Provides tools for domain analytics (overview, organic/paid keywords, competitors), keyword analytics (overview, related keywords, difficulty), backlink analysis, and traffic analytics using the Semrush API.
Click on "Install 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., "@semrush-mcp what are the top organic keywords for openai.com?"
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.
A Model Context Protocol (MCP) server implementation that provides tools for accessing Semrush API data.
The Semrush MCP server provides tools for:
Domain Analytics
Domain overview information
Organic and paid keywords analysis
Competitor analysis
Keyword Analytics
Keyword overview data
Related keyword discovery
Backlink Analysis
Backlink data
Referring domains analysis
Traffic Analytics
Traffic summary for domains
Traffic sources analysis
(Note: Requires .Trends API subscription)
Related MCP server: Majestic MCP Server
Clone the repository
Install dependencies:
npm installCreate a .env file with your Semrush API key:
SEMRUSH_API_KEY=your_api_key_hereBuild the project:
npm run buildStart the server:
npm run startVariable | Description | Default |
| Your Semrush API key | (Required) |
| Time to cache API responses | 300 |
| Maximum API requests per second | 10 |
| Environment (development/production) | development |
| Server port | 3000 |
| Logging level | info |
Tool Name | Description | Required Parameters |
| Get domain overview data | domain, [database] |
| Get organic keywords for domain | domain, [database], [limit] |
| Get paid keywords for domain | domain, [database], [limit] |
| Get organic search competitors | domain, [database], [limit] |
| Get backlinks for a domain/URL | target, [limit] |
| Get referring domains | target, [limit] |
| Get keyword overview data | keyword, [database] |
| Find related keywords | keyword, [database], [limit] |
| Get detailed keyword data for specific database | keyword, database |
| Analyze up to 100 keywords at once | keywords, database |
| Get domains ranking in organic results | keyword, database, [limit] |
| Get domains in paid search results | keyword, database, [limit] |
| Get 12-month history of domains bidding on keyword | keyword, database, [limit] |
| Get broad matches and alternate search queries | keyword, database, [limit] |
| Get question-based keywords | keyword, database, [limit] |
| Get difficulty index for ranking in top 10 | keywords, database |
| Get traffic summary data for domains | domains, [country] |
| Get traffic sources data | domain, [country] |
| Check API units balance | check: true |
Parameters in [brackets] are optional.
API requests to Semrush consume API units from your account. Different types of requests have different costs. You can check your API units balance using the semrush_api_units_balance tool.
Tool | API Units per Line |
| 10 |
| 10 |
| 10 |
| 10 |
| 20 |
| 40 |
| 100 |
| 20 |
| 40 |
| 50 |
You can add this MCP server to various AI coding assistants:
Install the package globally to use it with any AI assistant:
npm install -g semrush-mcpClone and build the repository:
git clone https://github.com/thomaswawra/semrush-mcp.git
cd semrush-mcp
npm install
npm run buildIn Cursor, go to Settings > MCP Servers
Click "Add Server"
Configure the server with the following settings:
Name: Semrush MCP (or any name you prefer)
Type: command
Command: semrush-mcp (if installed globally) or node
Arguments: Leave empty if using global installation, or /path/to/semrush-mcp/dist/index.js if using local installation
Environment Variables:
SEMRUSH_API_KEY: Your Semrush API key
Other optional variables as needed
Click "Save"
Open Claude Desktop
Go to Settings > MCP Servers
Click "Add Server"
Configure with these settings:
Name: Semrush MCP (or any name you prefer)
Command: semrush-mcp (if installed globally) or node /path/to/semrush-mcp/dist/index.js (for local installation)
Environment Variables:
SEMRUSH_API_KEY=your_api_key_here
Add other optional variables as needed
Click "Save"
Create or edit your Cline configuration file (usually at ~/.config/cline/config.json)
Add the Semrush MCP server to the mcpServers section:
{
"mcpServers": {
"semrush-mcp": {
"command": "npx",
"args": ["-y", "semrush-mcp"],
"env": {
"SEMRUSH_API_KEY": "your_api_key_here"
},
"transportType": "stdio"
}
}
}For a specific version, use:
{
"mcpServers": {
"semrush-mcp": {
"command": "npx",
"args": ["-y", "semrush-mcp@0.1.1"],
"env": {
"SEMRUSH_API_KEY": "your_api_key_here"
},
"transportType": "stdio"
}
}
}For local installation, use:
{
"mcpServers": {
"semrush-mcp": {
"command": "node",
"args": ["/path/to/semrush-mcp/dist/index.js"],
"env": {
"SEMRUSH_API_KEY": "your_api_key_here"
},
"transportType": "stdio"
}
}
}To run the server in development mode:
npm run devNever share your Semrush API key publicly
API key provides access to your API units balance
Exposing credentials can lead to unauthorized API usage and unexpected charges
Check the remaining API units balance
| Name | Required | Description | Default |
|---|---|---|---|
| check | Yes | Set to true to check the balance |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose whether checking consumes API units, if it's idempotent, or any side effects. Without annotations, this is a gap for a tool performing a mutating (?) check.
