Semrush MCP server for AI agents

Live

API KEY

SEO ANALYTICS

Marketing

Semrush gives your agent SEO analytics and local search data: analyze backlinks and referring domains, check keyword metrics, track map rankings, manage business locations and listings, and reply to reviews.

  • Per-user credentials: each call uses the actual user's API key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Semrush
agent · Acme Q3
Run
Who are the top backlink competitors for acme.com?
S
semrush_list_backlink_competitors
187ms
SEO agent
notion.so, clickup.com, and asana.com overlap most with acme.com's referring domains. notion.so shares 1,240 of them.
Sources: 1 domain, 10 competitors
semrush
10 domains
18:29
Message Claude...

Tools your SEO agent reaches for on Semrush, scoped per user.

CALL ANY TOOL
54 tools for SEO analytics in Semrush: analyze backlinks and keyword metrics, run Map Rank Tracker campaigns, manage locations and listings, and reply to reviews.
semrush_add_review_comment
Add review comment
Reply to a review. Returns the new comment. Check supports_reply on the review in list_reviews first, since not every publisher allows replies. Use update_review_comment to edit a reply later.
Parameters
Name
Type
Required
Description
content
string
Required
Text of the reply, at most 2000 characters. Example: Thank you for your feedback.
location_id
string
Required
32-character hex ID of the Local location. Find it with list_locations. Example: 1d21ceab55d740709311ec9b8a12c01e. It must be the location the review belongs to.
review_id
string
Required
ID of the review, from list_reviews. Example: review-abc123.
semrush_collect_map_rank_campaign
Collect map rank campaign
semrush_create_location
Create location
semrush_create_location_image
Create location image
semrush_create_map_rank_campaign
Create map rank campaign
semrush_delete_location
Delete location
semrush_delete_location_image
Delete location image
semrush_delete_project
Delete project
semrush_disable_listing
Disable listing
semrush_get_authority_score_distribution
Get authority score distribution
semrush_get_backlink_gap
Get backlink gap
semrush_get_backlinks_overview
Get backlinks overview
semrush_get_keyword_metrics
Get keyword metrics
semrush_get_location_more_hour_types
Get location more hour types
semrush_get_map_rank_campaign
Get map rank campaign
semrush_get_map_rank_heatmap
Get map rank heatmap
semrush_get_map_rank_metrics
Get map rank metrics
semrush_get_review_auto_reply_config
Get review auto reply config
semrush_list_anchors
List anchors
semrush_list_backlink_competitors
List backlink competitors
semrush_list_gbp_attributes
List gbp attributes
semrush_list_gbp_posts
List gbp posts
semrush_list_location_categories
List location categories
semrush_list_location_listings
List location listings
semrush_list_map_rank_campaigns
List map rank campaigns
semrush_list_projects
List projects
semrush_list_referring_ips
List referring ips
semrush_update_location
Update location
semrush_update_map_rank_campaign
Update map rank campaign
semrush_update_review_auto_reply_config
Update review auto reply config

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Semrush tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["semrush"], toolNames: [
    "semrush_get_backlinks_overview",
    "semrush_list_backlink_competitors",
    "semrush_get_backlink_gap"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Compare acme.com's backlinks with its top competitors and find link gaps" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["semrush"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Compare acme.com's backlinks with its top competitors and find link gaps" }],
  tools,
});

// Execute the tool call with the user's vaulted Semrush API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["semrush"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Compare acme.com's backlinks with its top competitors and find link gaps" }],
  tools,
});

// Tool call runs with the user's vaulted Semrush API key
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["semrush"] }, pageSize: 100,
});

const agent = new Agent({
  name: "seo_agent",
  model: "gemini-2.5-pro",
  instruction: "Semrush tools scoped to this user",
  tools,
});

await agent.run("Compare acme.com's backlinks with its top competitors and find link gaps");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Semrush tool. Click to copy, paste into your agent, done.
Backlinks
Copy the prompt
Copied
Show the backlinks overview for acme.com.
Copy the prompt
Copied
Compare backlink profiles of acme.com and globex.com.
Copy the prompt
Copied
Which domains link to globex.com but not to acme.com?
Local SEO
Copy the prompt
Copied
What is our average map position for 'coffee near me' this month?
Copy the prompt
Copied
List new reviews for the Austin location.
Copy the prompt
Copied
Reply to the latest 5-star review with a thank you.
Keywords and projects
Copy the prompt
Copied
What is the monthly search volume for 'crm software' in the US?
Copy the prompt
Copied
List our Semrush projects.
Copy the prompt
Copied
Create a Semrush project for globex.com.
SEE HOW AUTH WORKS
Each user connects their own Semrush API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Semrush
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Semrush
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Semrush
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Semrush
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other marketing and analytics connectors.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
Test other agents
See the same per-user auth pattern across other marketing and analytics connectors.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Semrush API key looks fine in a demo. In production every review reply and listing change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Semrush today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Semrush as the user or through a shared key?
As the user. Each user connects their own Semrush API key once, and Scalekit sends it with every call. Audit logs attribute every review reply, listing change, and campaign to that user, not a shared service account.
Where is the Semrush API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Semrush?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the backlink and keyword tools without semrush_delete_project, which permanently deletes a project and all its tools, settings, and history. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Semrush access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Which Semrush data can the agent reach?
Backlink analytics for a domain, subdomain, or subfolder, keyword metrics, projects, Map Rank Tracker campaigns, and Local listing management for the user's business locations, including reviews and Google Business Profile posts. semrush_get_map_rank_limits shows the account's campaign slots and monthly credits.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""semrush"": {
""url"": ""https://mcp.scalekit.com/semrush"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.semrush]
url = ""https://mcp.scalekit.com/semrush""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""semrush"": {
""url"": ""https://mcp.scalekit.com/semrush"",
""type"": ""http""
}
}
}