Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Meerkats.ai MCP Server search Google for meerkats.ai pricing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is a Model Context Protocol (MCP) server for the Meerkats.ai web scraping service. It provides tools for web scraping, RSS feed processing, and Google search.
Web Scraping: Scrape any URL and get the content as markdown
RSS Feed Processing: Process RSS feeds and get the content
Google Search: Search Google and get the results
Related MCP server: MCP Seekr Server
Clone this repository
Install dependencies:
npm installCreate a .env file based on .env.example and add your Meerkats.ai API key
Build the project:
npm run buildAdd the MCP server to your MCP settings configuration file:
{
"mcpServers": {
"meerkats": {
"command": "node",
"args": ["path/to/meerkats.ai/build/index.js"],
"env": {
"MEERKATS_API_KEY": "your_api_key_here",
"SCRAPPER_API_URL": "https://api.meerkats.ai",
"SCRAPPER_CALLBACK_API_URL": "https://api.meerkats.ai/callback"
}
}
}
}Scrape a URL and return the content as markdown.
Parameters:
url (required): URL to scrape
wait (optional): Time to wait in seconds before scraping
query (optional): Query to search for on the page
Process an RSS feed and return the content.
Parameters:
url (required): URL of the RSS feed
wait (optional): Time to wait in seconds before processing
Search Google and return the results.
Parameters:
query (required): Query to search for on Google
// Example of using the scrape_url tool
const result = await use_mcp_tool({
server_name: "meerkats",
tool_name: "scrape_url",
arguments: {
url: "https://example.com",
wait: 2
}
});
// Example of using the google_search tool
const searchResult = await use_mcp_tool({
server_name: "meerkats",
tool_name: "google_search",
arguments: {
query: "meerkats.ai web scraping"
}
});MIT
Check if a domain has a catch-all email address.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain to check |
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 states the operation but doesn't disclose what the result looks like, whether it requires network access, or how errors are handled. For a network check tool, this is insufficient for an agent to understand 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?
A single concise sentence with no fluff or redundancy. It front-loads the essential purpose.
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 is simple and the description captures its core purpose, but with no output schema or behavioral disclosure, the agent lacks understanding of return value and edge cases. It's minimally adequate but has clear gaps.
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 has one parameter with a description that fully covers the meaning, and schema coverage is 100%. The tool description adds no additional parameter detail, so the baseline of 3 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 uses a specific verb (check) and resource (domain's catch-all status), clearly distinguishing it from siblings like verify_email and get_mx_for_domain.
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 no guidance on when to use this tool vs alternatives. It doesn't mention that it's for catch-all detection as opposed to email verification or MX lookup, leaving the agent to infer from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
generate group of support email addresses are valid and active at a domain. Checks common group email patterns.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain of the group email addresses | |
| emails | No | List of email prefixes to check, separated by commas (optional) | |
| fromEmail | No | Email address to use as the sender in SMTP verification (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does not reveal that the tool may perform SMTP verification (evident only from the 'fromEmail' parameter), does not mention potential side effects like sending emails, and is vague about what 'valid and active' means. This lack of transparency could lead an agent to misuse the tool.
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 short but poorly structured and ungrammatical. The first sentence is a run-on and confusing, and the second sentence is a fragment. It is not concise in an effective way because the wording obscures meaning rather than clarifying it.
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 is moderately complex due to potential SMTP verification and multiple parameters, but the description does not explain return values, response format, or behavioral nuances. It does not address edge cases like catch-all domains or rate limiting. The lack of an output schema and annotations makes this incomplete for a reliable tool 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?
Schema coverage is 100%, with each parameter clearly described. The description adds minimal value beyond the schema, only hinting at 'group email patterns' which loosely connects to the 'emails' parameter. Since the schema handles parameter meaning well, a 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 attempts to convey that the tool checks support email addresses at a domain, but the grammar is ambiguous ('generate group of support email addresses are valid and active'). It mentions 'Checks common group email patterns,' which gives some indication of the purpose, but it fails to clearly specify whether it generates or verifies emails, and does not distinguish it from sibling tools like verify_email or guess_email.
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 is provided on when to use this tool versus alternatives. The description gives no context for selection, no exclusions, and no mention of prerequisites such as needing MX records or avoiding catch-all domains. The phrase 'Checks common group email patterns' implies a use case, but the agent is left without clear direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get MX records for a domain.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain to check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description merely restates the tool's function without disclosing behavioral details such as DNS query behavior, potential delays, or output format. With no annotations available, the description carries the full burden and does not deliver.
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 a single, efficient sentence with no wasted words. However, it is so minimal that it barely adds value beyond the tool name, so it is not a 5.
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 single-parameter tool with no output schema, the description covers the basic operation. However, it omits any mention of return values or usage context, making it minimally sufficient but not fully 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 description does not add parameter information, but the input schema fully documents the 'domain' parameter with a clear description. With 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 the tool fetches MX records for a domain, using a specific verb and resource. It is distinct from sibling tools by its focus on DNS MX lookups, though it does not explicitly call out alternatives.