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 short sentence, which is concise. However, it could include more contextual details without sacrificing brevity.
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 (one boolean parameter, no output schema), the description is minimally complete. It fails to mention what the response contains, which would be helpful.
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 parameter description 'Set to true to check the balance' is adequate. The tool description adds no additional value 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 'Check the remaining API units balance' clearly states the action (check) and the resource (API units balance), distinguishing it from sibling tools that deal with keywords, domains, etc.
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, such as before making batch requests or to monitor quota. The description lacks context on timing or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get backlinks for a specific domain or URL
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | Domain or URL to analyze backlinks for | |
| limit | No | Maximum number of backlinks to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits beyond the basic operation. It omits details on error handling, rate limits, data freshness, or what happens when the target is invalid.
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 that immediately conveys the tool's purpose. It is front-loaded and contains no 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?
For a simple tool with two parameters and no output schema, the description provides minimal but essential information. However, it lacks details on output format, pagination, and use cases relative to sibling tools.
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%, so the baseline is 3. The description does not add any meaning beyond the schema, which already explains the parameters adequately (target as domain/URL, limit as max count).
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 'backlinks for a specific domain or URL', which is specific and distinct from some sibling tools, though it does not explicitly differentiate from semrush_backlinks_domains.
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 semrush_backlinks_domains. The description lacks context about prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get referring domains for a specific domain or URL
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | Domain or URL to analyze referring domains for | |
| limit | No | Maximum number of referring domains to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks details about behavioral traits such as authentication requirements, rate limits, or whether the operation is read-only (implied but not stated). The description does not disclose any side effects or constraints.
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 is concise and to the point. Every word contributes to the purpose, with no extraneous 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 the lack of an output schema, the description should provide more context about what referring domains are, how the limit affects results, and what the response looks like. The minimal description leaves an AI agent guessing about the tool's output and behavior.
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 covers both parameters (target, limit) with descriptions, achieving 100% coverage. The description adds minimal extra meaning beyond 'for a specific domain or URL', which mirrors the schema's description. Thus, 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 'referring domains' with a specific scope 'for a specific domain or URL'. This effectively distinguishes it from sibling tools like semrush_backlinks which likely return backlinks, not just domains.
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 its siblings. For instance, it does not differentiate between semrush_backlinks_domains and semrush_backlinks, nor does it suggest prerequisites or context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyze up to 100 keywords at once in a specific database (10 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keywords | Yes | Array of keywords to analyze (max 100) | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must carry the burden. It mentions API cost but does not disclose whether the operation is read-only, safe, or has rate limits. Critical behavioral context is missing.
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 that is efficient and front-loaded with the core action and constraints. No unnecessary 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 description lacks information about the return format, error handling, or how results are structured. For a batch analysis tool, this is insufficient for an agent to fully assess suitability.
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 descriptions already present. The tool description adds the API cost per line and the max 100 keywords constraint, which provides some added value, but does not significantly enhance parameter understanding 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 the tool analyzes up to 100 keywords in batch within a specific database, distinguishing it from siblings like semrush_keyword_overview which handle single keywords.
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 batch tool versus alternatives (e.g., single keyword overviews) or how to choose a database. The description does not mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get broad matches and alternate search queries for a keyword (20 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only discloses cost per line, but fails to mention whether the tool is read-only, authentication requirements, or any side effects. This is insufficient for a tool with no 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 a single sentence with no wasted words. It includes essential information (action, resource, cost) and is front-loaded for quick understanding.
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 given the tool's complexity (3 parameters, no output schema, no annotations). It does not explain return format, pagination, or any behavioral details beyond cost, leaving significant gaps 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%, so the baseline is 3. The description adds context that the tool returns 'broad matches and alternate search queries', but does not elaborate on parameter formats or constraints beyond the schema descriptions.
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 gets 'broad matches and alternate search queries for a keyword', providing a specific verb ('get') and resource. The purpose is distinct from sibling tools like related keywords or phrase questions.
