# HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits (remote · hubvibe-io.com) Pay per call via HTTP 402: 5 site audits + 38 /work jobs as MCP tools and A2A skills, receipts - Trust score: 76/100 (medium) - Change this week: +3 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-25 ## Components - remote · `hubvibe-io.com`: 76/100 (this document), [markdown](https://verifymcp.io/servers/its-fortunatefolly-hubvibe/hubvibe-io.md), [page](https://verifymcp.io/servers/its-fortunatefolly-hubvibe/hubvibe-io) ## Channel facts - Endpoint: `https://hubvibe-io.com/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.5.0` ## 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 2026-09-25. - **Endpoint Security**: 74/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - 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**: 78/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 4713 tokens (~109/item across 43 items; 43 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 43/100 - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 93/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 74% of tool parameters carry a description. - Structured output schemas are declared (100% of tools); any adoption earns full credit. - **Tool Safety**: 75/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "hubvibe_data_query" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. - An AI judge read all 44 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits MCP server? HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits is a hosted endpoint at https://hubvibe-io.com/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 its-fortunatefolly-hubvibe 'https://hubvibe-io.com/mcp' ``` ### Cursor ```json { "mcpServers": { "its-fortunatefolly-hubvibe": { "url": "https://hubvibe-io.com/mcp" } } } ``` ### VS Code ```json { "servers": { "its-fortunatefolly-hubvibe": { "type": "http", "url": "https://hubvibe-io.com/mcp" } } } ``` ### Codex ```toml [mcp_servers.its-fortunatefolly-hubvibe] url = "https://hubvibe-io.com/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "its-fortunatefolly-hubvibe": { "type": "remote", "url": "https://hubvibe-io.com/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add its-fortunatefolly-hubvibe --url 'https://hubvibe-io.com/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: its-fortunatefolly-hubvibe: url: "https://hubvibe-io.com/mcp" ``` ### Netclaw ```json { "McpServers": { "its-fortunatefolly-hubvibe": { "Transport": "http", "Url": "https://hubvibe-io.com/mcp" } } } ``` ### Vellum ```bash assistant mcp add its-fortunatefolly-hubvibe -t streamable-http -u 'https://hubvibe-io.com/mcp' ``` ### Other ```json { "mcpServers": { "its-fortunatefolly-hubvibe": { "type": "http", "url": "https://hubvibe-io.com/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. ### 2026-09-25 (score 76, +1) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-09-24 (score 75, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [functional regression] Tool coverage: 100% → 74% - [functional improvement] Schema quality: 190 → 109 - [functional] Destructive annotations: pass → 0 - [functional] Server version: 1.4.2 → 1.5.0 - [functional] New tool “hubvibe_maps_places” - [functional] New tool “hubvibe_chain_address” - [functional] New tool “hubvibe_chain_network” - [functional] New tool “hubvibe_chain_rpc” - [functional] New tool “hubvibe_chain_transaction” - [functional] New tool “hubvibe_code_execute” - [functional] New tool “hubvibe_data_anomalies” - [functional] New tool “hubvibe_data_forecast” - [functional] New tool “hubvibe_data_query” - [functional] New tool “hubvibe_data_question” - [functional] New tool “hubvibe_extract_page” - [functional] New tool “hubvibe_fetch_raw” - [functional] New tool “hubvibe_image_generate” - [functional] New tool “hubvibe_llm_analyze” - [functional] New tool “hubvibe_llm_extract” - [functional] New tool “hubvibe_llm_generate” - [functional] New tool “hubvibe_maps_route” - [functional] New tool “hubvibe_video_generate” - [functional] New tool “hubvibe_verify_claims” - [functional] New tool “hubvibe_speech_transcribe” - [functional] New tool “hubvibe_speech_synthesize” - [functional] New tool “hubvibe_security_mcp_inspect” - [functional] New tool “hubvibe_search_web” - [functional] New tool “hubvibe_research_web” - [functional] New tool “hubvibe_research_page_facts” - [functional] New tool “hubvibe_research_company” - [functional] New tool “hubvibe_research_brief” - [functional] New tool “hubvibe_prediction_market” - [functional] New tool “hubvibe_prediction_events” - [functional] New