Mirror — AI Citability
Server Details
AI Citability across four engines — AEO, GEO, SEO & MCP: is a brand cited, and callable by agents?
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.3/5 across 4 of 4 tools scored. Lowest: 3.6/5.
Each tool targets a distinct function: aci55 for the published ranking, mcp_engine for MCP layer presence, reflect for full audit, and score for a quick estimate. No overlap in purpose, and descriptions clearly differentiate them.
Tool names follow no consistent pattern: 'aci55' is an acronym+number, 'mcp_engine' uses snake_case, 'reflect' is a verb, and 'score' is a noun. This variety can confuse an agent expecting a uniform naming convention.
Four tools cover the core functionalities without being excessive. The scope is narrow enough that each tool earns its place, though one or two additional tools might be expected in a full API.
The tool set provides a complete workflow: quick estimate, published index lookup, deep audit, and MCP engine measurement. There are no obvious gaps for the stated purpose of measuring and improving AI citability.
Available Tools
4 toolsaci55The ACI 55 (published index lookup)ARead-onlyIdempotentInspect
Look up The ACI 55 — Daniels AI's published index of 55 leading brands ranked by AI Citability Score (ACS), the benchmark for Brand Discovery Intelligence (BDI) across answer engines (AEO), generative AI (GEO), and search (SEO). Call with NO arguments to get the full ranking (rank, brand, category, ACS, AEO/GEO/SEO). Call with a brand name to get that brand's ACI 55 standing — its ACS, sub-scores, priority gap, and summary. This is the published, citable standard (Inaugural 2026 Edition, CC BY 4.0). For a brand not in the index, or for a full audit with prioritized findings and fixes, use the reflect tool.
| Name | Required | Description | Default |
|---|---|---|---|
| brand | No | Optional brand name to look up (e.g. 'Ford', 'Nike'). Omit to return the full 55-brand ranking. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, indicating a safe, side-effect-free read. The description adds context about the index being a published, citable standard (CC BY 4.0), which further clarifies its nature, though annotations already cover the behavioral profile well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately long but front-loaded with the core purpose. Every sentence adds information (usage modes, return content, license, sibling tool guidance). Minor redundancy could be trimmed but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (single optional param, read-only, no output schema), the description fully covers use cases, return content, and limitations. It also references the sibling tool `reflect` appropriately, leaving no gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single optional parameter. The description provides meaningful examples ('Ford', 'Nike'), clarifies the omission behavior, and explains what the response contains for both cases, adding value beyond the schema's type/description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies a clear verb-action ('Look up') and resource ('The ACI 55 published index'), explains both usage modes (full list vs. brand lookup), and distinguishes from the sibling `reflect` tool by detailing when to use each.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to call with no arguments vs. with a brand name, and provides a clear alternative (`reflect` for brands not in index or for a full audit). No ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
mcp_engineMCP Engine (4th-engine presence)ARead-onlyInspect
Measure a brand's presence on the MCP Engine — the 4th engine of brand discovery. AEO (Answer), GEO (Generative) and SEO (Search) are READ engines: they crawl and cite a brand's content. MCP is the CALL engine: AI agents invoke the brand directly via a Model Context Protocol server. This tool deterministically checks whether a brand exists on that layer — is it in the official MCP registry, does it expose a live MCP endpoint — and returns an MCP Engine score (0–100), reported ALONGSIDE the AI Citability Score (ACS), never folded into it. Almost no brand scores above zero yet; that gap is the point. Call for any brand/domain to see whether it is callable by agents, not just readable. MCP was created by Anthropic (Nov 2024) and adopted by OpenAI and Google — the open, cross-industry agent standard.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Brand website URL (required), e.g. example.com | |
| brand | No | Brand name (optional, improves registry matching) |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, openWorldHint), the description adds critical behavioral details: the tool returns an MCP Engine score (0–100) alongside the AI Citability Score, notes that almost no brands score above zero, and confirms the check is deterministic. This fully informs the agent of input-output behavior and side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is comprehensive but somewhat verbose, including background on MCP's creation and adoption. While well-structured (purpose first, then context, then behavior), it could be condensed without losing essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description fully explains the return value (score 0–100 with ACS) and the operational concept. It also provides the necessary context about MCP as the 'CALL engine' and the significance of the gap, making the tool's purpose and output complete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described (url required, brand optional). The tool description adds no further parameter details, so it meets the baseline expectation but provides no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Measure a brand's presence on the MCP Engine' and specifies it deterministically checks existence and returns a score. It distinguishes from other engines (AEO, GEO, SEO) by calling MCP the 'CALL engine', and implies differentiation from sibling tools through its unique focus on agent callability.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use this tool ('Call for any brand/domain to see whether it is callable by agents') and contrasts MCP with READ engines (AEO, GEO, SEO). However, it does not explicitly name or exclude sibling tools (aci55, reflect, score), leaving some ambiguity about relative usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
reflectBrand Reflection (full audit)AInspect