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 offers no guidance on when to use this tool versus alternatives. It only mentions cost (20 API units per line) but lacks explicit context about when to prefer broad match keywords over other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get competitors for a specific domain in organic search
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain name to analyze (e.g., "example.com") | |
| database | No | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of competitors to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description should disclose behavioral traits such as rate limits, data freshness, or the definition of 'competitors'. The current description provides none of these, offering only the bare minimum one-line statement.
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, which is concise but arguably too terse. It does not waste words, but could be expanded to include key details without becoming 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?
Given no output schema, the description should indicate what the tool returns (e.g., list of competitor domains, metrics). It also does not specify the scope of 'organic search' or any limitations. The description is insufficient for full understanding.
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?
All three parameters are described in the schema with 100% coverage. The description adds no additional meaning beyond the schema, e.g., by explaining optional interplay or formatting constraints. 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 action ('Get competitors') and the target resource ('domain in organic search'). It effectively distinguishes this tool from siblings like 'semrush_domain_organic_keywords' which focuses on keywords rather than competitors.
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 information is provided about when to use this tool versus alternative Semrush tools (e.g., 'semrush_domain_overview' or 'semrush_backlinks'). The description lacks context on prerequisites or scenarios that favor this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get organic keywords for a specific domain
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain name to analyze (e.g., "example.com") | |
| database | No | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of keywords to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as side effects, authentication requirements, rate limits, or return format. It only implies a read operation without explicit confirmation.
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 effectively communicates the tool's purpose. However, it could include more detail without sacrificing brevity, hence 4.
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 no output schema and minimal description, the tool lacks context about the return format, pagination, or result structure. For a tool with three parameters and no annotations, the description is incomplete for effective use.
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 description adds no additional meaning beyond what the input schema provides for domain, database, and limit. 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 action ('Get') and resource ('organic keywords for a specific domain'). It effectively distinguishes from sibling tools like semrush_domain_paid_keywords and semrush_domain_overview.
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 semrush_domain_paid_keywords or semrush_keyword_overview. No prerequisites or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get domain overview data including organic/paid search traffic, keywords, and rankings
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain name to analyze (e.g., "example.com") | |
| database | No | Database to use (e.g., "us", "uk", "ca", etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully disclose behavior. It only states what data is retrieved, but omits any discussion of side effects, rate limits, permissions, or output format. The agent cannot infer any constraints or important behavioral traits.
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 effectively front-loads the action ('Get domain overview data') and lists key deliverables. It is well-structured for quick comprehension, though it lacks additional useful structure.
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 data retrieval tool with 2 parameters and no output schema, the description is minimally adequate. It tells the agent what data is included, but does not explain output format, pagination, or limitations, leaving some gaps for a fully informed call.
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 are fully described in the schema (domain and database). The description adds no additional meaning beyond the schema, but the high schema coverage (100%) means the baseline is 3. The description does not enhance parameter understanding further.
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 domain overview data, specifying included metrics (organic/paid traffic, keywords, rankings). While it distinguishes from more specific sibling tools by using 'overview', it does not explicitly differentiate from semrush_traffic_summary or other broad 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?
No guidance is provided on when to use this tool versus sibling tools. The agent is left to infer that 'overview' implies a broad summary, but no explicit when-to-use or when-not-to-use instructions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get paid keywords for a specific domain
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain name to analyze (e.g., "example.com") | |
| database | No | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of keywords to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states 'Get paid keywords', implying a read operation, but lacks details on authentication, rate limits, error cases, or what happens with invalid domains.
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 that is front-loaded with the action and resource. Every word is necessary, with no redundancy or filler.
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 tool with three parameters and no output schema, the description is very brief. It explains the core purpose but does not mention output format or default behavior for optional parameters. Given low complexity, it is minimally 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?
Schema coverage is 100% with clear descriptions for all three parameters (domain, database, limit). The description adds no additional meaning beyond what the schema already provides, 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 'Get paid keywords for a specific domain' clearly states the action (Get), the resource (paid keywords), and the scope (specific domain). It directly distinguishes from the sibling tool 'semrush_domain_organic_keywords' by specifying 'paid'.
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 when not to use it, nor does it point to related tools for organic keywords or other analyses.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get domains that bid on a keyword in the last 12 months (100 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds API unit cost information ('100 API units per line'), which is a useful behavioral hint. However, no annotations are provided, so the description carries the full burden; it does not disclose read-only nature or other traits beyond cost.
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 delivering core purpose and cost hint with no extraneous words. Efficient and front-loaded.
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?
Lacks description of output format or return value details. With no output schema, the description should clarify what 'domains' entails (e.g., with metrics, count). Incomplete for a 3-parameter 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% with basic parameter descriptions. The tool description does not add further meaning or examples beyond the schema, so it meets baseline without enhancement.