tool “hubvibe_monitor_snapshot” - [functional] New tool “hubvibe_monitor_check” - [functional] New tool “hubvibe_market_ticker” - [functional] New tool “hubvibe_market_rates” - [functional] New tool “hubvibe_market_quote” - [functional] New tool “hubvibe_market_prediction” - [functional] New tool “hubvibe_market_intel” - [functional] New tool “hubvibe_maps_weather” ### 2026-09-23 (score 75, −1) - [security] The server rewrote its instructions, which are the text every model session reads - [functional regression] Schema quality: 137 → 190 - [functional] Server version: 1.4.1 → 1.4.2 - [functional] New tool “hubvibe_predictive_probability_engine” ### 2026-09-22 (score 76, 0) - [functional] Server version: 1.4.0 → 1.4.1 ### 2026-09-21 (score 76, +1) No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-19 (score 75, +2) - [security regression] Tool “web_fetch” was removed - [security regression] Tool “web_extract” was removed - [security regression] Tool “prediction_markets” was removed - [security regression] Tool “market_data” was removed - [security regression] Tool “chain_rpc” was removed - [functional improvement] Tool coverage: 68% → 100% - [functional improvement] Schema quality: 1280 → 687 - [functional] Server version: 1.3.0 → 1.4.0 ### 2026-09-18 (score 73, +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. ### 2026-09-17 (score 72, −1) - [functional regression] Tool coverage: 100% → 68% - [functional regression] Schema quality: 687 → 1280 - [functional] Server version: 1.2.0 → 1.3.0 - [functional] New tool “chain_rpc” - [functional] New tool “market_data” - [functional] New tool “prediction_markets” - [functional] New tool “web_extract” - [functional] New tool “web_fetch” ## MCP tools (43) ### `audit_wcag` (~148 tokens) Accessibility audit (WCAG 2.1 A/AA) Website accessibility audit (a11y, WCAG compliance check): WCAG 2.1 level A and AA conformance of any live URL or raw HTML, tested with axe-core in a real headless browser. Returns every violation with rule id, impact, help text and affected node count. Deterministic rules; a check that cannot run returns an error, never a pass. $0.05 per call. Returns: pass (bool), violations[] with id/impact/help/help_url/nodes_affected. Input parameters: - `html` (string): Raw HTML source to audit instead of fetching a URL. - `url` (string): Live, fetchable http(s) URL to audit. Output parameters: - `engine` (string) - `pass` (boolean): Whether every rule in this dimension passed. - `status` (string): Present only on a completed audit. - `violations` (array) ### `audit_seo` (~127 tokens) SEO and metadata audit SEO audit of a web page (on-page SEO check) for any live URL or raw HTML: title tag, meta description, H1 heading structure, canonical link, OpenGraph and social tags, JSON-LD structured data, html lang attribute. Rule-by-rule findings with severity and what is missing or malformed. $0.05 per call. Returns: pass (bool), findings[] with id/severity/detail. Input parameters: - `html` (string): Raw HTML source to audit instead of fetching a URL. - `url` (string): Live, fetchable http(s) URL to audit. Output parameters: - `findings` (array): One entry per rule that did not pass. Empty when the check is clean. - `pass` (boolean): Whether every rule in this dimension passed. - `status` (string): Present only on a completed audit. ### `audit_security` (~120 tokens) Security header audit Security headers check for a website: audits HTTPS, HSTS, Content- Security-Policy (CSP), X-Content-Type-Options, X-Frame-Options / clickjacking protection, Referrer-Policy and CORS from the real HTTP response of any live URL. Findings with severity for what is missing. Header posture only, not a penetration test. $0.05 per call. Returns: pass (bool), findings[] with id/severity/detail. Input parameters: - `url` (string, required): Live, fetchable http(s) URL to audit. Output parameters: - `findings` (array): One entry per rule that did not pass. Empty when the check is clean. - `pass` (boolean): Whether every rule in this dimension passed. - `status` (string): Present only on a completed audit. ### `audit_performance` (~100 tokens) Page performance audit Page speed and page weight audit of a web page from one real browser load: total bytes transferred, HTTP request count and DOM node count, measured rather than estimated, with findings when the page is heavy. Page-weight signals, not Core Web Vitals. $0.05 per call. Returns: pass (bool), metrics{}, findings[] with id/severity/detail. Input parameters: - `url` (string, required): Live, fetchable http(s) URL to audit. Output parameters: - `findings` (array): One entry per rule that did not pass. Empty when the check is clean. - `metrics` (object) - `pass` (boolean): Whether every rule in this dimension passed. - `status` (string): Present only on a completed audit. ### `audit_bundle` (~113 tokens) Full site compliance bundle (all four audits) Full website audit in one call: accessibility (WCAG 2.1 A/AA via axe-core), on-page SEO, HTTP security headers and page speed / page weight, from a single browser load of one URL. Cheaper than four separate calls; if any part cannot run, nothing is billed. $0.15 per call. Returns: pass (bool) plus wcag{}, seo{}, security{}, performance{} sub-results. Input parameters: - `url` (string, required): Live, fetchable http(s) URL to audit. Output parameters: - `pass` (boolean): Whether every rule in this dimension passed. - `performance` (object) - `security` (object) - `seo` (object) - `status` (string): Present only on a completed audit. - `wcag` (object) ### `hubvibe_predictive_probability_engine` (~449 tokens) Predictive probability engine: regression, normal model, p-values Deterministic statistics over (x, y) points: ordinary least squares linear regression with standard errors and confidence intervals, a fitted normal distribution with quantiles and probability queries, exact Student t and Jarque-Bera p-values validated at your alpha, and predictions with prediction intervals. Points come inline or from a BigQuery table (two numeric columns; above max_rows the rows are chosen by fingerprint, never at random). Pure arithmetic with exactly rounded sums: the same input always returns the same numbers, and no LLM is anywhere in the path. $0.50 per call. Returns: source{}, n, alpha, confidence_level, metrics[], linear_regression{}, normal_distribution{}, p_values{}, prediction[], notes[], method. Input parameters: - `alpha` (number): Significance level for p-value validation and intervals. Default 0.05. - `distribution_of` (string): Which values the normal model fits. Default y. - `max_rows` (integer): Rows to read from `table`, default 10000. A larger table is reduced to this many rows by FARM_FINGERPRINT order, so the same table always yields the same rows. - `metrics` (array): Which results to compute. Default: linear_regression, normal_distribution and p_values, plus prediction when predict_x is given. - `points` (array): The data: [x, y] pairs (or {x, y} objects), 2 to 100000 of them; at least 3 for a regression. Use this OR `table`. - `predict_x` (array): x values to predict y at, with mean and prediction intervals. - `probability_queries` (array): Probabilities to read off the fitted normal model: {"below": v}, {"above": v} or {"between": [a, b]}. - `table` (string): BigQuery table to read instead of `points`: project.dataset.table, readable by the node's service account (public datasets are). Needs x_column and y_column. - `x_column` (string): Numeric column for x, with `table`. - `y_column` (string): Numeric column for y, with `table`. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_chain_network` (~64 tokens) Base network state Current Base mainnet block height and gas price, read live from a Base RPC node. Use to check chain liveness or time an on-chain action. $0.02 per call. Returns: block_number, gas_price_wei, gas_price_gwei. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_chain_address` (~89 tokens) Base address report Everything about one Base mainnet address in a single call: ETH balance, transaction count, and whether it is a contract or an externally owned account. Three chain reads folded into one answer. $0.05 per call. Returns: balance_wei, balance_eth, transaction_count, is_contract, code_size_bytes. Input parameters: - `address` (string, required): 0x-prefixed Base address. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_chain_transaction` (~80 tokens) Base transaction lookup One Base mainnet transaction with its receipt folded in: sender, recipient, value, block, success or failure, and gas actually used. $0.05 per call. Returns: from, to, value_eth, block_number, status, gas_used, log_count. Input parameters: - `hash` (string, required): 0x-prefixed transaction hash. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_market_quote` (~84 tokens) Crypto spot quote Live spot price and 24-hour change for any Coinbase product (BTC-USD, ETH-USD and the rest), from Coinbase's public market data. $0.02 per call. Returns: price, price_change_24h_pct, volume_24h, base/quote currency. Input parameters: - `product_id` (string, required): e.g. BTC-USD. