# Pylon SEO (remote · api.pylonseo.io)

Audit, rank-track and analyze SEO for sites via an authenticated MCP server.

- Trust score: 69/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `api.pylonseo.io`: 69/100 (this document), [markdown](https://verifymcp.io/servers/io-pylonseo-pylon-seo/api.md), [page](https://verifymcp.io/servers/io-pylonseo-pylon-seo/api)

## Channel facts

- Endpoint: `https://api.pylonseo.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: this server exposes a tool marked destructive (submit_indexnow) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 81/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1873 tokens (~60/item across 31 items; 31 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 31 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - Manipulation not yet verified: none of the 32 captured unit(s) of tool text has been judged yet, so we will not certify text no model has read as clean.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Pylon SEO MCP server?

Pylon SEO is a hosted endpoint at https://api.pylonseo.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-pylonseo-pylon-seo 'https://api.pylonseo.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-pylonseo-pylon-seo": {
      "url": "https://api.pylonseo.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-pylonseo-pylon-seo": {
      "type": "http",
      "url": "https://api.pylonseo.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-pylonseo-pylon-seo]
url = "https://api.pylonseo.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-pylonseo-pylon-seo": {
      "type": "remote",
      "url": "https://api.pylonseo.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-pylonseo-pylon-seo --url 'https://api.pylonseo.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-pylonseo-pylon-seo:
    url: "https://api.pylonseo.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-pylonseo-pylon-seo": {
      "Transport": "http",
      "Url": "https://api.pylonseo.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-pylonseo-pylon-seo -t streamable-http -u 'https://api.pylonseo.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-pylonseo-pylon-seo": {
      "type": "http",
      "url": "https://api.pylonseo.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 10. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-08 (score 64)

First indexed and scored.

## MCP tools (31)

### `list_sites` (~43 tokens)

List sites in workspace

List every SEO site in the authenticated user's organisation (id, name, domain, status, last audit timestamp). Use before any other tool to discover which site_ids are valid.

### `get_site` (~43 tokens)

Get site details

Get one site's metadata (name, domain, status, verification state, last-audit / last-scan timestamps).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_site_audit` (~41 tokens)

Get latest site audit

Latest SEO audit run for a site: overall + per-category scores and issue counts by severity.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_audit_issues` (~89 tokens)

Get audit issues

Top issues from the latest audit run for a site. Optional filter by severity (critical|high|medium|low). Returns up to `limit` (default 25, max 200) instances.

Input parameters:

- `limit` (integer): Max issues to return (1-200)
- `severity` (string): Optional severity filter
- `site_id` (string, required): UUID of the site

### `get_score_history` (~42 tokens)

Get audit score history

Daily audit score history for a site (used for trend lines). Returns the most recent 90 samples.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_keyword_rankings` (~43 tokens)

Get keyword rankings

Tracked keyword positions + movement for a site (current + previous position, URL, country, device).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_serp_features` (~64 tokens)

Get SERP features

Aggregate SERP-feature presence (AI Overview, Featured Snippet, People-Also-Ask, Local Pack, Video, Images, Shopping, Knowledge) across the site's tracked keywords, from the latest ranking run.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_rank_alerts` (~39 tokens)

Get rank drop alerts

Configured rank-drop alert rules for a site (thresholds + is_active flags).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_ai_overview_presence` (~59 tokens)

Get AI Overview presence

Google AI Overview coverage for a site: coverage %, delta vs previous run, per-intent buckets, per-keyword state (gained / lost / still-covered / not-covered).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_ai_visibility` (~58 tokens)

Get AI visibility

AI visibility overview for a site: measured mention rate across configured AI engines (OpenRouter / OpenAI / Anthropic / Gemini / Perplexity), current engine set, planned engines.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_prompt_research` (~41 tokens)

Get prompt research

Per-prompt AI research for a site (target share, leader, rivals, opportunity bucket).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_gsc_metrics` (~97 tokens)

Get Search Console metrics

Google Search Console metrics for a site. `surface` = organic|ai_overview|ai_mode|discover_ai (default organic); `dimension` = query|page|country|device|date (default query).

Input parameters:

- `dimension` (string)
- `limit` (integer): Max rows (1-500, default 50)
- `site_id` (string, required): UUID of the site
- `surface` (string)

### `get_bing_metrics` (~81 tokens)

Get Bing Webmaster metrics

Bing Webmaster Tools metrics for a site (organic; Bing has no Copilot API split). `dimension` = query|page|country|device|date (default query).

Input parameters:

- `dimension` (string)
- `limit` (integer): Max rows (1-500, default 50)
- `site_id` (string, required): UUID of the site

### `get_competitors` (~46 tokens)

Get competitors

Tracked competitors for a site with their latest snapshot (domain authority, visibility, organic keywords, estimated traffic, backlinks).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_keyword_gaps` (~43 tokens)

Get keyword gaps

Top keyword-gap opportunities (keywords a competitor ranks for and the site does not, ordered by opportunity score).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_backlinks_domains` (~41 tokens)

Get referring domains

Top referring domains for a site with the Pylon-computed 0-100 authority score.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_content_grade` (~50 tokens)

Get content grade

Cached content-grade summary for a URL on a site (from the on-page grader).

