mcp-seo-auditor
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_SEO_PYTHON | No | Absolute executable path to a Python 3.11+ interpreter (the Node wrapper requires Python 3.11+ via `python3` on PATH, or this variable set to an absolute executable path). |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_htmlA | Audit supplied static HTML without network access. Returns evidence and prioritized recommendations. |
| audit_urlA | Fetch a public page and audit static SEO. Respects robots.txt; blocks private addresses. |
| crawl_siteA | Crawl up to 10 pages on the exact same origin, respecting robots.txt. Detect duplicate titles and descriptions. |
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
The three tools have clearly distinct inputs and scopes: audit_html takes supplied markup with no network, audit_url fetches a single public page, and crawl_site traverses up to 10 same-origin pages. There is no realistic way to confuse which tool to pick for a given task.
All tools follow a consistent snake_case verb_noun pattern (audit_html, audit_url, crawl_site). The verbs (audit/crawl) differ meaningfully to reflect the differing action, and the convention is uniform throughout.
Three tools is on the lean side but each earns its place by covering a distinct input path (raw HTML, single URL, multi-page crawl). The surface is tightly scoped to static SEO auditing without redundant tools.
The core workflow—auditing static HTML and single URLs plus a bounded same-origin crawl—is well covered. Minor gaps exist around sitemap/robots analysis and broken-link or redirect-chain detection, but agents can work around these, and the bounded crawl avoids dead ends.