Skip to main content
Glama

Metadata MCP Connector

by io.metadata.mcp-server
OverviewDiscussionsAdmin

Create CSV Upload - LinkedIn Native Audience

create_csv_upload_linkedin_native_audience

Create a CSV Upload - LinkedIn Native audience (platform customAudienceType=NATIVE_TARGETING_CSV).

            AUDIENCE TYPE (mirrors the UI's "Audience Type" dropdown):
              • UI label: "CSV Upload - LinkedIn Native"
              • Platform enum: NATIVE_TARGETING_CSV
              • Channel: LinkedIn only.
              • Two-step flow handled server-side: the CSV is uploaded as a NATIVE ABM list, then the audience is created from it with the LinkedIn-native firmographics + contact criteria applied.

            PREREQUISITE:
              • LinkedIn integration MUST be connected.

            WHEN TO USE (exact user phrasing this tool should match):
              • "CSV Upload - LinkedIn Native"
              • "Upload a CSV and target LinkedIn natively"
              • "LinkedIn native audience from this CSV"
              • The user attached a CSV of companies AND asked for LinkedIn-native targeting (employees / revenues / job titles / skills resolved via LinkedIn).

            WHEN NOT TO USE:
              • If the user asked for a plain "CSV Upload - Accounts" → use `upload_account_list_csv_audience` (creates FIRMOGRAPHIC_INCLUDE, NOT LinkedIn-native).
              • If the user asked for "Native Criteria - LinkedIn" without a CSV → use `create_linkedin_native_criteria_audience`.

            TWO WAYS TO SUPPLY THE ACCOUNT LIST — provide EXACTLY ONE of:
              • `companies`: inline `{<companyname>: <companywebsite>}` map (short ad-hoc lists).
              • `companies_source_csv_url`: URL of a CSV with header `companyname,companywebsite` (case-insensitive); only the `companywebsite` values are required, the name column may be empty. The MCP server downloads, validates, and uploads it as a native ABM list.

            CRITERIA (all optional, LinkedIn-native shapes resolved server-side):
              • employees — LinkedIn employee ranges (e.g. "201-500", "501-1000").
              • revenues — LinkedIn revenue ranges (e.g. "$1M-$10M").
              • company_names — free-text company names (resolved to LinkedIn IDs).
              • location_country_ids — country IDs (e.g. 229=US).
              • job_titles — free-text titles (resolved to LinkedIn IDs).
              • skills — free-text skills (resolved to LinkedIn IDs).