Input parameters:

- `site_id` (string, required): UUID of the site
- `url` (string, required): Exact URL to look up

### `get_cwv` (~54 tokens)

Get Core Web Vitals

Core Web Vitals (LCP, CLS, INP, FCP, TTFB) for a site from PageSpeed Insights — mobile + desktop snapshots.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_site_changes` (~48 tokens)

Get site changes

Recent SEO changes detected between the two most recent crawls (title / meta / h1 / canonical / indexability / status code).

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_scan_pages` (~67 tokens)

Get crawled pages

Newest pages from a site's latest crawl (status code, response time, size, depth, indexable). Windowed at 200 rows.

Input parameters:

- `limit` (integer): Max rows (1-200, default 50)
- `site_id` (string, required): UUID of the site

### `get_market_analysis` (~39 tokens)

Get market analysis

Market analysis overview for a site: tracked keyword demand aggregates, competitive concentration and provenance chips.

Input parameters:

- `site_id` (string, required): UUID of the site

### `get_local_seo` (~48 tokens)

Get local SEO overview

Local SEO overview for a site (rank-tracker with local intent). Returns tracked local keywords + rival domains + AI-only rivals.

Input parameters:

- `site_id` (string, required): UUID of the site

### `list_reports` (~86 tokens)

List saved reports

List stored report runs for the caller's organisation. Optional filter by `site_id` and `kind` (overview|seo_audit|rankings|competitors|ai_visibility).

Input parameters:

- `kind` (string): Optional kind filter
- `limit` (integer): Max rows (1-100, default 25)
- `site_id` (string): Optional UUID to filter by site

### `get_plans` (~67 tokens)

Get plans and pricing

Pylon SEO plans and the caller's entitlement: the paid catalogue (Growth / Agency, monthly / yearly) with USD + INR prices, site limits, credits and features, plus the caller's current plan, site usage and trial state, and the website pricing_url where plans are purchased.

### `add_keyword` (~133 tokens)

Track keyword

Track a new keyword for a site. `keyword` and `country_code` (ISO-3166-1 alpha-2, e.g. 'us') are required; `intent` (informational|commercial|transactional|navigational) is optional and estimated when omitted.

Input parameters:

- `country_code` (string, required): ISO-3166-1 alpha-2 (us / in / gb / de / fr / ca / au)
- `intent` (string): Optional intent
- `keyword` (string, required): Keyword text (1-200 chars)
- `site_id` (string, required): UUID of the site

### `add_competitor` (~70 tokens)

Track competitor

Track a new competitor for a site by its bare domain (no protocol). Discovery scan is enqueued asynchronously.

Input parameters:

- `domain` (string, required): Bare domain (e.g. example.com)
- `label` (string): Optional human-friendly label
- `site_id` (string, required): UUID of the site

### `add_rank_alert` (~69 tokens)

Add rank alert rule

Configure a rank-drop alert rule for a site. `drop_threshold` (positive int) fires when any tracked keyword drops that many positions between runs.

Input parameters:

- `drop_threshold` (integer, required): Positions dropped between runs to fire (1-100)
- `site_id` (string, required): UUID of the site

### `start_scan` (~46 tokens)

Run site crawl and audit

Enqueue a fresh crawl + audit run for a site. Idempotent: a running / queued run short-circuits.

Input parameters:

- `site_id` (string, required): UUID of the site

### `start_ranking_run` (~44 tokens)

Run keyword rankings sweep

Enqueue a keyword-rankings sweep for a site (resolves every tracked keyword's SERP position).

Input parameters:

- `site_id` (string, required): UUID of the site

### `submit_indexnow` (~97 tokens)

Submit URLs to IndexNow

Push a URL batch to IndexNow (Bing/Yandex/Naver/Seznam) for a site. Requires an existing verified IndexNow key. All URLs must share the site's host.

Input parameters:

- `confirm_token` (string): Single-use token from the preview call. Omit to preview; include to submit.
- `site_id` (string, required): UUID of the site
- `urls` (array, required): URL list (1-1000)

### `run_public_scan` (~54 tokens)

Scan URL publicly

Run the anonymous single-URL SEO checker (public). Returns the same audit shape logged-in users see. Rate-limited per anonymous identity.

Input parameters:

- `url` (string, required): Full URL to scan (https://example.com/path)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-pylonseo-pylon-seo/api#diagnostics

## Score history

- 2026-10-18: 69
- 2026-10-17: 68
- 2026-10-16: 68
- 2026-10-15: 68
- 2026-10-14: 67
- 2026-10-13: 67
- 2026-10-12: 66
- 2026-10-10: 65
- 2026-10-08: 64

## Common questions

### What is the Pylon SEO MCP server?

Pylon SEO is an MCP server listed in the public MCP registry as io.pylonseo/pylon-seo. Audit, rank-track and analyze SEO for sites via an authenticated MCP server. This page covers its hosted endpoint (https://api.pylonseo.io/mcp).

### Is the Pylon SEO MCP server safe to use?

Pylon SEO scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Pylon SEO MCP server expose?

Pylon SEO exposes 31 tools: list_sites, get_site, get_site_audit, get_audit_issues, get_score_history, and 26 more. Their descriptions and schemas cost roughly 1,842 tokens of context every time the server is loaded.

### Does the Pylon SEO MCP server require authentication?

No. We connected to Pylon SEO without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Pylon SEO MCP server still maintained?

Pylon SEO is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.pylonseo.io/mcp
- Website: https://pylonseo.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-pylonseo-pylon-seo/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-pylonseo-pylon-seo/api.json
- HTML version of this page: https://verifymcp.io/servers/io-pylonseo-pylon-seo/api