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object): Live spot quote. - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_market_prediction` (~98 tokens) Prediction market probabilities Live prediction markets and the probabilities they currently imply, from Polymarket. Search by topic or take the highest-volume markets. Returns each outcome as a percentage, not a raw price. $0.05 per call. Returns: markets[] with question, implied_probabilities[], volume, end_date. Input parameters: - `limit` (integer): 1-50, default 10. - `query` (string): Topic to match (optional). Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_extract_page` (~87 tokens) Web page extraction Fetch any web page and return its readable text, title, description and links, rendered in a real browser so JavaScript-built pages extract correctly. Falls back to direct fetch when rendering is unavailable. $0.10 per call. Returns: title, description, text, text_chars, links[], javascript_rendered. Input parameters: - `url` (string, required): http(s) URL to fetch. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_llm_analyze` (~89 tokens) Analyse text Answer a specific question about text you supply, using Gemini. Answers only from the material given and says so explicitly when the material does not contain the answer, rather than guessing. $0.25 per call. Returns: answer, model, tokens{prompt,output}. Input parameters: - `question` (string): What to answer. Optional. - `text` (string, required): Material to analyse. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_llm_extract` (~84 tokens) Extract fields as JSON Pull named fields out of text and return them as a JSON object with exactly the keys you asked for. Fields the text does not state come back as null instead of being invented. $0.25 per call. Returns: fields{} with one key per requested field. Input parameters: - `fields` (array, required): Field names to extract. - `text` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_data_query` (~108 tokens) Run a BigQuery query Execute a read-only BigQuery SQL query, including against Google's public datasets, and get the rows back as JSON. Every query is dry-run first and refused if it would scan more than the byte ceiling, so cost is bounded before anything runs. $0.50 per call. Returns: columns[], rows[], row_count, gib_processed, cache_hit. Input parameters: - `max_scan_gib` (number): Optional scan ceiling. - `sql` (string, required): Read-only SELECT or WITH query. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_data_question` (~113 tokens) Answer a question from a dataset Ask a question in plain language about any BigQuery table, including Google's public datasets, and get a written answer with the SQL and the rows it came from. Writes the query, runs it under a byte ceiling, and reads the result back as an analysis. $5.00 per call. Returns: answer, sql, columns[], rows[], gib_processed. Input parameters: - `columns` (array): Optional column hints. - `question` (string, required) - `table` (string, required): Fully qualified: project.dataset.table. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_research_brief` (~106 tokens) Research brief on a URL Read any web page and get a written answer to your question about it. Renders the page in a real browser, extracts the content, and analyses it in one paid call. Answers only from the page, and says when the page does not contain the answer. $5.00 per call. Returns: brief, title, final_url, source{}, model. Input parameters: - `question` (string): Optional; defaults to an overview. - `url` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_research_page_facts` (~100 tokens) Structured facts from a URL Read any web page and return exactly the fields you name as JSON -- pricing, contact, product names, whatever you ask for. Fields the page does not state come back null rather than invented. Built for pipelines that need a fixed shape. $5.00 per call. Returns: fields{} with one key per requested field, plus title and final_url. Input parameters: - `fields` (array, required) - `url` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_market_intel` (~114 tokens) Market intelligence read Combine a live crypto spot quote with live prediction-market probabilities on the same subject and get them analysed together in one call. Market data and implied probabilities only -- not investment advice. $5.00 per call. Returns: spot{}, prediction_markets[], analysis, disclaimer. Input parameters: - `limit` (integer) - `product_id` (string): e.g. BTC-USD. Default BTC-USD. - `query` (string): Prediction-market topic. Optional. - `question` (string): Optional analysis question. