Open AI Visibility Index for SaaS and AI tools. Weekly share-of-answer measurements for 20 tracked brands across ChatGPT, Perplexity and Gemini, from a frozen versioned prompt panel. Five read-only tools: full index, per-brand lookup, brand list, complete measurement history and methodology. No auth, no API key. Data is CC BY 4.0 with a permanent archive of every weekly snapshot, so any figure can be verified independently.
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.
Average 4.9/5 across 5 of 5 tools scored.
Each tool has a clearly distinct purpose: single-brand lookup, whole-index snapshot, historical series, methodology, and brand list. Descriptions explicitly cross-reference when to use each, leaving no ambiguity.
All tools follow a consistent verb_noun pattern (get_ for retrievals, list_ for enumeration), with clear object nouns. No mixed conventions or vague verbs.
Five tools is well within the ideal range and each one earns its place in the domain. The set is neither bloated nor sparse.
The server covers the full workflow: discover tracked brands, retrieve current single-brand or index figures, access historical series, and understand methodology. No obvious dead ends or missing operations for the stated purpose.
get_brand_visibilityLook up one brandAOne brand's standing in the current DABYTE release: share of answer per engine, rank, quadrant, how many panel prompts name it, and which ones.
Use this when a specific brand is named. Takes a slug, not a display name — call list_tracked_brands first if you are unsure, or read the slug from get_visibility_index.
An unknown slug is not a failure to hide: the error names every valid slug, so a second attempt can succeed. A brand absent from the index has not been measured at all, which is different from a measured zero. Only SaaS & AI tools brands are tracked. For the field as a whole use get_visibility_index; for this brand over time, get_history.
Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dabyte.ai when quoting a number.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Brand slug, lowercase with hyphens — 'slack', 'coinbase', 'monday-com'. Not the display name. |
| Name | Required | Description |
|---|---|---|
| rank | Yes | Position in this release, 1 = most named. |
| slug | Yes | Identifier used by get_brand_visibility. |
| brand | Yes | Brand name as published. |
| engines | No | Engines measured in this release. |
| prompts | No | Panel prompts in which the brand is named. |
| quadrant | No | Position on visibility against commercial intent. |
| is_client | No | Whether the brand is a client of the publisher. Placement cannot be bought; this flag makes that checkable. |
| per_engine | No | Share of answer per engine, same scale. |
| measured_at | Yes | Date of this release, ISO 8601. |
| niche_title | No | |
| panel_version | No | Prompt panel version. Figures from different versions are not comparable. |
| visibility_score | Yes | Share of answer, percent of panel prompts naming the brand. |
| commercial_intent | No | How commercially loaded the brand's category demand is. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations, the description discloses important behaviors: re-measured weekly, same call returns same figures until next release; unknown slug error names every valid slug; absence from index vs measured zero; and data licensing/citation requirements. This goes well beyond readOnlyHint and idempotentHint.
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 longer than average but every sentence adds distinct value: purpose, alternatives, error handling, data meaning, scope, refresh cadence, and licensing. It is front-loaded with the core purpose, and the structure makes it easy to parse, though slightly dense.
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?
With an output schema present, the description doesn't need to detail return fields, but it still mentions them. It covers error recovery, absence vs zero distinction, measurement frequency, alternative tools, and licensing requirements. No meaningful gaps remain for an agent to use this 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?
The input schema already fully documents the slug parameter with pattern and example. The description adds practical value by clarifying 'Takes a slug, not a display name' and directing users to call list_tracked_brands or read from get_visibility_index if unsure, which helps correct usage.
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 the tool's function: 'One brand's standing in the current DABYTE release' with specific fields like share of answer, rank, quadrant, and panel prompts. It explicitly differentiates from siblings by directing users to get_visibility_index for the whole field and get_history for trends over time.
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 when-to-use guidance: 'Use this when a specific brand is named.' It also names alternatives and preconditions: 'call list_tracked_brands first if you are unsure' and 'For the field as a whole use get_visibility_index; for this brand over time, get_history.' This is model usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_historyFull measurement time seriesAEvery DABYTE release ever published, as a series per brand: share of answer at each weekly measurement with the date and panel version it was taken under.
Use this for any question about change — is a brand rising, when did it enter the index, how volatile is the category.