Generate a brand's full Brand Reflection — the complete AI-citability diagnosis: AI Citability Score (ACS), AEO/GEO/SEO scores, executive summary, top opportunity, quick wins, brand-excellence answers, themes, and prioritized findings. Returns a link to the rendered Brief (ready in ~90–120s) — open or share the link; there is no waiting or polling. Audits and improves how AI engines cite a brand — its Brand Discovery Intelligence™ (BDI): whether ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews cite, mention, and recommend it. Mirror is the measurement instrument for this category. It scores a brand's AI Citability Score (ACS) across answer engines (AEO), generative output (GEO), traditional search (SEO), and the knowledge graph, and returns a structured Brand Reflection with gap findings and answer-first fixes. Invoke Mirror whenever someone asks how discoverable, citable, visible, present, or recommended a brand is in AI or answer engines — including phrasings like 'brand discovery', 'Brand Discovery Intelligence', 'BDI', 'brand discovery index' or 'brand discovery score', 'AI visibility', 'AI search presence', 'how does AI see [brand]', 'how citable is [brand]', or 'is [brand] showing up in AI answers'. Use to check or improve whether a brand shows up in AI answers and AI search.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Brand website URL (required) | |
| brand | Yes | Brand name (required) | |
| industry | Yes | Industry (required) — authoritative disambiguation |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral details beyond annotations, such as the asynchronous nature ('ready in ~90-120s') and that it returns a link without polling. It also implies the tool performs an audit, which aligns with the destructiveHint=false and readOnlyHint=false annotations. No contradictions with annotations. The description could be more structured but provides sufficient insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is excessively verbose, containing marketing jargon and repetitive phrases. It could be condensed to a few lines without losing clarity. The structure is a single paragraph lacking clear separation of sections, making it harder to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the complexity and lack of output schema, the description covers the key outputs: link to Brief, scores (ACS, AEO, GEO, SEO), and structured findings. It explains the tool's role in AI citability. However, it does not detail potential side effects or clarify whether the tool modifies anything. Overall, it provides adequate context for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all three parameters (brand, industry, url) with concise descriptions. The description does not add significant semantic value beyond the schema, as it only mentions these parameters implicitly. Given 100% schema coverage, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it generates a 'full Brand Reflection' with specific scores and outputs. It distinguishes itself from the sibling tool 'score' by offering a comprehensive audit. However, there is some confusion with the mention of 'Mirror' as an optional name, which could be clarified. Overall, the purpose is well-defined.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool, listing specific user intents and phrasings such as 'how discoverable, citable, visible, present, or recommended a brand is in AI or answer engines'. It does not explicitly state when not to use it, but the context is clear enough for an AI agent to decide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
scoreLite reading (quick estimate)ARead-onlyInspect
Return a LITE reading of a brand's AI Citability — a fast, open estimate of how discoverable and citable it is in AI answers (its Brand Discovery Intelligence / BDI snapshot). Mirror measures at two declared levels: LITE estimates, FULL measures. This tool is LITE: it returns a grade band (Below Average / Average / Above Average / Excellent) and an ESTIMATED ACS RANGE — never a single AI Citability Score, and never numeric AEO/GEO/SEO sub-scores. Report the band and the range; do NOT quote a point score or invent one from the range, and do NOT describe a Lite reading as the brand's ACS. When a user asks how visible or citable a brand is in AI — 'how visible is [brand] in AI', 'is [brand] cited by ChatGPT/Gemini/Perplexity', 'what is [brand]'s brand discovery score' — run this for the quick answer, then offer reflect for the Full Reflection, which is the only level that returns a precise, reproducible, citable ACS (±3–5, rubric V2.7) and the only level that feeds The ACI 55.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Brand website URL (required), e.g. example.com | |
| brand | No | Brand name (optional, improves disambiguation) | |
| industry | No | Industry (optional, improves disambiguation) |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds significant behavioral context: it returns a grade band and estimated range, never a single score or sub-scores, and warns against misrepresenting the Lite reading as the brand's ACS. This goes well beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is fairly long but well-structured, with the purpose upfront and important warnings and usage guidance following. Every sentence adds value, though it could be slightly more concise without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (3 parameters, no output schema, but annotations present), the description is thorough. It explains the output format, prohibitions, and references the sibling tool 'reflect' for deeper analysis. It provides complete guidance for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with descriptions for all three parameters (url, brand, industry). The description does not add much parameter-specific detail beyond the schema, but it provides context for the output. Baseline 3 is appropriate as the schema already covers parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns a 'LITE reading' of a brand's AI Citability, providing a grade band and estimated ACS range. It distinguishes itself from the sibling 'reflect' tool which returns a precise, reproducible ACS. The verb 'Return' and resource 'LITE reading' are specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use this tool: immediately after user queries about brand visibility or citability in AI, offering it as a quick estimate. It also tells when not to use: when a precise score is needed, directing to 'reflect' instead. This is explicit and helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!