            RETURNS: id, audience_id, audience_name, audience_type (NATIVE_TARGETING_CSV), status, abmSearchCriteriaId, companies_count (the rows sent, each with a website), dropped_without_website (up to 25 rows left out for having no website; pass such a company in company_names to target it as a LinkedIn organization) and dropped_without_website_count, upload_filename, counts, and companies_summary (status, list_companies, linkedin_organizations resolved from company_names, total). Quote company counts from companies_summary.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skillsNoFree-text professional skills (resolved to LinkedIn skill IDs). Example: ['HubSpot', 'Salesforce']
revenuesNoLinkedIn revenue ranges for audience targeting. Valid values: Under $1M, $1M-$10M, $10M-$100M, $100M-$1B, $1B+. Example: ['$1M-$10M', '$10M-$100M']
companiesNoInline map of company names to website URLs (optional). MUTUALLY EXCLUSIVE with `companies_source_csv_url`. Example: {"Acme Corp": "https://acme.com"}
employeesNoLinkedIn employee count ranges for audience targeting. Valid values: 1, 2-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, +10001. Example: ['201-500', '501-1000']
job_titlesNoFree-text job titles (resolved to LinkedIn job-title IDs). Example: ['Software Engineer', 'Product Manager']
audience_nameYesName for the new audience (required).
company_namesNoFree-text company names (resolved to LinkedIn company IDs). Example: ['Metadata', 'Google']
location_country_idsNoCountry IDs for geographic targeting (optional). Valid IDs: 1 (Afghanistan), 2 (Albania), 3 (Algeria), 4 (American Samoa), 5 (Andorra), 6 (Angola), 7 (Anguilla), 8 (Antarctica), 9 (Antigua and Barbuda), 10 (Argentina), 11 (Armenia), 12 (Aruba), 13 (Australia), 14 (Austria), 15 (Azerbaijan), 16 (Bahamas), 17 (Bahrain), 18 (Bangladesh), 19 (Barbados), 20 (Belarus), 21 (Belgium), 22 (Belize), 23 (Benin), 24 (Bermuda), 25 (Bhutan), 26 (Bolivia), 27 (Bosnia and Herzegovina), 28 (Botswana), 29 (Brazil), 30 (British Indian Ocean Territory), 31 (British Virgin Islands), 32 (Brunei), 33 (Bulgaria), 34 (Burkina Faso), 35 (Burundi), 36 (Cambodia), 37 (Cameroon), 38 (Canada), 39 (Cape Verde), 40 (Cayman Islands), 41 (Central African Republic), 42 (Chad), 43 (Chile), 44 (China), 45 (Christmas Island), 46 (Cocos Islands), 47 (Colombia), 48 (Comoros), 49 (Cook Islands), 50 (Costa Rica), 51 (Croatia), 53 (Curacao), 54 (Cyprus), 55 (Czech Republic), 56 (Democratic Republic of the Congo), 57 (Denmark), 58 (Djibouti), 59 (Dominica), 60 (Dominican Republic), 61 (East Timor), 62 (Ecuador), 63 (Egypt), 64 (El Salvador), 65 (Equatorial Guinea), 66 (Eritrea), 67 (Estonia), 68 (Ethiopia), 69 (Falkland Islands), 70 (Faroe Islands), 71 (Fiji), 72 (Finland), 73 (France), 74 (French Polynesia), 75 (Gabon), 76 (Gambia), 77 (Georgia), 78 (Germany), 79 (Ghana), 80 (Gibraltar), 81 (Greece), 82 (Greenland), 83 (Grenada), 84 (Guam), 85 (Guatemala), 86 (Guernsey), 87 (Guinea), 88 (Guinea-Bissau), 89 (Guyana), 90 (Haiti), 91 (Honduras), 92 (Hong Kong), 93 (Hungary), 94 (Iceland), 95 (India), 96 (Indonesia), 98 (Iraq), 99 (Ireland), 100 (Isle of Man), 101 (Israel), 102 (Italy), 103 (Ivory Coast), 104 (Jamaica), 105 (Japan), 106 (Jersey), 107 (Jordan), 108 (Kazakhstan), 109 (Kenya), 110 (Kiribati), 111 (Kosovo), 112 (Kuwait), 113 (Kyrgyzstan), 114 (Laos), 115 (Latvia), 116 (Lebanon), 117 (Lesotho), 118 (Liberia), 119 (Libya), 120 (Liechtenstein), 121 (Lithuania), 122 (Luxembourg), 123 (Macau), 124 (Macedonia), 125 (Madagascar), 126 (Malawi), 127 (Malaysia), 128 (Maldives), 129 (Mali), 130 (Malta), 131 (Marshall Islands), 132 (Mauritania), 133 (Mauritius), 134 (Mayotte), 135 (Mexico), 136 (Micronesia), 137 (Moldova), 138 (Monaco), 139 (Mongolia), 140 (Montenegro), 141 (Montserrat), 142 (Morocco), 143 (Mozambique), 144 (Myanmar), 145 (Namibia), 146 (Nauru), 147 (Nepal), 148 (Netherlands), 149 (Netherlands Antilles), 150 (New Caledonia), 151 (New Zealand), 152 (Nicaragua), 153 (Niger), 154 (Nigeria), 155 (Niue), 157 (Northern Mariana Islands), 158 (Norway), 159 (Oman), 160 (Pakistan), 161 (Palau), 162 (Palestine), 163 (Panama), 164 (Papua New Guinea), 165 (Paraguay), 166 (Peru), 167 (Philippines), 168 (Pitcairn), 169 (Poland), 170 (Portugal), 171 (Puerto Rico), 172 (Qatar), 173 (Republic of the Congo), 174 (Reunion), 175 (Romania), 176 (Russia), 177 (Rwanda), 178 (Saint Barthelemy), 179 (Saint Helena), 