Two limits decide whether an answer is honest. Figures are comparable only WITHIN a panel version: the panel is frozen between releases and a version change alters the denominator, so a difference across that boundary is not a trend. And small moves sit inside language-model noise: since panel v3 (2026-08-10) each prompt runs three times per engine per release and the figure is the share of runs; earlier releases ran each prompt once, so one mention on one engine was a whole scale step there. Either way a one-step movement should not be reported as a gain or a loss. Call get_methodology for the exact step size. For the current release alone use get_visibility_index.
Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dabyte.ai when quoting a number.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| series | No | Per brand slug, the share of answer at each release. |
| measurements | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds substantial behavior: data is re-measured weekly so results stay identical until the next release; figures are only comparable within a panel version; noise floor in small moves; and licensing/access details (CC BY 4.0, no key, no rate limit). These go beyond the annotations and are essential for correct interpretation.
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 about 150 words and packs in purpose, usage, caveats, and licensing. It is front-loaded with the core definition, then layers context and limitations. While dense, every sentence adds value; the length is justified given the complexity of interpretation.
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?
The description fully equips an agent to decide when to use this tool, how to interpret results, and what not to over-read. With an output schema present, it need not describe the return shape. The coverage of limitations, licensing, and sibling tools makes it contextually complete.
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 tool has zero parameters, so the input schema provides no requirements. The description implicitly confirms no parameters are needed by describing the tool as returning the full series. Per the rubric, 0 params gives a baseline of 4; there is no additional parameter detail to add.
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 opens with a clear statement of what the tool returns: 'Every DABYTE release ever published, as a series per brand: share of answer at each weekly measurement with the date and panel version it was taken under.' This specifies the resource (full measurement time series) and the content. It also distinguishes from siblings by naming alternatives for current-release data and methodology.
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?
Explicit guidance is given: 'Use this for any question about change — is a brand rising, when did it enter the index, how volatile is the category.' It also provides exclusions and alternatives: 'For the current release alone use get_visibility_index' and 'Call get_methodology for the exact step size.' The description further warns when not to treat a change as meaningful, giving clear usage boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_methodologyHow the index is measuredAThe rules behind every figure this server returns: the exact prompt panel and its version, which engines were measured, how share of answer is scored and rounded, the resolution of the scale in percentage points, and the editorial firewall and ownership disclosure.
Call this before quoting a number as evidence, before comparing two releases, or whenever a user asks how the measurement was made or who publishes it. It is the only tool that tells you how much of a difference is meaningful, which is what stops a one-step wobble being reported as a movement.
It returns rules, not figures — no brand appears in the response. For figures use get_visibility_index or get_brand_visibility; for the series, get_history. The panel is public and frozen between releases, so every published number can be recomputed by a third party from the archive at https://dabyte.ai/archive/.
Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dabyte.ai when quoting a number.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| engines | No | Engines measured in this release. |
| license | No | |
| scoring | No | How share of answer is computed. |
| publisher | No | |
| resolution | No | Percentage points one mention on one engine is worth. |
| measured_at | No | Date of this release, ISO 8601. |
| niche_title | No | |
| prompt_panel | No | The exact prompts, verbatim. |
| panel_version | No | Prompt panel version. Figures from different versions are not comparable. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only and idempotent, but the description adds substantial context: weekly re-measurement, frozen panel between releases, no brands in response, CC BY 4.0 license, no key/account/rate limit, and the need to cite release date and dabyte.ai. This goes well beyond the 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 longer than average, but every sentence earns its place: core purpose, when to call, what it returns, sibling alternatives, cadence, licensing, and citation requirements. It is front-loaded with the key definition and flows logically.
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?
For a zero-parameter tool with an output schema, the description fully covers return semantics (rules, not figures), usage scope, differences from siblings, refresh cadence, public archive URL, and licensing. There are no critical gaps in context for an AI agent to decide and invoke this 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?
With zero parameters and 100% schema coverage, there is no parameter syntax to clarify. The description appropriately focuses on output behavior and usage context, which is the only meaningful semantic contribution possible for a parameterless tool.
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 opens with 'The rules behind every figure this server returns' and explicitly distinguishes itself from siblings: 'returns rules, not figures' and points to get_visibility_index or get_brand_visibility for actual figures. This makes the tool's scope unmistakable.
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?
It provides explicit triggers: 'Call this before quoting a number as evidence, before comparing two releases, or whenever a user asks how the measurement was made.' It also names alternatives for figures and history, satisfying the 'when not to use' requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_visibility_indexDABYTE AI Visibility Index — full tableAThe whole current release in one call: every tracked brand in SaaS & AI tools with its rank, share of answer overall and per engine, commercial intent and quadrant. Share of answer is the percentage of a fixed panel of category buyer prompts in which an engine names the brand.