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_search_web` (~69 tokens) Web search A live web search, answered from current Google Search results with the sources it used. Grounded, not the model's own memory. $0.10 per call. Returns: query, answer, sources[{url,title}], search_queries_used[], model. Input parameters: - `query` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_llm_generate` (~178 tokens) Raw text completion A raw completion from a large language model: your prompt, your system message, your provider and model choice among what this deployment has configured (Gemini; Claude on Vertex once Model Garden access is enabled). Unlike llm.analyze, nothing is prescribed about the shape of the answer. $0.25 per call. Returns: text, model, provider, finish_reason, usage{input_tokens,output_tokens}. Input parameters: - `max_tokens` (integer): 1-4096, default 1024. - `model` (string): Optional: a specific model from that provider. - `prompt` (string, required): The prompt. - `provider` (string): Optional: gemini or anthropic. - `system` (string): Optional system message. - `temperature` (number): 0-2, default 0.7. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_code_execute` (~68 tokens) Execute Python Run Python code in Google's own hosted sandbox and get the executed code, its output, and the outcome back. Not run in this service's own infrastructure. $0.25 per call. Returns: code, output, outcome, summary, model. Input parameters: - `code` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_image_generate` (~101 tokens) Generate an image Generate one image from a text prompt using Imagen 4. Returns the image as base64-encoded bytes. $0.50 per call. Returns: prompt, aspect_ratio, image_base64, mime_type, model. Input parameters: - `aspect_ratio` (string): 1:1, 3:4, 4:3, 16:9 or 9:16. Default 1:1. - `prompt` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_speech_synthesize` (~75 tokens) Text to speech Convert text to spoken audio (MP3) using Google Cloud Text-to-Speech. $0.25 per call. Returns: text_chars, voice, audio_base64, mime_type. Input parameters: - `text` (string, required) - `voice` (string): e.g. en-US-Standard-C. Optional. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_speech_transcribe` (~100 tokens) Speech to text Transcribe up to 60 seconds / 10MB of audio using Google Cloud Speech-to-Text. Longer audio is refused before payment; this is the synchronous API only. $0.25 per call. Returns: transcript, language_code, confidence, model. Input parameters: - `audio_base64` (string, required): Base64-encoded audio, any common format. - `language_code` (string): BCP-47, default en-US. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_data_forecast` (~145 tokens) Forecast a time series Forecast a time series in a BigQuery table with Google's pretrained TimesFM model (AI.FORECAST) -- no model to train. Point it at the table and the timestamp/value columns. $10.00 per call. Returns: table, timestamp_col, data_col, horizon, columns[], rows[], row_count, gib_processed. Input parameters: - `data_col` (string, required) - `horizon` (integer): Periods to forecast, default 10. - `id_cols` (array): Optional: forecast multiple series at once. - `max_scan_gib` (number) - `table` (string, required): project.dataset.table - `timestamp_col` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_data_anomalies` (~174 tokens) Detect anomalies in a time series Detect anomalies in a target table's time series against a history table, using AI.DETECT_ANOMALIES (TimesFM). Both tables share the same timestamp and value column names. $10.00 per call. Returns: history_table, target_table, timestamp_col, data_col, anomaly_prob_threshold, columns[], rows[], row_count, gib_processed. Input parameters: - `anomaly_prob_threshold` (number): 0.5-0.999, default 0.95. - `data_col` (string, required) - `history_table` (string, required): project.dataset.table - `id_cols` (array): Optional: one series per value of these columns. - `max_scan_gib` (number) - `target_table` (string, required): project.dataset.table - `timestamp_col` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_verify_claims` (~100 tokens) Verify claims against sources Check up to 10 specific claims against up to 4 specific source URLs. Each claim comes back SUPPORTED, CONTRADICTED or UNSUPPORTED, with the quote the verdict is based on. $5.00 per call. Returns: claims[], verdicts[{claim,verdict,quote,source_n}], sources_read[], sources_unread[], model. Input parameters: - `claims` (array, required) - `sources` (array, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_research_web` (~90 tokens) Research brief from live web search Answer a question from a live web search: search, read the top sources, and get a cited answer with every claim tied to [n] source numbers. $5.00 per call. Returns: question, answer, sources[{n,url,title}], partial[], model. Input parameters: - `max_sources` (integer): 1-4, default 3. - `question` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_research_company` (~100 tokens) Research and verify a company A research brief on a company from live web sources: what it does, its products, and anything notable, cited to [n] source numbers, with thin or conflicting evidence disclosed rather than papered over. $10.00 per call. Returns: company, report, sources[{n,url,title}], partial[], model. Input parameters: - `company` (string, required) - `max_sources` (integer): 1-4, default 4. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_monitor_snapshot` (~71 tokens) Save a monitoring baseline Fetch a page and save it as the baseline for monitor.check. Call this once, then monitor.check later to see what changed. $0.50 per call. Returns: url, title, text_chars, content_hash, note. Input parameters: - `url` (string, required): http(s) URL to fetch. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_monitor_check` (~71 tokens) Check a page against its baseline Re-fetch a page monitor.snapshot was called on, and get back whether it changed and a summary of what changed. $0.50 per call. Returns: url, title, changed, baseline_age_seconds, change_summary, model. Input parameters: - `url` (string, required): http(s) URL to fetch. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_security_mcp_inspect` (~92 tokens) Inspect an MCP endpoint Probe a customer-specified MCP server's initialize handshake and tools/list: whether it requires authentication, what protocol version it speaks, and which of its tools are not marked read-only. $5.00 per call. Returns: reachable, requires_auth, protocol_version, tool_count, tools[], tools_without_readonly_annotation[]. Input parameters: - `url` (string, required): http(s) URL to fetch. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_fetch_raw` (~101 tokens) Raw HTTP fetch Fetch any URL and get back exactly what the server sent: status code, headers, and body. Unlike extract.page, every status code is a result, not a failure -- a 404 or 500 from the target is delivered as one. $0.10 per call. Returns: url, final_url, status, content_type, bytes, text, truncated, headers{}. Input parameters: - `url` (string, required): http(s) URL to fetch. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_chain_rpc` (~117 tokens) Base RPC passthrough A generic allowlisted read-only JSON-RPC call to Base mainnet: your method, your params. A JSON-RPC error (a revert reason, 'block not found') comes back as the result, not a failure -- it is the chain's own answer to exactly this call. $0.05 per call. Returns: method, result or error, endpoint. Input parameters: - `method` (string, required): e.g. eth_call, eth_getLogs. - `params` (array): JSON-RPC positional params. Default []. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_market_rates` (~59 tokens) Currency exchange rates Coinbase's exchange-rate table for one base currency against every currency it quotes -- crypto and fiat. $0.02 per call. Returns: currency, rates{}. Input parameters: - `currency` (string, required): e.g. USD, ETH, BTC. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_market_ticker` (~80 tokens) Crypto ticker Live bid, ask and volume for one Coinbase product, from an independent market-data host to market.quote -- a genuine second source, not the same read twice. $0.02 per call. Returns: product_id, price, bid, ask, volume, time. Input parameters: - `product_id` (string, required): e.g. BTC-USD. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_prediction_market` (~67 tokens) Prediction market by slug One named Polymarket market, looked up by its exact slug, with its current implied probabilities. $0.05 per call. Returns: slug, market{question,implied_probabilities[],...}. Input parameters: - `slug` (string, required): The market's Polymarket slug. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_prediction_events` (~67 tokens) Prediction market events Live Polymarket events -- groupings of related markets -- ranked by volume. $0.05 per call. Returns: events[{id,title,slug,volume,end_date,market_count}], count. Input parameters: - `limit` (integer): 1-50, default 10. