Blockquote

Audit public HTTPS pages for AI citability.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Start Scan: Scan a public HTTPS URL for AI citability (0-100 score + fixes). Returns a scanId immediately; poll get_scan until status is done. A fresh cached report (< 24h) returns as done at once. re
  • Get Scan: Fetch a scan by id. view 'summary' (default) returns score, category scores, and the top recommendations; 'markdown' returns the WHOLE report as one Markdown document (all checks, evidence,
  • List Checks: The catalog of every check a scan runs, with what it measures and why it matters. Categories and weights: schema 40%, structure 30%, citability 30%.

What data it sees

Do you need an account

No: the server works without sign-in

Audit public HTTPS pages for AI citability. Start scans, read reports and fixes, compare results, and explore the check catalog. Anonymous access supports limited free scans and public reports. Paid API keys unlock account quotas and monitoring. Documentation: https://blockquote.io/docs/ai-agents

How to connect

How to connect Blockquote to Claude

The server address to paste into Claude settings:

https://blockquote--blockquote.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Blockquote to ChatGPT

The server address to paste into ChatGPT settings:

https://blockquote--blockquote.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Blockquote to Cursor

The server address to paste into Cursor settings:

https://blockquote--blockquote.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (9)

Raw names from tools/list. Only developers need these.

start_scanScan a public HTTPS URL for AI citability (0-100 score + fixes). Returns a scanId immediately; poll get_scan until status is done. A fresh cached report (< 24h) returns as done at once. refresh: true skips the cache and needs an API key.
get_scanFetch a scan by id. view 'summary' (default) returns score, category scores, and the top recommendations; 'markdown' returns the WHOLE report as one Markdown document (all checks, evidence, and fix payloads — the best input for analysis); 'full' returns the complete report JSON. A caller with no API key gets one full fix; the rest keep their titles and are locked. A bearer API key applies the caller's own account and plan.
list_checksThe catalog of every check a scan runs, with what it measures and why it matters. Categories and weights: schema 40%, structure 30%, citability 30%.
explain_checkWhat a specific check measures, why it matters for AI citation, and the typical fix. Use the checkId from a report or from list_checks.
get_accountPlan, limits, and scans used today/this month for the API key in the Authorization header. Requires a bearer key (bq_…) — create one at https://blockquote.io/account.
compare_scansWhat changed between two finished scans of the same page: score and per-category deltas, every check whose verdict flipped, and recommendations split into resolved, new and still open. Name the pair with from (the older, baseline scan) and to (the newer one), or pass url to compare that page's two newest stored scans. view 'markdown' returns the same comparison as one Markdown section. Replaces fetching two full reports and diffing them yourself.
list_monitorsThe URLs this account re-scans weekly, each with its last score and run time, plus the monitor allowance of the account's plan, returned as `limit`. Requires a bearer key (bq_…).
add_monitorAdd a public HTTPS URL to this account's weekly re-scan. Monitoring needs a paid plan; on the free plan, or at the plan's cap, the call is refused with the reason — the cap refusal names the allowance. Requires a bearer key (bq_…).
remove_monitorRemove one monitor by its id, from list_monitors. Weekly re-scans of that URL stop; the reports it already produced stay readable. Requires a bearer key (bq_…).