Koskamo

SEOWrench MCP

An official MCP server operated by SEOWrench that enables AI agents to perform technical SEO and AI-readiness audits on web pages. It provides SEO and AI citation scores, identifies issues blocking AI crawlers, and verifies if specific fixes have been applied. All commands are read-only.

Visit SEOWrench

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

SEOWrench MCP logo, by SEOWrenchVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by SEOWrench
You need:ChatGPT only accepts custom connectors on paid plans
MCP endpoint (Streamable HTTP)
https://api.seowrench.com/mcp
Vendor documentation

What you can do with it

  • Audit a page for technical SEO and AI readiness scores
  • Check which AI crawlers are blocked from reading the site
  • Verify if a specific page fix has passed validation

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.seowrench/seowrench@1.0.0Project website

Protocol and capabilities

Server
seowrench 1.0.0
MCP protocol
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

SEOWrench audits public web pages for technical SEO and AI readiness with a deterministic rule engine. Typical loop: audit_url (or geo_check) to find problems, edit the page, then verify with the problem codes to confirm the fix worked. Scores come from measured rules, not from a model's opinion.

Tools

3 advertised

audit_url — Audit a page
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Audit one public web page for technical SEO and AI readiness with SEOWrench's rule engine. Returns two scores (SEO and AI readiness) and the problems ordered by severity: critical, warning, opportunity. Each problem has a stable code, what was measured, and how to fix it. Use it before editing a page, and use verify after editing.

audit_url input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Full public URL of the page, with http:// or https://."
    },
    "lang": {
      "enum": [
        "en",
        "pt"
      ],
      "type": "string",
      "description": "Language of names and recommendations. Default: en."
    }
  },
  "additionalProperties": false
}
audit_url annotations
{
  "title": "Audit a page",
  "readOnlyHint": true,
  "openWorldHint": true
}
geo_check — Check AI readiness
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Check whether AI assistants (ChatGPT, Claude, Perplexity, Gemini) can read and cite a page. Returns the AI readiness score, which AI crawlers robots.txt blocks, whether llms.txt exists, and only the AI-related problems with how to fix them.

geo_check input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Full public URL of the page, with http:// or https://."
    },
    "lang": {
      "enum": [
        "en",
        "pt"
      ],
      "type": "string",
      "description": "Language of names and recommendations. Default: en."
    }
  },
  "additionalProperties": false
}
geo_check annotations
{
  "title": "Check AI readiness",
  "readOnlyHint": true,
  "openWorldHint": true
}
verify — Verify a fix
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Confirm that a fix worked. Reads the page again right now (never a cached result) and answers, for each problem code you pass, passed, failing or not_measured. Use the codes returned by audit_url or geo_check, after you change the page.

verify input schema
{
  "type": "object",
  "required": [
    "url",
    "codes"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Full public URL of the page, with http:// or https://."
    },
    "lang": {
      "enum": [
        "en",
        "pt"
      ],
      "type": "string",
      "description": "Language of names and recommendations. Default: en."
    },
    "codes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 50,
      "minItems": 1,
      "description": "Problem codes to check, as returned by audit_url or geo_check (e.g. missing_h1)."
    }
  },
  "additionalProperties": false
}
verify annotations
{
  "title": "Verify a fix",
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
274 ms
95th percentile latency
274 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 274 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http seowrench-mcp https://api.seowrench.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add seowrench-mcp --url https://api.seowrench.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable seowrench-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "seowrench-mcp": {
      "url": "https://api.seowrench.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "seowrench-mcp": {
      "type": "streamableHttp",
      "url": "https://api.seowrench.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start seowrench-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "seowrench-mcp": {
      "type": "http",
      "url": "https://api.seowrench.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http seowrench-mcp https://api.seowrench.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "seowrench-mcp": {
      "url": "https://api.seowrench.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "seowrench-mcp": {
      "serverUrl": "https://api.seowrench.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like SEOWrench MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 6,645

Do you run SEOWrench MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing