Skip to main content
Glama

Search companies (billed per row)

search_companies
Read-only

Return companies matching an ICP. BILLABLE — about $0.0067 per returned row (0 rows costs $0) (Tier 0 list price; your account may pay a different rate — call get_balance for your real prices, and read cost.amount_charged in every response for what was actually spent). Run count_companies first. Note that headcount_range is a snapshot taken when the record was indexed and can lag the company's current size; the filter itself is applied at query time.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoData mode. "database" = cached, sub-second, cheaper, free counts, core filters only. "realtime" = live LinkedIn lookup, 5–60s, pricier, supports every filter. "auto" (default) tries database first and only escalates to realtime if a filter you passed is unsupported there — an escalation is reported in the response. Pick "database" explicitly when freshness is not critical and cost matters more than freshness.
limitNoAlias for limit_by.
offsetNoAlias for offset_by.
compactNoDefault true: return a small per-company summary (including the Generect `id`, which every later step accepts). Set false for the full raw record (~80 fields) — only worth it when you specifically need skills, education or other deep fields.
keywordsNoFree-text keywords across name/description/specialties — realtime only: using it forces the pricier live mode.
limit_byNoRows to return this call (1–100, default 25). You are billed per returned row, so this number IS the price of the call.
locationsNoHQ locations — cities, states or countries.
offset_byNoRows to skip (pagination).
headcountsNoSize buckets. Allowed ONLY: "1-10","11-50","51-200","201-500","501-1000","1001-5000","5001-10000","10 000+".
industriesNoCompany industries. Must match Generect industry names exactly (e.g. "Software Development"); unknown names are rejected with HTTP 400.
timeout_msNoRequest timeout in milliseconds.
exclude_idsNoExclude companies by LinkedIn id/URN.
technologiesNoTechnologies the company uses — realtime only: using it forces the pricier live mode.
company_namesNoRestrict to specific company names — realtime only: using it forces the pricier live mode.
company_typesNoCompany types: "Public Company","Privately Held","Non Profit","Government Agency","Educational", …
revenues_rangeNoAnnual revenue range, single object {min,max} — realtime only: using it forces the pricier live mode.
sub_industriesNoExpand each selected industry to its sub-industries as well (broadens the match).
exclude_domainsNoExclude companies by domain (e.g. existing customers).
linkedins_linksNoSpecific LinkedIn company URLs — realtime only: using it forces the pricier live mode.
headcount_growthNoHeadcount growth in percent — realtime only: using it forces the pricier live mode.
num_of_followersNoLinkedIn follower buckets: "1-50","51-100","101-1000","1001-5000","5001+" — realtime only: using it forces the pricier live mode.
confirm_spend_usdNoExplicit approval for an unusually large charge. Calls whose worst case exceeds $5 are refused unless this is set to at least the amount the tool reports. Only set it after the user has agreed to that number.
exclude_locationsNoHQ locations to exclude.
get_max_companiesNoDEPRECATED — accepted but ignored. Always on now: search responses include results_count without asking.
exclude_industriesNoIndustries to exclude.
hiring_on_linkedinNoOnly companies actively hiring — realtime only: using it forces the pricier live mode.
fallback_from_leadsNoDEPRECATED — accepted but ignored. Removed. It fabricated lead-derived name aggregates and cost an extra billable query.
department_headcountNoDepartment size, e.g. {"name":"engineering","min":10,"max":100} — realtime only: using it forces the pricier live mode.
allow_unlisted_valuesNoEscape hatch for the local vocabulary check — see the lead-side field of the same name.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixNo
costNo
modeNo
noteNo
leadsNo
statusNo
returnedNo
companiesNo
test_modeNo
spend_guardNo
results_countNo
next_page_argsNo
requested_rowsNo
escalation_noteNo
test_mode_noticeNo
vocabulary_warningsNo
blocked_by_vocabularyNo
deprecated_params_ignoredNo
escalated_to_realtime_becauseNo
api_returned_more_than_requestedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / allow_unlisted_values
      Added value: +{
      +  "description": "Escape hatch for the local vocabulary check — see the lead-side field of the same name.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / confirm_spend_usd
      Added value: +{
      +  "description": "Explicit approval for an unusually large charge. Calls whose worst case exceeds $5 are refused unless this is set to at least the amount the tool reports. Only set it after the user has agreed to that number.",
      +  "type": "number"
      +}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "api_returned_more_than_requested": {
      +      "type": "number"
      +    },
      +    "blocked_by_vocabulary": {
      +      "$ref": "#/properties/vocabulary_warnings"
      +    },
      +    "companies": {
      +      "type": "array"
      +    },
      +    "cost": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "amount_charged_usd": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "billed": {
      +          "type": "string"
      +        },
      +        "note": {
      +          "type": "string"
      +        },
      +        "operation": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "deprecated_params_ignored": {
      +      "additionalProperties": {
      +        "type": "string"
