Marketing

agencystandings.com

Provides tools to search agency standings and credited work examples, retrieve agency profiles with sourced evidence, and submit agency applications.

1 endpoint7 known toolsFirst detected October 16, 2026Last detected October 16, 2026

ENDPOINT 1

https://agencystandings.com/mcp

No auth detected

MCP server metadata

Name: agency-standings
Version: 1.3.0

Capabilities

tools.listChanged

Server instructions

Ask whether the user is a brand looking for an agency or an agency that wants to join, starting with get_started. Real rankings, earned through evidence: client results, testimonials and published work. On every tool call, fill user_request with a short paraphrase of what the user is looking for, in their words, and leave out personal or sensitive information. For a brand, use search_agencies, search_work, get_agency, list_industries_and_services, and get_methodology. search_work shows real examples of agency work, then offer to connect the user with the agency that built it. Qualified briefs are not open yet. For an agency, collect the name, website, contact email, industries, services, and a city or region, then call join_as_agency. We review the evidence before listing or ranking. No one can pay to be ranked. Rankings come only from evidence. After the agency claims its profile, it can install a private connection from the join page. That connection submits work and profile details for review. OAuth comes later. Public read tools stay on this server. Use rank numbers for Ecom, Legal, SaaS, Finance, and Service. Agencies without enough evidence stay unranked and have no rank number. Never invent or report a numeric score, phone number, or street address.

Known tools 7

get_started

Start here.

Inferred read-only

join_as_agency

Store a pending agency application.

Inferred read-only

search_agencies

Search Agency Standings.

Inferred read-only

search_work

Returns credited examples of agency work, including the client link, image, agency, source, and contact link, plus dateShipped and featuredIn when the library has them, so you can show real examples of agency work, then offer to connect the user with the agency that built it.

Inferred read-only

get_agency

Return the full evidence review for one agency slug: the industry rank or an unranked standing, services, sourced facts with URLs and retrieval dates, profile URL, and contact URL.

Inferred read-only

list_industries_and_services

List industries and service types.

Inferred read-only

get_methodology

Explain how Agency Standings publishes ranks.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agency-standings]
url = "https://agencystandings.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agency-standings": {
      "type": "http",
      "url": "https://agencystandings.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agency-standings
Remote MCP URL: https://agencystandings.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agency-standings": {
      "url": "https://agencystandings.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agency-standings": {
      "type": "http",
      "url": "https://agencystandings.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agency-standings",
  "transport": "streamable-http",
  "url": "https://agencystandings.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.