mcpField
G
GetCited

GetCited

Remote
getcited.devBusiness & Marketing0Updated 4w ago

About GetCited

GetCited is a connector that lets coding agents inspect site health, rankings, AI citations, and visitor behavior through GetCited. It includes MCP configuration, client extensions, and a stdio proxy for clients without remote transport.

Key features

  1. 01Site health and audit tools
  2. 02Rank and AI citation tracking
  3. 03Action queue with evidence
  4. 04Visitor behavior insights
  5. 05Claude Code and Gemini CLI support
  6. 06stdio proxy for local clients

Use cases

  1. 01Review site issues and prioritized actions
  2. 02Track keyword rankings and AI visibility
  3. 03Inspect visitor behavior by page

MCP support

Exposes GetCited tools to MCP clients through its hosted HTTP endpoint. A stdio proxy forwards JSON-RPC for clients without remote transport.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://app.getcited.dev/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://app.getcited.dev/api/mcpAuth required

Tools

29

This tool takes no parameters.

Details

From the project README

GetCited MCP connector

GetCited MCP server on Glama

Client-side pieces for connecting a coding agent to GetCited: the MCP server definition, a Claude Code plugin with its skills, a Gemini CLI extension, and a small stdio proxy for clients that cannot speak Streamable HTTP.

GetCited audits a site the way an answer engine reads it, tracks where it ranks, records which AI engines cite it, and files each measured problem as an action with the evidence behind it. It never proposes the fix: your agent has the repository open and it does not.

The service itself is closed source. Everything in this repository is the connector — transport, manifests and prompts — so you can read exactly what your agent is being told and what leaves your machine.

Connect

Create a key under Settings → API keys in the app, then pick your client.

Claude Code

claude mcp add --transport http getcited https://app.getcited.dev/api/mcp \
  --header "Authorization: Bearer $SEO_API_KEY"

Any client that reads a JSON config

{
  "mcpServers": {
    "getcited": {
      "type": "http",
      "url": "https://app.getcited.dev/api/mcp",
      "headers": { "Authorization": "Bearer ${SEO_API_KEY}" }
    }
  }
}

Gemini CLI

gemini extensions install https://github.com/bapierre/getcited-mcp

Clients without a remote transport (Claude Desktop, whose config takes a command rather than a URL) use the stdio proxy in src/:

claude mcp add getcited --env SEO_API_KEY="vseo_..." -- npx -y getcited-mcp
VariableRequiredMeaning
SEO_API_KEYyesThe key from Settings → API keys.
SEO_API_URLnoEndpoint override. Defaults to https://app.getcited.dev/api/mcp.

Without SEO_API_KEY the proxy still starts and lists the tools from a bundled snapshot (src/tool-snapshot.ts), so registries can inspect it; every call then fails with a message naming the variable. Refresh the snapshot after the hosted tool list changes with npm run build && SEO_API_KEY=vseo_... npm run snapshot.

llms-install.md is the same instructions written for an agent, so you can tell your assistant to set this up rather than doing it yourself.

What is in here

PathWhat it is
src/stdio.tsThe stdio proxy. Forwards JSON-RPC to the HTTPS endpoint and nothing else.
src/tool-snapshot.tsTool definitions served when no key is set. Generated by scripts/snapshot-tools.mjs.
DockerfileBuilds the stdio proxy, for registries that run servers in a container.
.claude-plugin/, skills/The Claude Code plugin and its two skills.
gemini-extension.jsonThe Gemini CLI extension manifest.
.mcp.jsonA project-scoped Claude Code server entry.
llms-install.mdSetup instructions addressed to an agent.

The tools

Sites (list_projects, add_project, remove_project, get_site_health), onboarding and profile (get_setup_status, get_project_profile, set_project_profile), the queue (get_next_work, list_actions, get_action, claim_action, complete_action, dismiss_action, run_audit), growth (list_opportunities, get_content_brief, list_regressions, get_page_history), rankings (add_keywords, list_keywords, rank_history, check_rankings), AI visibility (add_geo_prompts, geo_summary, check_geo, run_brain) and visitors (get_behavior_digest, get_page_profile).

Each tool carries a title and the readOnlyHint or destructiveHint annotation that matches what it does. Full documentation, including what every number means and the rules the measurements follow: https://getcited.dev/docs/mcp.

Registry

Listed in the official MCP Registry as dev.getcited/mcp, published under a DNS-verified namespace.

Support

getcited.dev/support · privacy · terms · MIT licensed.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.