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_maps_places` (~117 tokens) Search places Search for places -- businesses, addresses, points of interest -- via Google's managed Maps Grounding Lite MCP server. Requires the operator to enable the Maps Grounding Lite API and set a key; unavailable until then. $0.10 per call. Returns: query, result (places found, per Maps Grounding Lite's own shape). Input parameters: - `query` (string, required): What to find, e.g. 'coffee near the Ferry Building'. - `region_code` (string): Optional ISO 3166-1 alpha-2 bias. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_maps_route` (~93 tokens) Compute a route Directions and travel time between two places, via Google's managed Maps Grounding Lite MCP server. $0.10 per call. Returns: origin, destination, travel_mode, result (route, per Maps Grounding Lite's own shape). Input parameters: - `destination` (string, required) - `origin` (string, required) - `travel_mode` (string): DRIVE, WALK, BICYCLE or TRANSIT. Default DRIVE. Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_maps_weather` (~61 tokens) Weather at a location Current or forecast weather at a named place, via Google's managed Maps Grounding Lite MCP server. $0.10 per call. Returns: location, result (weather, per Maps Grounding Lite's own shape). Input parameters: - `location` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ### `hubvibe_video_generate` (~141 tokens) Generate a video Generate a short video from a text prompt using Veo. Off by default: enabled only once the operator has confirmed the configured Veo model resolves on this project (see the provider module for why). $10.00 per call. Returns: prompt, aspect_ratio, duration_seconds, video_base64 or gcs_uri, mime_type, model. Input parameters: - `aspect_ratio` (string): 16:9 or 9:16. Default 16:9. - `duration_seconds` (integer): 4, 6 or 8. Default 6. - `generate_audio` (boolean): Default false. - `prompt` (string, required) Output parameters: - `billing_warning` (string): Present only when the charge was recorded with a caveat. - `price_usd` (number): What this call cost, in USD. - `provenance` (object): How the result was produced: which providers ran and how long each took. - `receipt_id` (string): Receipt id for this job. - `receipt_url` (string): Where to fetch the machine-readable receipt (free, no payment). - `result` (object) - `status` (string): Present only on a delivered result. - `worker` (string): Catalog name of the worker that ran. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/its-fortunatefolly-hubvibe/hubvibe-io#diagnostics ## Score history - 2026-09-25: 76 - 2026-09-24: 75 - 2026-09-23: 75 - 2026-09-22: 76 - 2026-09-21: 76 - 2026-09-20: 75 - 2026-09-19: 75 - 2026-09-18: 73 - 2026-09-17: 72 - 2026-09-16: 73 - 2026-09-15: 73 - 2026-09-14: 73 - 2026-09-13: 72 - 2026-09-12: 72 ## Common questions ### What is the HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits MCP server? HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits is an MCP server listed in the public MCP registry as io.github.Its-fortunatefolly/hubvibe. Pay per call via HTTP 402: 5 site audits + 38 /work jobs as MCP tools and A2A skills, receipts. This page covers its hosted endpoint (https://hubvibe-io.com/mcp). ### Is the HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits MCP server safe to use? HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits scores 76 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 HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits MCP server expose? HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits exposes 43 tools: audit_wcag, audit_seo, audit_security, audit_performance, audit_bundle, and 38 more. Their descriptions and schemas cost roughly 4,610 tokens of context every time the server is loaded. ### Does the HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits MCP server require authentication? No. We connected to HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits MCP server still maintained? HubVibe: 38 Machine-Payable Dev Utilities and WCAG Audits is still listed as active in the MCP registry. We last reached this channel on 25 September 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://hubvibe-io.com/mcp - Repository: https://github.com/Its-fortunatefolly/HubVibe - Website: https://hubvibe-io.com/ - Changelog RSS feed: https://verifymcp.io/servers/its-fortunatefolly-hubvibe/hubvibe-io.xml - Changelog JSON feed: https://verifymcp.io/servers/its-fortunatefolly-hubvibe/hubvibe-io.json - HTML version of this page: https://verifymcp.io/servers/its-fortunatefolly-hubvibe/hubvibe-io