Semrush Keyword Magic Tool MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | Yes | API key for Semrush Keyword Magic Tool API authentication |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| keyword_overview_analysisD | Keyword Overview analysis |
| keyword_magic_toolB | Find millions of keyword suggestions for your SEO. Enter a topic and get your list of best keywords for you |
| questionsD | Questions |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
keyword_overview_analysis and keyword_magic_tool are clearly distinct (one provides metrics for a specific keyword, the other generates suggestions). The questions tool is somewhat ambiguous in name but appears to target a specific keyword type, so it is distinguishable.
Two tools share a 'keyword_' prefix, but the third is simply 'questions', breaking the pattern. There is no consistent verb_noun structure, making naming conventions mixed though still readable.
Three tools is a reasonable number for a focused keyword research server. It covers the core capabilities without being bloated, though it is slightly sparse.
The set covers keyword overview and keyword suggestion discovery, which are central to the domain. Questions adds a specialized angle, but common operations like keyword filtering or clustering are missing, leaving minor gaps.