# AIReady

> Scan and fix your site's AI discoverability: crawler access, llms.txt, JSON-LD. Free.

- name: io.github.everyai-com/ai-ready
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 90/100 flags: duplicate-repo
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Fai-ready
- tools: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Fai-ready/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ai-ready": {
      "type": "http",
      "url": "https://ai-ready.magicteams.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-97% +updated-16d-ago -duplicate-repo(15 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 19 of 19 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 3,090 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 30 tool changes in 30 days
- fail `stability.rug_pull`: 15 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 19, about 3,090 tokens to load them all
- tool set hash: 3c3242cf57d65de34c04fec3d59f2f76
- tools last changed: 2026-10-19T19:15:15.355Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.everyai-com/ai-ready.svg)](https://protogrid.dev/servers/io.github.everyai-com/ai-ready)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `list_prompts` added
  - The prompts a project tracks. (Requires an AIReady API key.)
- 2026-10-19 `get_usage` added
  - This month's engine spend, checks run and remaining budget, plus the price per check of each engine. (Requires an AIReady API key.)
- 2026-10-19 `scan_project_site` added
  - Run the AI readiness scan on the project's own domain and save it to the project history. (Requires an AIReady API key.)
- 2026-10-19 `get_action_plan` added
  - Prioritized steps to get named more often: dead cited pages to redirect, readiness fixes, prompts the brand loses and what to publish for each, sites to get listed on, and competitors to close the gap with. (Requires an AIReady API key.)
- 2026-10-19 `get_citations` added
  - Which domains and pages AI engines cite for the project's prompts, which are the brand's own or a competitor's, and any of the brand's cited pages that now return 404. (Requires an AIReady API key.)
- 2026-10-19 `get_visibility_report` added
  - The brand's AI visibility: score, mention and citation rates, average rank, share of voice vs competitors, results per engine, country and prompt, trend over runs, sentiment, and untracked brands the engines recommend. (Requires an AIReady API key.)
- 2026-10-19 `get_run_status` added
  - Progress and summary of a visibility run. (Requires an AIReady API key.)
- 2026-10-19 `run_visibility_check` added
  - Run every active prompt of a project through every tracked engine and country. Starts immediately and finishes in the background (usually 1-5 minutes); poll get_run_status. Spends engine checks from the monthly budget; the estimate is returned. (Requires an AIReady API key.)
- 2026-10-19 `add_prompts` added
  - Add prompts (questions buyers ask AI assistants) to a project. Duplicates are skipped. (Requires an AIReady API key.)
- 2026-10-19 `suggest_prompts` added
  - Suggest the questions real buyers ask AI assistants in this brand's category (category, problem, comparison and branded prompts). Does not save them; pass the ones you want to add_prompts. (Requires an AIReady API key.)

Full history: https://api.protogrid.dev/v1/servers/io.github.everyai-com%2Fai-ready/changes

## Remotes

- https://ai-ready.magicteams.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.9677419)

## Packages

_none_

## Tools (19)

- `add_competitors`: Add competitors to a project so reports rank the brand against them. (Requires an AIReady API key.)
- `add_prompts`: Add prompts (questions buyers ask AI assistants) to a project. Duplicates are skipped. (Requires an AIReady API key.)
- `ask_ai_engine`: Run one prompt through a live AI engine (ChatGPT, Gemini, Perplexity, Copilot or Google AI Mode) from a country and return the full answer, the pages it cited and, if a brand is given, whether and where it was named. Costs one engine check from the workspace budget. (Requires an AIReady API key.)
- `check_ai_readiness`: Scan one website for AI discoverability: which AI crawlers robots.txt allows or blocks (OAI-SearchBot, ClaudeBot, PerplexityBot...), llms.txt, sitemap, schema.org data, meta tags and Content Signals. Returns a 0-100 score, grade and prioritized fixes. Fetches only the domain's /robots.txt, /llms.txt, /sitemap.xml and homepage.
- `crawler_policy_guide`: Reference table of AI crawlers and control tokens (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended...): owner, purpose and whether each drives AI citations or only training.
- `create_project`: Create a project that tracks one brand's visibility in AI answers. Optionally add competitors and prompts in the same call. Use suggest_prompts first if you don't have prompts. (Requires an AIReady API key.)
- `get_action_plan`: Prioritized steps to get named more often: dead cited pages to redirect, readiness fixes, prompts the brand loses and what to publish for each, sites to get listed on, and competitors to close the gap with. (Requires an AIReady API key.)
- `get_citations`: Which domains and pages AI engines cite for the project's prompts, which are the brand's own or a competitor's, and any of the brand's cited pages that now return 404. (Requires an AIReady API key.)
- `get_run_status`: Progress and summary of a visibility run. (Requires an AIReady API key.)
- `get_usage`: This month's engine spend, checks run and remaining budget, plus the price per check of each engine. (Requires an AIReady API key.)
- `get_visibility_report`: The brand's AI visibility: score, mention and citation rates, average rank, share of voice vs competitors, results per engine, country and prompt, trend over runs, sentiment, and untracked brands the engines recommend. (Requires an AIReady API key.)
- `list_projects`: List the workspace's tracked brands (projects) with their latest visibility summary. (Requires an AIReady API key.)
- `list_prompts`: The prompts a project tracks. (Requires an AIReady API key.)
- `llms_txt_draft`: Draft a starter llms.txt from a business name, one-line summary, key pages and contact, so AI assistants get a curated map of the site.
- `robots_txt_for_ai`: Generate robots.txt rules for an AI policy: max_visibility, search_only, block_training or block_all_ai, optionally with Content-Signal lines and a sitemap reference.
- `run_visibility_check`: Run every active prompt of a project through every tracked engine and country. Starts immediately and finishes in the background (usually 1-5 minutes); poll get_run_status. Spends engine checks from the monthly budget; the estimate is returned. (Requires an AIReady API key.)
- `scan_project_site`: Run the AI readiness scan on the project's own domain and save it to the project history. (Requires an AIReady API key.)
- `schema_jsonld_sample`: Generate a schema.org JSON-LD snippet (organization, local_business, product or faq) to paste into a page head so AI systems identify the entity correctly.
- `suggest_prompts`: Suggest the questions real buyers ask AI assistants in this brand's category (category, problem, comparison and branded prompts). Does not save them; pass the ones you want to add_prompts. (Requires an AIReady API key.)