Scan any website for SEO, performance, accessibility, and AI search issues. Returns structured issues with fix prompts you can paste into Claude or Cursor to fix immediately. 40+ checks including Core Web Vitals, Open Graph, structured data, and AI search visibility.
Scored across 4 tools
Each tool has a unique purpose: triggering scans, retrieving results by ID, obtaining full site intelligence, or getting a single actionable issue. No overlap or ambiguity.
Three tools follow verb_noun pattern (get_scan, get_site_intelligence, scan_website), but 'next_issue' deviates slightly as it omits a verb. Still, the naming is clear and consistent in style.
With 4 tools, the server is well-scoped for an SEO analysis workflow. Each tool is essential, and the count avoids unnecessary complexity.
Covers the core workflow: scan, retrieve results, get intelligence, and get prioritized tasks. Minor gap: no way to list all scans or bulk view issues, but 'next_issue' fills the action-oriented need.
Get the results of a previous SEOLint scan by its ID.
| Name | Required | Description | Default |
|---|---|---|---|
| scanId | Yes | The scan ID (UUID) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description only indicates this is a read operation. It does not disclose any behavioral traits (e.g., required permissions, scan status prerequisites, rate limits).
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?
Single sentence, front-loaded with purpose. No wasted words.
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 simple retrieval tool with no output schema, the description is adequate but lacks details about return format or expected content of scan results.
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% and the description adds little beyond 'by its ID'. Baseline of 3 is appropriate since the schema already documents the parameter.
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 retrieves scan results by ID, using verb 'Get' and resource 'results of a previous SEOLint scan'. It is distinguishable from siblings like 'scan_website' which initiates scans, but does not explicitly differentiate.
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?
No guidance on when to use this tool versus alternatives (e.g., after initiating a scan with scan_website). No prerequisites or context are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the full intelligence picture for a domain: site goal, ICP, sitemap structure and gaps, cross-page patterns (template issues affecting multiple pages), and scan coverage by page type. Call this at the start of any SEO session.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The domain, e.g. example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It lists what the tool returns (site goal, ICP, etc.), which adds value beyond the schema. However, it lacks details on side effects, data freshness, authentication needs, or error handling, which are typical for a read operation.
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 two sentences: the first lists the tool's outputs, the second provides usage guidance. Every word is purposeful and front-loaded. No fluff or redundancy.
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 single parameter and lack of output schema, the description covers what the tool does and when to use it. It lists components of the intelligence picture, aiding the agent's decision. Missing details like invalid domain handling or result format, but still adequate for a simple retrieval tool.
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% and the schema already describes the 'domain' parameter as 'The domain, e.g. example.com.' The description does not add further information about the parameter, so 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 uses a specific verb ('Get') and resource ('full intelligence picture for a domain'), and lists concrete components (site goal, ICP, sitemap gaps, cross-page patterns, scan coverage). It clearly distinguishes from siblings like get_scan and scan_website, which focus on individual scans.
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 says 'Call this at the start of any SEO session,' providing strong guidance on when to use the tool. It does not explicitly name alternatives or exclusions, but the directive is clear and contextually sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the single most actionable SEO todo for the user's site. Priority: recurrence-review > critical > warning > info; newest within a tier. Returns markdown that copy-pastes into a coding session as a task. When nothing is pending, returns the next scheduled scan time so the caller can tell the user to check back later. Requires an API key (get one at https://seolint.dev/api).
| Name | Required | Description | Default |
|---|---|---|---|
| apiKey | Yes | Your SEOLint API key. Get it at https://seolint.dev/api. | |
| domain | No | Optional domain override, e.g. example.com. Falls back to the user's primary_domain. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description discloses key behaviors: priority ordering, return format (markdown), fallback behavior, and authentication requirement. It does not mention rate limits or side effects, but these are not expected for a read-only tool that retrieves a pre-computed issue.
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 three sentences with front-loaded main purpose, clear priority, and explicit fallback. Every sentence adds value with no redundancy.
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 adequately explains return values and special cases. It could mention the single-item nature more explicitly, but overall it is sufficient for an AI agent to understand the tool's output.
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 both parameters with descriptions that match the tool's description. The description adds no new information beyond the schema, so baseline score applies.
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 the verb 'get' and the resource 'single most actionable SEO todo', and provides a clear priority order (recurrence-review > critical > warning > info; newest within a tier). This distinguishes it from sibling tools like get_scan, which would return full scan results.
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 states when to use the tool (to get the next task) and what happens when nothing is pending. It does not explicitly exclude use cases or compare to siblings, but the sibling tools are sufficiently different in functionality.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan a website for SEO, performance, accessibility, and AI search issues. Returns structured issues with LLM-ready fix instructions.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The full URL to scan, e.g. https://example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It mentions returning structured issues with LLM-ready fix instructions but omits critical details like sync/async nature, rate limits, timeouts, or any side effects (e.g., does it modify data?).
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?
Two sentences that are efficient and front-loaded: the first gives the core purpose, the second describes the output. No wasted words.
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 tool has no output schema and one parameter, but the description lacks details on return format, pagination (sibling 'next_issue' hints at this), limits, or performance expectations. For a scanning tool, this is incomplete for an agent to use effectively.
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 schema coverage is 100% for the single parameter 'url', and the description adds no new meaning beyond the schema's description. Baseline 3 is appropriate as it does not detract but also does not enhance.
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 scans websites for SEO, performance, accessibility, and AI search issues, providing a specific verb and resource. It distinguishes itself from siblings like 'get_scan' (retrieving results) and 'next_issue' (navigation) by being the initiation action.
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?
No explicit guidance on when to use this tool versus alternatives. The context of sibling names implies it is for starting a scan, while 'get_scan' retrieves results, but the description does not state this distinction or provide usage conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
next_issueget_site_intelligenceget_scanscan_website
Add one secure layer between your agents and this server.