cited-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Override the default Gemini model (gemini-2.5-flash-lite). | |
| OPENAI_MODEL | No | Override the default OpenAI model (gpt-5.4-mini). | |
| GEMINI_API_KEY | No | Your Gemini API key. Enables Gemini with Grounding with Google Search. At least one of OPENAI_API_KEY, PERPLEXITY_API_KEY, or GEMINI_API_KEY must be set for the server to function. | |
| OPENAI_API_KEY | No | Your OpenAI API key. Enables ChatGPT via the OpenAI Responses API with the web_search tool. At least one of OPENAI_API_KEY, PERPLEXITY_API_KEY, or GEMINI_API_KEY must be set for the server to function. | |
| PERPLEXITY_MODEL | No | Override the default Perplexity model (sonar). | |
| PERPLEXITY_API_KEY | No | Your Perplexity API key. Enables Perplexity Sonar. At least one of OPENAI_API_KEY, PERPLEXITY_API_KEY, or GEMINI_API_KEY must be set for the server to function. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_ai_visibilityA | Ask AI engines (ChatGPT via the OpenAI API, Perplexity, Gemini) buyer questions with live web search on, and report whether a business is named, its position in any list, whether its website is cited, which competitors are named instead, and the source domains each engine used. Engines without an API key in the server env are skipped. Each question costs a few cents per engine, billed by the provider. Pass 1 to 10 questions, or omit them and pass a category (for example "family dentist") plus a location to use 5 generic buyer questions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of overlap or misselection. The tool's purpose is clearly distinct and unambiguous.
The single tool name follows a clear verb_noun snake_case pattern (check_ai_visibility). With only one tool, consistency is trivially satisfied.
A single tool is on the thin side for the server's stated purpose; while the tool is comprehensive, the absence of auxiliary tools (e.g., engine configuration, result retrieval) makes the surface feel minimal. The rubric considers 1-2 tools borderline.
The tool covers the core AI visibility check thoroughly, including question generation, multi-engine querying, and detailed reporting. Minor gaps exist (e.g., no way to select specific engines or retrieve historical data), but these are not critical for the primary use case.