Skip to main content
Glama
PROMPTEYE-SP-Z-O-O

prompteye-mcp

Official

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP transport port3000
MCP_SERVER_NAMENoName reported to clientsprompteye-mcp
PROMPTEYE_API_KEYYesThe API key
MCP_SERVER_VERSIONNoVersion reported to clients1.0.0
PROMPTEYE_API_BASE_URLYesAPI root of the deployment that key belongs to

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

CapabilityDetails
tools
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_accountA

Who the configured PromptEye API key belongs to, which plan the workspace is on, which addons and scopes it has, and how many prompts it tracks. Call this to diagnose a key or to check whether a plan covers a feature before promising it.

list_projectsA

Every project the API key reaches, newest first, with the access the key has to each. A project is one brand tracked in one market, and it is the root of everything else PromptEye measures. Call this first, then select_project, before asking about visibility, competitors, prompts or sources.

select_projectA

Makes one project the active one. Every other tool reports on the active project and takes no project argument, so call this once before asking about visibility, competitors, prompts, answers or sources. Call it again to switch projects mid-conversation.

get_active_projectA

The project every other tool is currently reporting on. Call this when unsure which project the numbers in this conversation refer to.

get_knowledge_baseA

The description of the brand the project measures against — what the company sells and to whom. Useful for judging whether a prompt or a competitor genuinely belongs to this brand.

list_promptsA

The questions the active project puts to the assistants, with the visibility each one earns. Every measurement PromptEye reports is taken on the answers to these prompts, so this is where to look for which questions carry the brand and which do not.

get_promptA

One prompt of the active project, with its visibility broken down per assistant. Call this to see which assistant is carrying a prompt and which is dropping the brand from it.

list_prompt_groupsA

How the active project's prompts are grouped, with the visibility and business priority of each group. Use a group id to narrow list_prompts.

list_categoriesA

Every category of the active project, two levels deep: top-level categories with their subcategories beneath, and whether PromptEye proposed each one or it was written by hand.

list_prompt_suggestionsA

Prompts PromptEye suggests the active project start tracking, still awaiting a decision. Each carries why it was suggested — a gap in the funnel, or a theme close to prompts that already perform — with the search demand behind it, how close to a purchase it is asked and how well it fits the brand. Grouped by the prompt group each would join, strongest demand first. Call this when asked what to monitor next.

get_visibility_summaryA

The headline visibility figures for the active project over a period, and how they moved against the period before it. This is the tool to call for 'how visible are we' — use get_visibility_timeseries only when the individual measurements behind the number are needed.

Pass by to split the same figures along an axis: day for a trend line, model to compare assistants, prompt to rank the prompts carrying the brand.

get_visibility_timeseriesA

The individual measurements behind the summary: one row per day, prompt and assistant, saying whether the brand was named and in which position. Call this to inspect the raw record; call get_visibility_summary for a headline number.

list_competitorsA

Every brand the assistants named on the active project's prompts, measured the same way the project's own brand is and ranked by share of voice. The project's own brand is in the list and marked, so it can be charted against the rest.

Share of voice answers a different question from visibility: visibility is how often the brand was named at all, share of voice is how much of the naming it took from everyone else. This ranks rather than pages — it answers with the strongest brands, not a list you walk to the end of.

list_answersA

The answers the assistants actually gave on the active project's prompts, each with whether the brand was named, in which position, and which sources the answer cited. Call this when a visibility figure needs explaining rather than restating.

list_sourcesA

The domains the assistants leaned on when answering the active project's prompts, ranked by how often they were cited. The project's own domain is marked. Call this to see which pages shape what the assistants say about the brand.

get_citation_qualityA

What the brand is to the answers that mention it — recommended, compared, cited as an expert, or merely mentioned in passing — and with what sentiment. Visibility says how often the brand appears; this says what appearing is worth.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
PromptEye VisibilityVisibility totals, period-over-period change and breakdown for a project

TDQS

A3.9/5.0

Scored across 16 tools

Disambiguation4/5

Most tools are clearly distinct (projects, prompts, visibility, competitors, answers, sources), but get_visibility_summary and get_visibility_timeseries overlap in purpose and require careful reading to distinguish. list_prompts and get_prompt are also similar but the singular/plural pattern helps.

Naming Consistency4/5

The set consistently uses get_/list_ prefixes with clear noun objects (get_prompt, list_projects, list_competitors). Minor inconsistency: get_knowledge_base and get_account are not project-scoped like the rest, and get_visibility_summary vs get_visibility_timeseries breaks the simple noun pattern slightly.

Tool Count4/5

16 tools is at the upper edge of reasonable for a domain with projects, prompts, visibility, competitors, answers, and sources. Each tool covers a distinct resource, though a few could be consolidated (e.g., visibility summary/timeseries).

Completeness4/5

The surface covers the core workflow well: project selection, prompt management, visibility measurement, competitor analysis, answer inspection, and source tracking. Minor gaps: no tool to create/update prompts or prompt groups, and no way to drill into a specific competitor's details beyond the ranked list.

Maintenance

ActivityMaintained
ResponsivenessNo issues