      +      },
      +      "type": "object"
      +    },
      +    "escalated_to_realtime_because": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "escalation_note": {
      +      "type": "string"
      +    },
      +    "fix": {
      +      "type": "string"
      +    },
      +    "leads": {
      +      "type": "array"
      +    },
      +    "mode": {
      +      "type": "string"
      +    },
      +    "next_page_args": {},
      +    "note": {
      +      "type": "string"
      +    },
      +    "requested_rows": {
      +      "type": "number"
      +    },
      +    "results_count": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "returned": {
      +      "type": "number"
      +    },
      +    "spend_guard": {},
      +    "status": {
      +      "type": "string"
      +    },
      +    "test_mode": {
      +      "type": "boolean"
      +    },
      +    "test_mode_notice": {
      +      "type": "string"
      +    },
      +    "vocabulary_warnings": {
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed29 schema fields changed
    • changedInput schema / properties / compact / description
      Previous value: -"Default true: 6-field summary per company. Set false for the full raw object."New value: +"Default true: return a small per-company summary (including the Generect `id`, which every later step accepts). Set false for the full raw record (~80 fields) — only worth it when you specifically need skills, education or other deep fields."
    • changedInput schema / properties / company_names / description
      Previous value: -"Restrict to specific company names."New value: +"Restrict to specific company names — realtime only: using it forces the pricier live mode."
    • changedInput schema / properties / company_types / description
      Previous value: -"Company types. Allowed values: \"Public Company\", \"Educational\", \"Self Employed\", \"Government Agency\", \"Non Profit\", \"Self Owned\", \"Privately Held\", \"Partnership\"."New value: +"Company types: \"Public Company\",\"Privately Held\",\"Non Profit\",\"Government Agency\",\"Educational\", …"
    • addedInput schema / properties / department_headcount
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Department size, e.g. {\"name\":\"engineering\",\"min\":10,\"max\":100} — realtime only: using it forces the pricier live mode.",
      +  "properties": {
      +    "max": {
      +      "type": "number"
      +    },
      +    "min": {
      +      "type": "number"
      +    },
      +    "name": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "name"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / properties / exclude_domains
      Added value: +{
      +  "description": "Exclude companies by domain (e.g. existing customers).",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / exclude_ids
      Added value: +{
      +  "description": "Exclude companies by LinkedIn id/URN.",
      +  "items": {
      +    "type": [
      +      "string",
      +      "number"
      +    ]
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / exclude_industries / description
      Previous value: -"Industries to exclude (same taxonomy as industries)."New value: +"Industries to exclude."
    • changedInput schema / properties / exclude_locations / description
      Previous value: -"Locations to exclude."New value: +"HQ locations to exclude."
    • changedInput schema / properties / fallback_from_leads / description
      Previous value: -"Default FALSE. If true and the company search is empty, derive candidate company NAMES by aggregating a keyword lead search. These are lead-derived name counts (source:\"leads_derived\"), NOT real company records, and cost an extra query."New value: +"DEPRECATED — accepted but ignored. Removed. It fabricated lead-derived name aggregates and cost an extra billable query."
    • removedInput schema / properties / fallback_from_leads / type
      Removed value: -"boolean"
    • changedInput schema / properties / get_max_companies / description
      Previous value: -"Also report the total number of matching companies."New value: +"DEPRECATED — accepted but ignored. Always on now: search responses include results_count without asking."
    • removedInput schema / properties / get_max_companies / type
      Removed value: -"boolean"
    • addedInput schema / properties / headcount_growth
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Headcount growth in percent — realtime only: using it forces the pricier live mode.",
      +  "properties": {
      +    "max": {
      +      "type": "number"
      +    },
      +    "min": {
      +      "type": "number"
      +    }
      +  },
      +  "type": "object"
      +}
    • changedInput schema / properties / headcounts / description
      Previous value: -"Employee headcount buckets. Allowed ONLY: \"1-10\",\"11-50\",\"51-200\",\"201-500\",\"501-1000\",\"1001-5000\",\"5001-10000\",\"10 000+\" (note the space in \"10 000+\")."New value: +"Size buckets. Allowed ONLY: \"1-10\",\"11-50\",\"51-200\",\"201-500\",\"501-1000\",\"1001-5000\",\"5001-10000\",\"10 000+\"."
    • addedInput schema / properties / hiring_on_linkedin
      Added value: +{
      +  "description": "Only companies actively hiring — realtime only: using it forces the pricier live mode.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / industries / description
      Previous value: -"Industries. Must match Generect industry names exactly (e.g. \"Software Development\", \"Financial Services\"). Names are hierarchical. Invalid names are rejected (HTTP 400)."New value: +"Company industries. Must match Generect industry names exactly (e.g. \"Software Development\"); unknown names are rejected with HTTP 400."
