stillindexed MCP server

• Registry namecom.stillindexed/seo-checkersverified in the MCP registry

The registry name sits under stillindexed.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-20
• Tools9
• Server calls itselfstillindexed
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 548 ms.

• Its tools do every use case we checked: catch noindex or blocking directives after client deploys; check redirect chains and canonical targets per URL.
• Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer564 ms
• Space in an agent's context≈ 931 tokensthe definitions of all its tools (9), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• stillindexed_check_url

  Fetch one URL and report HTTP status, redirect chain, meta robots, X-Robots-Tag, canonical, title, H1, and whether it is indexable. Same check as https://stillindexed.com/tools/indexability-checker.

• stillindexed_bulk_check

  Indexability check for up to 20 URLs in one call. Order preserved. Invalid URLs become per-row errors; HTTP status stays 200. Counts against the 60 fetches/hour budget, one per URL.

• stillindexed_check_robots

  Fetch robots.txt for the host and report the effective allow/disallow for each path, wildcard group vs Googlebot separately.

• stillindexed_check_sitemap

  Fetch a sitemap (or the host's /sitemap.xml) and report status, XML validity, and URL count.

• stillindexed_check_tls

  TLS certificate for the host: days remaining, chain validity, hostname match.

• stillindexed_check_domain

  Domain registration expiry via RDAP. Many ccTLDs have no RDAP; the tool says so instead of inventing an expiry.

• stillindexed_crawler_diff

  Fetch the same URL as Googlebot, Bingbot, GPTBot and a browser, then compare status, indexability directives and content. Costs 4 fetches.

• stillindexed_check_ai_crawlers

  Check robots.txt for the 13 tracked AI crawlers (ChatGPT search, Claude, Perplexity, Gemini grounding, and the training crawlers) and report, per crawler, whether the given URL's path is allowed or blocked, naming the deciding group and…

• stillindexed_generate_seo_skill

  Fetch the URL, robots.txt, sitemap (with index expansion), host variants, a four-persona crawler diff and TLS, then return a SKILL.md an agent can install for that host. Up to 12 fetches. Same generator as…