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 is provided on when to use this tool versus alternatives like check_domain_catch_all or verify_email. The description lacks any contextual hints about typical use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Google Maps data for a location query, optionally at specific coordinates
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return (default: 10) | |
| query | Yes | Location search query | |
| location | No | Optional location parameter. If in "latitude,longitude" format (e.g., "37.7749,-122.4194"), will search at those coordinates. Otherwise, will be added to the search query. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions only that data is fetched, without addressing return format, pagination, rate limits, auth requirements, or whether the operation is read-only. The phrase 'Get Google Maps data' implies a read operation, but no confirmatory details are given.
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 a single efficient sentence that front-loads the tool's purpose and highlights the optional coordinate feature. It contains no filler, earning a strong score, though it is brief enough to omit some valuable context.
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 the description gives no indication of what 'Google Maps data' includes, whether it returns structured records, has limits, or handles errors. This is insufficient for an agent to fully understand expected response semantics.
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 has 100% coverage with descriptions for all three parameters. The description echoes the optional coordinate behavior already present in the schema but adds nothing beyond that, so a 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 that the tool retrieves Google Maps data based on a location query with an optional coordinate filter. It is specific in verb and resource, but does not explicitly distinguish itself from sibling tools like google_places or google_serp, so it stops short of a 5.
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 is provided on when to use this tool versus alternatives such as google_places or google_serp. The description offers only the tool's function and no contextual prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Google Maps Places API data for a search query
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | search query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read operation ('Get') but does not mention authentication requirements, rate limits, or what the response data looks like.
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 a single sentence with no redundant content. It efficiently communicates the core purpose without being overly verbose.
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 is simple with one parameter, but without annotations or an output schema, the description could add detail about what 'Places API data' entails, such as whether it returns a list of places or specific fields. It is minimally sufficient but has gaps.
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 the parameter 'query' described as 'search query'. The description's 'for a search query' adds little beyond the schema, so a 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 the verb 'Get' and the resource 'Google Maps Places API data' with a scope of 'search query'. It is specific and understandable, but does not explicitly distinguish from the sibling tool 'google_map' which might have similar functionality.
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?
There is no guidance on when to use this tool versus alternatives like 'google_map' or other search tools. The description only states the basic action without providing context, exclusions, or alternative recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Google search results for a query with page limit
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return (default: 10) | |
| query | Yes | Search query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action ('Get') without detailing rate limits, auth requirements, result format, or pagination behavior. The phrase 'page limit' is ambiguous and does not clarify how results are paginated.
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 a single succinct sentence with no filler words. It effectively communicates the core action, though 'page limit' is slightly imprecise.
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 is minimal but provides the basic purpose. However, without an output schema, it does not explain return values, and it lacks context for selecting this tool over the similar 'web_search'. For a two-parameter tool, it is adequate but leaves clear gaps.
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?
Both parameters (query and limit) are fully described in the input schema with 100% coverage, so the baseline is 3. The description's phrase 'page limit' adds negligible meaning beyond the schema's 'limit' description, but does not conflict.
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 resource 'Google search results', clearly stating the tool's function. However, it does not differentiate from sibling tools like 'web_search' or 'google_places', so it earns a 4 rather than a 5.
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 is provided on when to use this tool versus alternatives such as 'web_search'. There are no exclusions or prerequisites mentioned, so the agent has no context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Guess an email address based on name and domain using common email patterns.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Company domain name | |
| lastName | Yes | Last name of the person | |
| firstName | Yes | First name of the person | |
| fromEmail | No | Email address to use as the sender in SMTP verification (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden of behavioral disclosure. However, it only states the core function and does not reveal that the tool is probabilistic, may return multiple guesses, or how it handles failures. It also omits any mention of the optional 'fromEmail' parameter's role in SMTP verification, which could indicate a side-effect or external interaction.
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 a single, front-loaded sentence that immediately communicates the tool's purpose. It contains no filler words and every element contributes to understanding. It is appropriately concise for a tool of this apparent simplicity.
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 lack of an output schema and annotations, the description must convey expected return values and behavioral nuances. It does not mention whether the tool returns one email, multiple candidates, a confidence score, or how to handle invalid domains. It also fails to position the tool within the broader email workflow (e.g., pairing with 'verify_email'). This leaves significant gaps for an agent trying to use the tool 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 input schema provides 100% coverage of parameter descriptions, so the baseline is 3 as per the rubric. The description adds no extra parameter-specific meaning beyond restating that the guess is based on 'name and domain.' It does not clarify usage of 'fromEmail' or any optional behavior beyond what the schema already states.
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: 'Guess an email address based on name and domain using common email patterns.' It uses a specific verb ('guess'), identifies the resource ('email address'), and specifies the input basis (name and domain). This distinguishes it from sibling tools like 'verify_email' or 'check_domain_catch_all', which serve different purposes in the email workflow.