    • changedInput schema / properties / keywords / description
      Previous value: -"Free-text keywords (Boolean phrases allowed)."New value: +"Free-text keywords across name/description/specialties — realtime only: using it forces the pricier live mode."
    • changedInput schema / properties / limit / description
      Previous value: -"Alias for limit_by"New value: +"Alias for limit_by."
    • changedInput schema / properties / limit_by / description
      Previous value: -"Companies to return (1–100, default 25)."New value: +"Rows to return this call (1–100, default 25). You are billed per returned row, so this number IS the price of the call."
    • addedInput schema / properties / linkedins_links
      Added value: +{
      +  "description": "Specific LinkedIn company URLs — realtime only: using it forces the pricier live mode.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / locations / description
      Previous value: -"Locations (countries/regions, e.g. [\"United States\"])."New value: +"HQ locations — cities, states or countries."
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "Data mode. \"database\" = cached, sub-second, cheaper, free counts, core filters only. \"realtime\" = live LinkedIn lookup, 5–60s, pricier, supports every filter. \"auto\" (default) tries database first and only escalates to realtime if a filter you passed is unsupported there — an escalation is reported in the response. Pick \"database\" explicitly when freshness is not critical and cost matters more than freshness.",
      +  "enum": [
      +    "auto",
      +    "database",
      +    "realtime"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / num_of_followers / description
      Previous value: -"LinkedIn follower-count buckets."New value: +"LinkedIn follower buckets: \"1-50\",\"51-100\",\"101-1000\",\"1001-5000\",\"5001+\" — realtime only: using it forces the pricier live mode."
    • changedInput schema / properties / offset / description
      Previous value: -"Alias for offset_by"New value: +"Alias for offset_by."
    • changedInput schema / properties / offset_by / description
      Previous value: -"Offset for pagination."New value: +"Rows to skip (pagination)."
    • changedInput schema / properties / revenues_range / description
      Previous value: -"Annual revenue range in millions USD, e.g. {\"min\":0.5,\"max\":1001}. Single object, NOT an array."New value: +"Annual revenue range, single object {min,max} — realtime only: using it forces the pricier live mode."
    • addedInput schema / properties / sub_industries
      Added value: +{
      +  "description": "Expand each selected industry to its sub-industries as well (broadens the match).",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / technologies / description
      Previous value: -"Technologies the company uses (BuiltWith taxonomy)."New value: +"Technologies the company uses — realtime only: using it forces the pricier live mode."
    • changedInput schema / properties / timeout_ms / description
      Previous value: -"Request timeout in milliseconds"New value: +"Request timeout in milliseconds."
  3. Changed15 schema fields changed
    • changedInput schema / properties / compact / description
      Previous value: -"Return compact summary instead of full JSON"New value: +"Default true: 6-field summary per company. Set false for the full raw object."
    • addedInput schema / properties / company_names
      Added value: +{
      +  "description": "Restrict to specific company names.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / exclude_industries
      Added value: +{
      +  "description": "Industries to exclude (same taxonomy as industries).",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / exclude_locations
      Added value: +{
      +  "description": "Locations to exclude.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / fallback_from_leads / description
      Previous value: -"If no companies, derive from leads by keywords"New value: +"Default FALSE. If true and the company search is empty, derive candidate company NAMES by aggregating a keyword lead search. These are lead-derived name counts (source:\"leads_derived\"), NOT real company records, and cost an extra query."
    • changedInput schema / properties / get_max_companies / description
      Previous value: -"Get maximum companies"New value: +"Also report the total number of matching companies."
    • changedInput schema / properties / headcounts / description
      Previous value: -"Employee headcount ranges. Allowed values ONLY: \"1\", \"2-10\", \"11-50\", \"51-200\", \"201-500\", \"501-1000\", \"1001-5000\", \"5001-10000\", \"10000+\". Note the largest bucket is \"10000+\" (NOT \"10001+\")."New value: +"Employee headcount buckets. Allowed ONLY: \"1-10\",\"11-50\",\"51-200\",\"201-500\",\"501-1000\",\"1001-5000\",\"5001-10000\",\"10 000+\" (note the space in \"10 000+\")."
    • changedInput schema / properties / industries / description
      Previous value: -"Industries. Must match Generect industry names exactly (e.g. \"Software Development\", \"Financial Services\"). Invalid names are rejected by the API."New value: +"Industries. Must match Generect industry names exactly (e.g. \"Software Development\", \"Financial Services\"). Names are hierarchical. Invalid names are rejected (HTTP 400)."
    • changedInput schema / properties / keywords / description
      Previous value: -"Keywords"New value: +"Free-text keywords (Boolean phrases allowed)."
    • changedInput schema / properties / limit_by / description
