Give your coding agent an SEO memory

Get an API key

Create a key from your dashboard after you get access — while sign-in and checkout are in pre-order, join the waitlist. Keys start with sk- and are shown once.

{
  "mcpServers": {
    "seo-mcp": {
      "url": "https://seo-mcp.io/mcp",
      "headers": { "Authorization": "Bearer sk-..." }
    }
  }
}

Claude Code

claude mcp add --transport http seo-mcp https://seo-mcp.io/mcp \
  --header "Authorization: Bearer sk-..."

Verify with claude mcp list.

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit config):

{
  "mcpServers": {
    "seo-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://seo-mcp.io/mcp",
        "--header",
        "Authorization: Bearer sk-..."
      ]
    }
  }
}

Cursor

Add to .cursor/mcp.json (or global MCP settings):

{
  "mcpServers": {
    "seo-mcp": {
      "url": "https://seo-mcp.io/mcp",
      "headers": {
        "Authorization": "Bearer sk-..."
      }
    }
  }
}

Codex

Add to ~/.codex/config.toml:

[mcp_servers.seo-mcp]
command = "npx"
args = ["-y", "mcp-remote", "https://seo-mcp.io/mcp", "--header", "Authorization: Bearer sk-..."]

What the agent gets

start_seo_session

Entry point for every SEO request. Returns the workflow state for project_id: needs_profile (fresh project) or resumed (applied/verified counts).

profile_project

Deterministically normalise repo signals (package.json, framework configs, homepage HTML, robots.txt, CMS markers) into a project profile with missing fields.

analyze_project

Return published tips applicable to this project, ordered foundation → quick wins → growth. Safe tips only unless include_risky is true.

get_action_plan

Ordered plan with why it applies, concrete steps, verification checks, prerequisites and risk warnings.

get_tip

Fetch a tip by id or slug: brief, extended brief, prerequisites, how-to steps with verification, source, and the agent prompt.

get_tips_by_ids

Batch fetch up to 20 tips by id or slug.

search_tips

Full-text search (FTS5/BM25) over published tips with category/tag filters and a total count.

list_categories

Category tree with published tip counts.

list_tags

Tags with published tip counts, for filtering.

get_next_action

Return the highest-priority unfinished tip for the project (foundation blockers first).

mark_applied

Record progress for a project. Status: applied | skipped | not_applicable | in_progress.

verify_tip

Record that the tip's verification check passed, with the observed evidence. Increments the anonymous verification success rate.

get_progress

List recorded tips for a project with status, verification and evidence.

report

Deterministic session report for a project: profile summary, applied and verified tips, open next actions. Use it to close a session.

reset_progress

Delete all recorded progress for a project. Destructive; confirm with the user first.

whats_new

Tips published or updated since a timestamp (default: last 30 days).

audit_html

Run deterministic SEO checks against supplied HTML, files from the repo, or a public URL (SSRF-guarded fetch). Returns findings with evidence and the tip ids that fix them. No AI.

submit_feedback

Report a tip as outdated, wrong, or that it worked. The message reaches the editors.

Resources: seo-mcp://categories, seo-mcp://categories/{slug}, seo-mcp://tips/{id}, seo-mcp://guide, seo-mcp://projects/{id}/progress. Prompts: audit_plan, fix_issue, weekly_review, profile_project.

Sample session

Ask your agent: “Connect to seo-mcp and work on the SEO of this project.” A correct first exchange:

→ tools/call start_seo_session { "project_id": "riverstone-web" }
← {
    "state": "needs_profile",
    "project_id": "riverstone-web",
    "workflow": ["Inspect the repo read-only", "Call profile_project", "Work get_next_action"],
    "applied": 0,
    "verified": 0,
    "applied_count": 0,
    "next_step": "Inspect package.json and the routing/pages directory, then call profile_project."
  }

→ tools/call profile_project {
    "project_id": "riverstone-web",
    "site_type": "saas", "cms": [], "stack": ["nextjs"],
    "size": "small", "goals": ["organic-traffic"]
  }
← { "profile_id": "…", "next_step": "Call get_next_action." }

project_id is the repository name (package.json name or the git remote), so the plan resumes across chats. Calls that change state return a next_step; follow it instead of guessing the next tool.

Connector OAuth and redirects

claude.ai and Claude Desktop discover the authorization server from /.well-known/oauth-protected-resource, register a public client, and use PKCE. You approve the connection once on the consent page; the server issues a normal revocable key.

Tip slugs are stable. If an admin renames one, the old URL answers with a 301 to the new slug, and tag aliases (nextjs, next.js) resolve to the canonical tag page.

Limits and errors

600 requests/hour per key by default. Errors come back as JSON with a code (invalid_api_key, payment_required, rate_limited, not_found). 429 responses carry Retry-After and X-RateLimit-Remaining. Search pagination uses next_cursor.