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?
Clearly states it retrieves domains that bid on a keyword within the last 12 months, specifying the verb, resource, and time constraint. Distinguishes from siblings focused on organic data or overviews.
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 vs alternatives like semrush_keyword_paid_results. The description implies historical ad analysis but lacks context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get difficulty index for ranking in Google's top 10 (50 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keywords | Yes | Array of keywords to analyze (max 100) | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions the API unit cost ('50 API units per line'), which is useful, but omits other aspects like rate limiting, error handling, or data freshness.
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 that conveys the core purpose and cost. It is front-loaded and contains no unnecessary words, earning it a high score.
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 simplicity of the tool (2 params, no output schema), the description lacks completeness. It does not describe the output format, typical return structure, or any edge cases, leaving gaps 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%, so the baseline is 3. The description does not add any meaning beyond what the schema already provides; it only mentions the cost, not parameter details.
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 action ('get') and the resource ('difficulty index for ranking in Google's top 10'). It distinguishes the tool from sibling tools by focusing specifically on keyword difficulty, a unique metric among the listed 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?
The description provides no guidance on when to use this tool versus alternatives. It does not mention when it is appropriate or inappropriate to use, nor does it reference any sibling tools for comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get domains ranking in Google's top 100 for a keyword (10 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description fails to disclose behavioral traits beyond API unit cost. It does not indicate read-only nature, rate limits, or any 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 very short but front-loads the key action and cost. While concise, it could benefit from slightly more detail without becoming 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 has no output schema, so the description should explain return values. It does not describe the result format or structure, leaving the agent underinformed.
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?
All three parameters have descriptions in the schema, so schema coverage is 100%. The description adds no extra information about parameters, meeting the baseline of 3.
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 purpose: get domains ranking in Google's top 100 for a keyword. It also includes cost information, making it specific and distinguishable from sibling tools like keyword_overview or paid_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?
No guidance on when to use this tool versus siblings or alternatives. The description does not mention any prerequisites, exclusions, or context for optimal use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get overview data for a specific keyword
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | No | Database to use (e.g., "us", "uk", "ca", etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description fails to disclose any behavioral traits such as whether it is read-only, rate limits, or what 'overview data' includes.
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?
Very concise single sentence with no wasted words. However, it could benefit from slightly more detail without losing conciseness.
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 (2 params, no output schema) but the presence of many sibling tools, the description is insufficient to help an agent select the correct tool. It lacks context about what 'overview data' includes.
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 parameters are fully documented in the schema. The description adds no extra meaning beyond that, meeting baseline.
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?
Clear verb+resource: 'Get overview data for a specific keyword'. However, it doesn't differentiate from siblings like semrush_keyword_overview_single_db or semrush_batch_keyword_overview.
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. With many sibling tools, explicit usage context is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed overview data for a keyword from a specific database (10 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full transparency burden. It only mentions API cost and vague 'detailed overview data' without specifying behavior (e.g., read-only, mutating, authentication needs, or data structure).
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 with no extraneous information. Efficient and front-loaded.
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?
No output schema, and description does not explain what 'detailed overview data' contains. With 18 sibling tools, more differentiation is needed. The description is too brief for a tool with moderate complexity.
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 has 100% coverage, so baseline is 3. Description adds no extra meaning beyond schema. 'Keyword to analyze' and 'Database to use' are already in 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 the verb 'Get', the resource 'detailed overview data for a keyword', and the scope 'from a specific database'. It distinguishes from siblings like semrush_keyword_overview (likely multi-database) and semrush_batch_keyword_overview.
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 cost hint (10 API units) is present but insufficient for usage context. No mention of when not to use or comparisons with sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get domains in Google's paid search results for a keyword (20 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description only mentions API unit cost but does not disclose other behavioral traits like read-only nature or result pagination, leaving gaps for an agent.
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 with no waste, front-loading the core purpose and including a crucial cost note.
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?
Adequate for a simple tool with good schema, but lacks details about output format, pagination, or any usage constraints beyond cost.
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?
Input schema has 100% coverage with descriptions for all 3 parameters, so baseline is 3; the description adds no additional parameter meaning beyond 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 the action ('Get domains') and the resource ('Google's paid search results for a keyword'), distinguishing it from sibling tools like semrush_keyword_organic_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?
No explicit when-to-use or when-not-to-use guidance, but the name and description imply it is for paid search analysis, contrasting with organic results siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get question-based keywords related to a term (40 API units per line)
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to analyze | |
| database | Yes | Database to use (e.g., "us", "uk", "ca", etc.) | |
| limit | No | Maximum number of results to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only mentions API cost (40 units per line) but does not disclose other behavioral traits such as read-only nature, rate limits, or whether the call is destructive.
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 front-loads the core purpose. It contains no unnecessary 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?
Given the complexity (3 parameters, no output schema, no annotations), the description is too sparse. It does not mention return format, pagination, or any results structure, leaving the agent underinformed.
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?
All parameters have descriptions in the schema (100% coverage), so the baseline is 3. The description adds no additional meaning beyond stating the keyword is a 'term,' which is already implied.
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 action ('Get'), the resource ('question-based keywords'), and the relation to a term. It distinguishes from sibling tools by specifying the question-based nature, which is unique among the listed 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?
No guidance is provided on when to use this tool versus alternatives like semrush_related_keywords or semrush_broad_match_keywords. The description lacks explicit context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get traffic sources data for a domain (requires .Trends API access)
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain to analyze traffic sources for | |
| country | No | Country code (e.g., "us", "uk", "ca", etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description adds the authentication requirement, which is useful. However, it does not disclose other behavioral traits like rate limits, error handling, or data refresh characteristics.
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 with no unnecessary words. It efficiently conveys the core purpose and a key requirement.
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 is adequate but could be more informative. It lacks explanation of what 'traffic sources data' includes and does not specify the return format or any pagination.
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%, so the description does not add extra meaning beyond the parameter names and types. The baseline of 3 is appropriate as the schema already does the heavy lifting.
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 'Get traffic sources data for a domain', including the required access. It distinguishes itself from siblings like semrush_traffic_summary through the specific resource, but does not explicitly differentiate from other traffic-related 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?
The description only mentions the prerequisite of '.Trends API access' but provides no guidance on when to use this tool versus alternatives, such as when to use semrush_traffic_summary or semrush_domain_overview.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get traffic summary data for domains (requires .Trends API access)
| Name | Required | Description | Default |
|---|---|---|---|
| domains | Yes | Array of domains to analyze traffic for | |
| country | No | Country code (e.g., "us", "uk", "ca", etc.) |
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 basic function and a prerequisite, omitting behavioral details like rate limits, data freshness, response structure, or 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?
Extremely concise single sentence that includes purpose and a prerequisite. No wasted words, but could be slightly more structured for clearer parsing.
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 tool with 2 parameters and no output schema, the description is adequate but leaves gaps: no mention of return format, pagination, or limitations. With no annotations, more context would be beneficial.
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 are fully described in the schema (100% coverage). The description adds no additional meaning beyond what is in the schema, so baseline 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?
Clearly states verb 'Get' and resource 'traffic summary data for domains'. Differentiates from siblings like semrush_traffic_sources and semrush_domain_overview by specifying 'traffic summary' and requiring '.Trends API access', but does not explicitly contrast with those 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?
No guidance on when to use this tool versus alternatives. Only mentions a requirement ('.Trends API access'), but no context on appropriate scenarios or exclusion criteria.
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.
v0.1.5semrush_api_units_balancesemrush_backlinkssemrush_backlinks_domainssemrush_batch_keyword_overviewsemrush_broad_match_keywordssemrush_competitorssemrush_domain_organic_keywordssemrush_domain_overviewsemrush_domain_paid_keywordssemrush_keyword_ads_historysemrush_keyword_difficultysemrush_keyword_organic_resultssemrush_keyword_overviewsemrush_keyword_overview_single_dbsemrush_keyword_paid_resultssemrush_phrase_questionssemrush_related_keywordssemrush_traffic_sourcessemrush_traffic_summaryScored across 19 tools
Most tools have distinct purposes, but keyword-related tools (e.g., keyword_overview, keyword_overview_single_db, batch_keyword_overview, related_keywords, broad_match_keywords) could be confused by an agent despite detailed descriptions.
All tools follow the consistent pattern 'semrush_<object>_<action>' or 'semrush_<action>_<object>', using snake_case throughout, making naming predictable.
19 tools cover a comprehensive range of SEO functionalities (keywords, backlinks, competitors, traffic) without being excessive or sparse for the API's scope.
Core SEO workflows are well-covered, including keyword research, domain analysis, backlinks, and traffic. Minor gaps exist, like rank tracking or site audit, but overall surface is solid.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Semrush MCP Pack — SEO analytics via the Semrush Analytics API.
SEO MCP server for keyword research, SERP analysis, audits, and Search Console workflows.
SEO MCP server — backlinks, domain authority, tech stack, and 18+ tools via Common Crawl.
MCP server: 447 pay-as-you-go research tools (SEO, ads, SERP) + verified prowl_analyze reports