      Previous value: -"Number of results to return"New value: +"Companies to return (1–100, default 25)."
    • changedInput schema / properties / locations / description
      Previous value: -"Locations (countries, e.g. [\"United States\"])"New value: +"Locations (countries/regions, e.g. [\"United States\"])."
    • addedInput schema / properties / num_of_followers
      Added value: +{
      +  "description": "LinkedIn follower-count buckets.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / offset_by / description
      Previous value: -"Offset for pagination"New value: +"Offset for pagination."
    • addedInput schema / properties / revenues_range
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Annual revenue range in millions USD, e.g. {\"min\":0.5,\"max\":1001}. Single object, NOT an array.",
      +  "properties": {
      +    "max": {
      +      "type": "number"
      +    },
      +    "min": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "min",
      +    "max"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / properties / technologies
      Added value: +{
      +  "description": "Technologies the company uses (BuiltWith taxonomy).",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  4. Changed6 schema fields changed
    • changedInput schema / properties / company_types / description
      Previous value: -"Company types"New value: +"Company types. Allowed values: \"Public Company\", \"Educational\", \"Self Employed\", \"Government Agency\", \"Non Profit\", \"Self Owned\", \"Privately Held\", \"Partnership\"."
    • changedInput schema / properties / headcounts / description
      Previous value: -"Headcount ranges"New value: +"Employee headcount ranges. Allowed values ONLY: \"1\", \"2-10\", \"11-50\", \"51-200\", \"201-500\", \"501-1000\", \"1001-5000\", \"5001-10000\", \"10000+\". Note the largest bucket is \"10000+\" (NOT \"10001+\")."
    • changedInput schema / properties / industries / description
      Previous value: -"Industries"New value: +"Industries. Must match Generect industry names exactly (e.g. \"Software Development\", \"Financial Services\"). Invalid names are rejected by the API."
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Alias for limit_by",
      +  "type": "number"
      +}
    • changedInput schema / properties / locations / description
      Previous value: -"Locations (Countries, e.g \"United States\")"New value: +"Locations (countries, e.g. [\"United States\"])"
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Alias for offset_by",
      +  "type": "number"
      +}
  5. Changed4 schema fields changed
    • addedInput schema / properties / limit_by
      Added value: +{
      +  "description": "Number of results to return",
      +  "type": "number"
      +}
    • addedInput schema / properties / locations
      Added value: +{
      +  "description": "Locations (Countries, e.g \"United States\")",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedInput schema / properties / max_items
      Removed value: -{
      -  "description": "Maximum items to include in response (local trim)",
      -  "type": "number"
      -}
    • addedInput schema / properties / offset_by
      Added value: +{
      +  "description": "Offset for pagination",
      +  "type": "number"
      +}
  6. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description discloses billing per returned row, zero-cost for zero rows, the cost-reading mechanism, snapshot lag for headcount data, and referential guidance to get_balance. The schema adds escalation behavior for auto mode, realtime-only constraints, and HTTP 400 rejections. This goes far beyond the readOnlyHint/openWorldHint annotations without contradicting them.

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?

The description is three sentences long, front-loads the core operation, and every sentence carries operational value: what it returns, what it costs, what to run first, and a data-freshness caveat. No filler or repetition of schema content.

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 29-parameter, billable, output-schema-bearing tool, the description plus schema covers cost, prerequisites, mode behavior, data freshness, error conditions, pagination, and deprecations. The output schema handles return-value documentation, so nothing critical is missing for an agent to call this correctly.

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 description coverage is 100%, so the schema already documents every parameter in detail, including realtime-only behavior and cost implications. The tool-level description adds only a small extra note about headcount snapshot lag, which is useful but not essential given the rich parameter descriptions already present.

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 opens with a specific verb and resource: 'Return companies matching an ICP,' so an agent immediately knows this is a search/list tool for companies. It does not explicitly name a sibling it is not (e.g. count_companies), but 'Return companies' plus the sibling name makes the distinction clear enough.

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?

The description explicitly directs the agent to 'Run count_companies first,' providing a concrete sibling-workflow rule. The schema further adds strong mode-selection guidance ('Pick database explicitly when freshness is not critical and cost matters more than freshness') and flags filters that force realtime, which is exactly the kind of when-to-use-vs-alternative guidance this dimension rewards.

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.