180 (Saint Kitts and Nevis), 181 (Saint Lucia), 182 (Saint Martin), 183 (Saint Pierre and Miquelon), 184 (Saint Vincent and the Grenadines), 185 (Samoa), 186 (San Marino), 187 (Sao Tome and Principe), 188 (Saudi Arabia), 189 (Senegal), 190 (Serbia), 191 (Seychelles), 192 (Sierra Leone), 193 (Singapore), 194 (Sint Maarten), 195 (Slovakia), 196 (Slovenia), 197 (Solomon Islands), 198 (Somalia), 199 (South Africa), 200 (South Korea), 201 (South Sudan), 202 (Spain), 203 (Sri Lanka), 205 (Suriname), 206 (Svalbard and Jan Mayen), 207 (Swaziland), 208 (Sweden), 209 (Switzerland), 211 (Taiwan), 212 (Tajikistan), 213 (Tanzania), 214 (Thailand), 215 (Togo), 216 (Tokelau), 217 (Tonga), 218 (Trinidad and Tobago), 219 (Tunisia), 220 (Turkey), 221 (Turkmenistan), 222 (Turks and Caicos Islands), 223 (Tuvalu), 224 (U.S. Virgin Islands), 225 (Uganda), 226 (Ukraine), 227 (United Arab Emirates), 228 (United Kingdom), 229 (United States), 230 (Uruguay), 231 (Uzbekistan), 232 (Vanuatu), 233 (Vatican), 234 (Venezuela), 235 (Vietnam), 236 (Wallis and Futuna), 237 (Western Sahara), 238 (Yemen), 239 (Zambia), 240 (Zimbabwe), 241 (Guadeloupe). Example: [29] for Brazil, [229] for United States
companies_source_csv_urlNoPublic URL of a CSV with header EXACTLY `companyname,companywebsite` (case-insensitive); only the `companywebsite` values are required, the name column may be empty. Use when the user attached a CSV to the chat — the URL comes via `AudienceBrief.attached_file_urls`. MUTUALLY EXCLUSIVE with `companies`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / companies_source_csv_url / description
      Previous value: -"Public URL of a CSV with header EXACTLY `companyname,companywebsite` (case-insensitive). Use when the user attached a CSV to the chat — the URL comes via `AudienceBrief.attached_file_urls`. MUTUALLY EXCLUSIVE with `companies`."New value: +"Public URL of a CSV with header EXACTLY `companyname,companywebsite` (case-insensitive); only the `companywebsite` values are required, the name column may be empty. Use when the user attached a CSV to the chat — the URL comes via `AudienceBrief.attached_file_urls`. MUTUALLY EXCLUSIVE with `companies`."
  2. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so safety profile is known. The description adds genuinely useful behavior beyond that: the LinkedIn integration prerequisite, the server-side two-step CSV->ABM list->audience flow, and the dropped_without_website handling. This is more than the annotations supply, but the description is written as documentation rather than a succinct behavioral delta, so it sits at a solid 3 rather than higher.

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?

Long, but the complexity (9 params, two-step flow, mutual exclusivity, sibling disambiguation) justifies it. Front-loaded with purpose and enum, organized under clear headers. Some repetition (mutual exclusivity stated twice) keeps it from a 5.

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?

Despite no output schema, the description enumerates the return fields (id, audience_id, status, dropped_without_website, companies_summary, etc.) and instructs which to quote. Prerequisite, input modes, and criteria semantics are all covered, making it fully adequate for correct invocation.

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, but the description adds real meaning: it frames the EXACTLY ONE OF constraint between companies and companies_source_csv_url, explains CSV header format and that only website is required, and describes how free-text fields are resolved to LinkedIn IDs. This goes beyond restating the schema.

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 (create a CSV Upload - LinkedIn Native audience) plus the platform enum NATIVE_TARGETING_CSV, and explicitly names the two sibling tools it must not be confused with. An agent can distinguish it from upload_account_list_csv_audience and create_linkedin_native_criteria_audience without opening schemas.

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?

Provides explicit when-to-use (with literal user phrasings and the attached-CSV + LinkedIn-native condition) and when-not-to-use, routing each alternative case to a named sibling tool. Nothing is left to inference.

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

All Metadata MCP Connector toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources