# Superflow Free Tools (remote · usesuperflow.ai) 19 free website QA and AI-visibility tools. Remote HTTP MCP, no account, no API key. - Trust score: 77/100 (medium) - Change this week: +3 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-20 ## Components - remote · `usesuperflow.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ai-usesuperflow-tools/api-mcp.md), [page](https://verifymcp.io/servers/ai-usesuperflow-tools/api-mcp) ## Channel facts - Endpoint: `https://usesuperflow.ai/api/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 2026-09-20. - **Endpoint Security**: 63/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation not fully verified: no authorisation is required to call this server, and 14 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - 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**: 65/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 4824 tokens (~344/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 100/100 - No destabilizing schema changes in the last 30 days. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 60/100 - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. ## Install ### How do I install the Superflow Free Tools MCP server? Superflow Free Tools is a hosted endpoint at https://usesuperflow.ai/api/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 ai-usesuperflow-tools 'https://usesuperflow.ai/api/mcp' ``` ### Cursor ```json { "mcpServers": { "ai-usesuperflow-tools": { "url": "https://usesuperflow.ai/api/mcp" } } } ``` ### VS Code ```json { "servers": { "ai-usesuperflow-tools": { "type": "http", "url": "https://usesuperflow.ai/api/mcp" } } } ``` ### Codex ```toml [mcp_servers.ai-usesuperflow-tools] url = "https://usesuperflow.ai/api/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "ai-usesuperflow-tools": { "type": "remote", "url": "https://usesuperflow.ai/api/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add ai-usesuperflow-tools --url 'https://usesuperflow.ai/api/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: ai-usesuperflow-tools: url: "https://usesuperflow.ai/api/mcp" ``` ### Netclaw ```json { "McpServers": { "ai-usesuperflow-tools": { "Transport": "http", "Url": "https://usesuperflow.ai/api/mcp" } } } ``` ### Vellum ```bash assistant mcp add ai-usesuperflow-tools -t streamable-http -u 'https://usesuperflow.ai/api/mcp' ``` ### Other ```json { "mcpServers": { "ai-usesuperflow-tools": { "type": "http", "url": "https://usesuperflow.ai/api/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. ### 2026-09-20 (score 77, 0) - [security] Stability: 0.97 → pass ### 2026-09-19 (score 77, +1) No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-17 (score 76, +1) No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-14 (score 75, +1) No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-12 (score 74, +1) No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-10 (score 73, +1) - [security] The server rewrote its instructions, which are the text every model session reads - [functional regression] Schema quality: 4274 → 4824 - [functional] New tool “find_meeting_times” ### 2026-09-08 (score 72, +1) No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-06 (score 71, +1) No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes. ## MCP tools (14) ### `find_meeting_times` (~482 tokens) Time Zone Converter & Meeting Planner Find overlapping working hours and meeting times across cities or countries. Resolves locations to IANA time zones and applies daylight saving for the requested date. Returns resolved locations, overlap windows, the earliest matching meeting starts with UTC and local times, readable copy text, and a link to open the plan. Ambiguous names or countries with multiple zones return choices: retry with a returned location ID or a more specific city/region/country. The same working schedule is applied in each location's local time; the browser plan supports individual schedules. Does not access calendars, account for holidays, send invitations, or book meetings. Returns { ok, date, dateZone, durationMinutes, locations[], overlapMinutes, overlapWindows[], slots[] with UTC/local times and copyText, totalAvailableStarts, hasMore, planUrl, availability }. Limit: No application rate limit. Up to 8 locations, 20 returned starts, and a 16 KB request body; no result storage.. Allow up to 10s for a response. Free, no account, no API key. Input parameters: - `date` (string, required): Meeting date as YYYY-MM-DD (2000–2099), in the first location's time zone. Required: use the actual meeting date so daylight saving is correct. - `durationMinutes` (number): Length of the whole meeting, 15–1440 minutes in 15-minute increments. - `limit` (number): Maximum suggested meeting starts to return, 1–20. Earliest first, at 15-minute intervals; totalAvailableStarts reports the full count. - `locations` (array, required): Cities, single-zone countries, or location IDs returned in choices. Include a region/country to distinguish namesakes, e.g. San Francisco California or London United Kingdom. The first location deter… - `workDays` (string): Comma-separated working days: 0=Sunday through 6=Saturday. For overnight shifts, the day the shift starts. Applied to all locations. - `workEnd` (string): End of working hours, as local 24-hour HH:mm, in 15-minute increments. An earlier end means an overnight shift. Must differ from workStart. - `workStart` (string): Start of working hours, as local 24-hour HH:mm, in 15-minute increments. Applied to all locations. ### `check_ai_visibility` (~399 tokens) AI Visibility Checker Check whether AI assistants (ChatGPT, Claude, Perplexity, Google AI) can reach, read, and cite a web page. Runs the full suite: robots.txt rules per AI crawler, a live firewall test that requests the page as GPTBot, JavaScript dependency, llms.txt, headings, structured data, and author identity. Returns a score out of 100 with a grade, a score per category, and a finding per check with why it matters and how to fix it. Use this for a whole-page verdict; use check_robots_txt_for_ai when the question is only about crawler access. Returns { ok, report: { score, grade, scoredOutOf, categories[], findings[] with why and fix, detection }, cached, ageSeconds }. Limit: 10 runs per hour per IP. Allow up to 75s for a response. Free, no account, no API key. Pass `url` to start a run. A slow run answers with `{ status: "pending", runId }` instead of a result: call this same tool again with just that `runId` to collect it, as many times as it takes. Collecting costs no rate-limit slot. Input parameters: - `refresh` (boolean): Skip the 24 hour cache and run again. Costs a rate-limit slot even when a cached result exists, so leave it off unless the page has changed. - `runId` (string): Collect a run that answered with `{ status: "pending", runId }` instead of a result. Send the runId back on its own, with no url, and the same tool returns the finished result once the run is done. C… - `url` (string): The page to run against. A bare domain like example.com is fine; https is assumed. Must be a public URL: anything behind a login, on a private network, or on localhost is refused. ### `check_robots_txt_for_ai` (~366 tokens) robots.txt AI Checker Test a site's robots.txt against every AI crawler that matters (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, Googlebot, Bingbot and the rest) and report which are allowed, which are blocked, and which rule decided it. Also runs a firewall test, because CDN-level blocks stop crawlers before robots.txt is ever read. This is the access-scoped view of check_ai_visibility. Returns { ok, report: { accessScore, crawlers[] with the rule that decided each verdict, firewall, findings[] }, cached, ageSeconds }. Limit: 10 runs per hour per IP. Allow up to 75s for a response. Free, no account, no API key. Pass `url` to start a run. A slow run answers with `{ status: "pending", runId }` instead of a result: call this same tool again with just that `runId` to collect it, as many times as it takes. Collecting costs no rate-limit slot. Input parameters: - `refresh` (boolean): Skip the 24 hour cache and run again. Costs a rate-limit slot even when a cached result exists, so leave it off unless the page has changed. - `runId` (string): Collect a run that answered with `{ status: "pending", runId }` instead of a result. Send the runId back on its own, with no url, and the same tool returns the finished result once the run is done. C… - `url` (string): The page to run against. A bare domain like example.com is fine; https is assumed. Must be a public URL: anything behind a login, on a private network, or on localhost is refused. ### `generate_llms_txt` (~362 tokens) llms.txt Generator Generate llms.txt and llms-full.txt for a site, following the llmstxt.org convention. Inventories the site from its robots.txt, sitemaps, and homepage links, then writes an index file and a full file with page content inlined. Deterministic: no model is involved, so two runs over an unchanged site produce the same bytes. Returns the file contents ready to write to disk. Returns { ok, report: { siteName, llmsTxt, llmsFullTxt, pagesDiscovered, pagesIncluded, truncated }, cached, ageSeconds }. Limit: 10 runs per hour per IP. Allow up to 75s for a response. Free, no account, no API key. Pass `url` to start a run. A slow run answers with `{ status: "pending", runId }` instead of a result: call this same tool again with just that `runId` to collect it, as many times as it takes. Collecting costs no rate-limit slot. Input parameters: - `refresh` (boolean): Skip the 24 hour cache and run again. Costs a rate-limit slot even when a cached result exists, so leave it off unless the page has changed. - `runId` (string): Collect a run that answered with `{ status: "pending", runId }` instead of a result. Send the runId back on its own, with no url, and the same tool returns the finished result once the run is done. C… - `url` (string): The page to run against. A bare domain like example.com is fine; https is assumed. Must be a public URL: anything behind a login, on a private network, or on localhost is refused. ### `page_to_markdown` (~326 tokens) Markdown for Agents Fetch one web page and convert it to clean CommonMark, with the navigation, cookie banners, and boilerplate stripped out. Use this to read a page as text an agent can reason over, or to publish a .md copy of a page alongside the HTML. Returns { ok, report: { markdown, title, description, wordCount, bytes, truncated, httpStatus }, cached, ageSeconds }. Limit: 10 runs per hour per IP. Allow up to 75s for a response. Free, no account, no API key. Pass `url` to start a run. A slow run answers with `{ status: "pending", runId }` instead of a result: call this same tool again with just that `runId` to collect it, as many times as it takes. Collecting costs no rate-limit slot. Input parameters: - `refresh` (boolean): Skip the 24 hour cache and run again. Costs a rate-limit slot even when a cached result exists, so leave it off unless the page has changed. - `runId` (string): Collect a run that answered with `{ status: "pending", runId }` instead of a result. Send the runId back on its own, with no url, and the same tool returns the finished result once the run is done. C… - `url` (string): The page to run against. A bare domain like example.com is fine; https is assumed. Must be a public URL: anything behind a login, on a private network, or on localhost is refused. ### `generate_json_ld` (~339 tokens) JSON-LD Generator Read a page and write a schema.org JSON-LD block for it, then validate that block against the same checks a validator would run. The markup is model-written from the page's own content and should be reviewed before it is published. Returns the block ready to paste into a