fields changed
    • addedOutput schema / properties / result / items / properties / referral
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / result / items / properties / signup_go_url
      Added value: +{
      +  "description": "Same link via mrrledger.com/go/<slug> (counts the click, then 302)",
      +  "type": "string"
      +}
    • addedOutput schema / properties / result / items / properties / signup_url
      Added value: +{
      +  "description": "Referral link (only on businesses with one). Always shown with signup_url_disclosure; never affects figures, ranking, sorting or verification.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / result / items / properties / signup_url_disclosure
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / result / items / properties / signup_url_label
      Added value: +{
      +  "type": "string"
      +}
  4. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, yet the description still adds real value: default sort ('highest revenue first' when query empty), empty-query semantics, pagination mechanics (offset/cursor, limit max 50), the meaning of the verification_label, and a rate/cost limit (100 calls/day without a key). These are traits not encoded in the annotations. The only gap is what a key unlocks or how auth is supplied.

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 user intent, then the return payload, then sibling alternatives, then pagination/cost. Every sentence carries information, though the parenthetical stacking ('(

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

Completeness5/5

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

For a filtered search with an output schema present, the description supplies everything an agent needs: trigger, alternatives, empty-query semantics, sort order, pagination contract, field list, verification semantics, and rate limit. Even though the output schema exists, listing the brief's fields is a helpful redundancy rather than a gap.

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 100%, so the baseline is 3; the description goes beyond the schema by specifying the empty-query behavior and default ordering, the max page size, and that cursor/offset must be reused with the same query and filters. The example call fixes the query/limit shape concretely. It does not add much on tier or category beyond what the schema already defines.

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 concrete verb and resource (search AI-agent businesses) and immediately frames the user intent it serves: revenue/MRR/ARR figures and niche examples. It explicitly carves out its territory from siblings ('for a pure top-N use leaderboard, for one full record get_business'), so an agent can select it without opening another schema.

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 an explicit trigger ('use when the user asks how much revenue... or wants real examples of AI businesses in a niche') plus the precise condition for choosing it ('when you have no slug') and names the two alternatives with their own selecting conditions. This is close to a routing decision table in prose.

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