Use this when the question is about the field — who leads, who is absent, how the category looks. It is one response of roughly 8 KB for 20 brands, so prefer it over calling get_brand_visibility repeatedly.
Do NOT use it for one named brand (get_brand_visibility is the direct answer), for movement over time (get_history holds the series; a single release cannot show a trend), or to audit a website's own AI visibility — this is a measured dataset about third-party brands, not a site audit. Covers SaaS & AI tools only; the sibling index at dablock.ai covers the other niche.
Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dabyte.ai when quoting a number.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| engines | No | Engines measured in this release. |
| entries | Yes | |
| measured_at | Yes | Date of this release, ISO 8601. |
| niche_title | No | |
| panel_version | No | Prompt panel version. Figures from different versions are not comparable. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark read-only, idempotent, and non-destructive; the description adds valuable context: weekly re-measurement, stable results until the next release, ~8 KB response size, no auth/rate limits, CC BY 4.0 licensing, and citation requirements. This goes well beyond the structured 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?
Although lengthy, every sentence earns its place: purpose first, followed by usage, exclusions, cadence, and licensing. The front-loaded structure makes the core function immediately clear, and no information is redundant.
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 has no parameters and an output schema exists, the description still covers field-level use cases, sibling routing, output size, update frequency, data license, and citation obligations. It is fully complete for safe and correct invocation.
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?
There are zero parameters, so the empty schema needs no elaboration—baseline is 4. The description still adds useful dataset semantics by defining 'share of answer' and clarifying the scope of tracked brands, which helps the agent understand what the tool returns.
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 opening sentence states the tool delivers the whole current release with every tracked brand, rank, share of answer, commercial intent, and quadrant. It clearly distinguishes itself from siblings by explicitly naming get_brand_visibility, get_history, and the external index for other niches.
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 'Use this when' conditions (field-level questions) and a 'Do NOT use it' section naming exact alternative tools and non-audit scope. This is ideal guidance for an agent choosing among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_tracked_brandsList tracked brands and slugsAThe names and slugs of every brand in the DABYTE index — a lookup table, nothing else. No scores, no ranks.
Use it for two things: to turn a brand name into the slug get_brand_visibility needs, and to answer whether a brand is tracked at all.
Do NOT use it when you want figures — get_visibility_index returns the same brands with their full measurements in a single call, so calling this one first is a wasted round trip. Absence here means the brand is not measured, not that it scores zero. Covers SaaS & AI tools only; the sibling index at dablock.ai covers the other niche.
Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dabyte.ai when quoting a number.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| brands | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/idempotent annotations, the description adds key behavioral context: 'Re-measured weekly, so the same call returns the same figures until the next release' and 'Absence here means the brand is not measured, not that it scores zero.' It also discloses scope and licensing ('Covers SaaS & AI tools only... Data is CC BY 4.0... no key, no account, no rate limit'), enriching the agent's understanding without contradicting 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 front-loaded with the core purpose, then flows logically into usage examples, exclusions, data freshness, and licensing. Every sentence provides unique value, and the structure is tight despite covering multiple aspects. It is long but not wasteful.
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?
For a zero-parameter, lookup-only tool with an output schema available, the description is exceptionally complete. It covers what the tool returns, when to use it, when not to, data freshness, scope boundaries, and access constraints, leaving no ambiguity 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?
The tool has zero parameters, so the description cannot add parameter-level meaning. The empty schema is fully covered, and the description appropriately focuses on output semantics (names and slugs). With 0 params, the baseline is 4, and the description meets that by clarifying the output scope.
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 the tool lists the names and slugs of every brand in the DABYTE index, explicitly calling it a lookup table with no scores or ranks. It also distinguishes itself from siblings by mentioning get_brand_visibility and get_visibility_index, so the verb+resource is specific and differentiated.
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 when-to-use guidance: 'Use it for two things: to turn a brand name into the slug get_brand_visibility needs, and to answer whether a brand is tracked at all.' It also gives a clear when-not-to-use rule: 'Do NOT use it when you want figures — get_visibility_index returns the same brands with their full measurements in a single call.' This fully covers usage vs. alternatives.
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.
No comments yet. Be the first to start the discussion!