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 no guidance on when to use this tool versus alternatives. It does not mention using 'verify_email' to check the guess, nor does it indicate any prerequisites or exclusions. The usage is entirely implied by the name and function, but the rubric expects explicit or at least contextually clear guidance, which is absent here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scrape a URL and return the content as markdown
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to scrape | |
| formats | No | Content formats to extract (default: ['markdown']) | |
| timeout | No | Maximum time in milliseconds to wait for the page to load | |
| waitFor | No | Time in milliseconds to wait for dynamic content to load | |
| excludeTags | No | HTML tags to exclude from extraction | |
| includeTags | No | HTML tags to specifically include in extraction | |
| onlyMainContent | No | Extract only the main content, filtering out navigation, footers, etc. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must shoulder behavioral transparency. It only states the basic action and default output, without disclosing that it can also return HTML, handle dynamic content (waitFor), or filter tags. This under-discloses significant behaviors.
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?
One sentence with no redundancy; directly front-loads the tool's purpose.
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 schema is rich, but the description is minimal. It doesn't mention the tool's ability to return HTML or to handle dynamic content, though these are in the schema. For a tool with 7 parameters, this is adequate but not thorough.
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% and describes all 7 parameters, including formats, timeout, waitFor, and tag filtering. The description merely echoes the markdown default without adding semantic context 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?
Description states 'Scrape a URL and return the content as markdown' – specific verb (scrape), resource (URL), and output format (markdown), clearly distinguishing from search/email sibling tools.
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?
Provides clear context: use when you need to scrape a specific URL. No exclusions or alternatives are mentioned, but sibling tools are unrelated (search, email), so the intended use case is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify if an email address is valid and active using SMTP verification.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Email address to verify | ||
| fromEmail | No | Email address to use as the sender in SMTP verification (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the method (SMTP verification) and the outcome (valid/active) but does not disclose potential side effects, such as whether it sends an actual email to the address, triggers spam filters, requires a fromEmail, or has rate limits. This lack of detail for a tool with no annotation support is a significant gap.
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 a single, concise sentence that clearly communicates the core function. It is front-loaded with the action and resource, with no wasted words or redundant 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?
The tool has no output schema, so the description should ideally indicate what the tool returns (e.g., a boolean or detailed report). The description says 'verify if...' but does not disclose the return format or any edge-case behavior. For a simple tool, this is adequate but incomplete given the lack of annotations and output schema.
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%, so the schema already documents both 'email' and 'fromEmail'. The description adds minimal extra meaning beyond mentioning SMTP verification, which indirectly explains the role of fromEmail. Since the schema handles parameter documentation, a 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 the tool's purpose: 'Verify if an email address is valid and active using SMTP verification.' It specifies the verb 'verify', the resource 'email address', and the method 'SMTP verification', which distinguishes it from siblings like guess_email or check_domain_catch_all.
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 implies when to use this tool (when you need to check email validity/activity) but provides no explicit guidance on when not to use it or how it compares to alternatives such as check_domain_catch_all or get_mx_for_domain. There is no mention of prerequisites or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search on web and return the results
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Query to search for on web |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only says 'return the results' with no details on pagination, result count, rate limits, or any other behavior. This is insufficient for a web search tool.
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 a single sentence with no filler, and the verb 'Search' is front-loaded. It is appropriately sized for a tool with one parameter, and every word earns its place.
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 absence of annotations and output schema, the description is incomplete. It does not explain the exact result format, result limits, or how it differs from the similar sibling tool google_serp, leaving the AI agent without enough context to invoke it 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 describes the only parameter (query) with 100% coverage. The tool description adds no additional meaning or constraints beyond the schema, so the baseline score of 3 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 uses a specific verb 'Search' and identifies the resource 'web', clearly stating that it returns results. However, it does not differentiate from siblings like google_serp or google_places, which also search the web, so it lacks sibling differentiation.
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 is provided on when to use this tool versus alternatives. There is no mention of when to prefer web_search over google_serp, google_places, or other siblings, and no exclusions or prerequisites are stated.
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.
v1.0.0check_domain_catch_allgenerate_support_emailsget_mx_for_domaingoogle_mapgoogle_placesgoogle_serpguess_emailscrape_urlverify_emailweb_searchScored across 10 tools
Several tools have overlapping purposes: google_places and google_map both return Google Maps data for location queries, and web_search and google_serp both provide search results. Additionally, guess_email and generate_support_emails overlap in guessing email patterns. This creates multiple ambiguous boundaries that an agent must navigate.
Tool names follow no consistent pattern: some start with verbs (verify_email, scrape_url), others with nouns (web_search, google_map), and some are mixed (generate_support_emails, check_domain_catch_all). There is no uniform verb_noun structure, making the naming style chaotic.
With 10 tools, the count is within the ideal range for a utility server. However, the presence of redundant or overlapping tools (e.g., google_places vs google_map) indicates a slight over-scoping, so it earns a 4 rather than a 5.
The email/domain verification tools cover verification, guessing, catch-all detection, and MX checks, while web tools cover search, scraping, and Google-specific queries. Minor gaps exist, such as missing reverse geocoding or additional domain checks, but core workflows are well covered.
Web search and page-reading for AI agents. One-click OAuth connect, or a Caesar API key.
Scrape, crawl and search the web for AI agents via MCP.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.