Connect Claude to Semrush

Research domains, keywords, competitors and backlinks with Semrush's SEO and advertising data. Toolspoke puts 16 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 16
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Semrush
Open the marketplace in your workspace, add Semrush to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Semrush shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Semrush asks for

API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API keyRequired: Semrush → profile menu (top right) → Subscription info → API units. The key is shown there once your plan includes API units (Semrush One Starter/Pro+, SEO Classic Pro/Guru, or Business with a units package).

What Claude can do in Semrush

16 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 16Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

domain_rank
One domain's headline numbers in one regional database: Semrush rank, organic keywords and traffic, paid keywords and traffic, and their estimated cost. Costs 10 API units - the cheapest real report, which is why an install tests itself with it.
domain_ranks
The same headline numbers as domain_rank, for one domain across every regional database at once - one line per database, each line billed. Use domain_rank when you know the market.
domain_rank_history
Month-by-month history of a domain's rank, organic and paid keywords and traffic in one database.
domain_organic
The keywords a domain ranks for in Google's organic results in one database, with position, volume, traffic share and landing URL. Billed per line, so keep display_limit small.
domain_adwords
The keywords a domain buys Google Ads for in one database, with position, volume, CPC and ad URL. Billed per line.
organic_competitors
The domains that compete with this one in organic search in one database, ranked by keyword overlap. Semrush calls this report domain_organic_organic.
keyword_overview
One keyword's volume, CPC, competition and result count in one database. Semrush calls this report phrase_this.
keyword_overview_all_databases
The same keyword overview across every regional database, one billed line each. Semrush calls this report phrase_all.
keyword_organic_results
The domains and URLs ranking in Google's organic top 100 for one keyword in one database. Semrush calls this report phrase_organic.
related_keywords
Keywords related to one keyword, with volume and CPC, for content and campaign ideas. Semrush calls this report phrase_related.
keyword_difficulty
Keyword difficulty scores (0-100) for up to 100 keywords in one database. Separate the keywords with semicolons. Semrush calls this report phrase_kdi.
url_organic
The keywords one exact URL ranks for in Google's organic results in one database.
backlinks_overview
Backlink totals for a root domain, host or URL - backlinks, referring domains and IPs, follow and nofollow counts, and authority score.
list_backlinks
Individual backlinks pointing at a root domain, host or URL, with source URL, anchor and first and last seen dates. Billed per line.
referring_domains
The domains linking to a root domain, host or URL, with how many backlinks each one sends. Billed per line.
list_projects
List the Semrush projects on this account (the containers for Position Tracking and Site Audit), as JSON. Costs API units like any other report.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 16 actions above are the whole of it. A call to any other name is refused before it reaches Semrush rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in Semrush.
It reaches no further than your credential: Toolspoke holds no access to Semrush of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Semrush: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Semrush. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Semrush's own rate limits. A call that Semrush refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Semrush?

16 named actions: 16 that only read. They include domain_rank, domain_ranks and domain_rank_history. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Semrush connector need?

API key. The connector asks for api key. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Semrush connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 16 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Semrush connector not do?

The 16 actions above are the whole of it. A call to any other name is refused before it reaches Semrush rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in Semrush. Toolspoke holds no access to Semrush of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Semrush. An agent has to ask. Toolspoke does not retry, queue or back off around Semrush's own rate limits. A call that Semrush refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Semrush's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Semrush?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More marketing connectors

Browse all of them