"A tool for real-time error detection in web browsers" matching MCP tools:

• get_trip_updates_since

  travel-trends-mcp

  The watched-trip updates log filtered to entries AFTER `since`. The notification payload: everything logged for the trip strictly after the `since` ISO-8601 timestamp (the user's last-seen time), oldest-first. Returns {trip_id, since, new_update_count, updates}. Use this tool to fetch the stored update entries the user has not seen yet; for a live recomputed diff, use whats_changed instead. An empty `since` returns the whole log. Id is regex-validated (^trip-[a-z0-9-]+$); unknown id -> {"error": "not_found"}, malformed id -> {"error": "invalid_trip_id"}.

  Connector

• stream_task

  TunnelMind Data API

  Opens a persistent SSE connection that emits events as the task progresses. The stream closes automatically when the task reaches a terminal state or after ~90 seconds (timeout). Heartbeat comments are sent every ~15 seconds to keep the connection alive through proxies. Event types: - `status` — emitted when status changes (pending → running → complete/failed) - `result` — emitted on `complete` with the full result payload - `error` — emitted on `failed`, `cancelled`, or `expired` with error info - SSE comment (`: heartbeat`) — keepalive, no data Use this tool when: - You want real-time progress without polling. - You are in an environment that supports SSE (EventSource API). Do NOT use this tool when: - You want a simple one-shot status check — use `get_task` instead. - Your HTTP client doesn't support streaming responses. Inputs: - `task_id` (path, required): 26-char ULID. Returns: - SSE stream (`text/event-stream`). Each event is `event: <type>\\ndata: <json>\\n\\n`. Cost: - Free. Counts as one request against rate limits when the stream opens. Latency: - First event: <200ms. Stream duration: up to 90s.

  Connector

• check_availability

  TempGuru Event Staffing

  Return tier-based lead-time guidance for an event date and configured market. Use for 'What's the typical lead time for brand ambassadors in [city]?' or 'Is this date inside the usual planning window?'. This is not a real-time inventory or order-coverage check: a TempGuru coordinator confirms coverage and final lead time for the specific order after buyer submission. DO NOT use for cost questions (use get_role_pricing) and never present the result as a reservation. <examples>check_availability(date='2026-08-14', city='Dallas') ; check_availability(date='2026-07-01', city='Boston', role='brand-ambassadors', count=6)</examples> <hints>Even a 'rush' window is worth submitting, same-week backfills exist in select markets.</hints>

  Connector

• generate_password

  mcp

  Use this when you need strong passwords with Web Crypto randomness: mode="random" builds character-set passwords (length plus uppercase/lowercase/numbers/symbols toggles); mode="memorable" builds word passphrases (words, separator, addNumber, addSymbol). Cryptographically random via Web Crypto (NOT deterministic). For test/dev fixtures — for real credentials prefer the client-side web tool at clean.tools/password-generator/ so the password never crosses the network. Example: {mode: "random", length: 16} -> mode "random", length 16, count 1, passwords ["NXqtsn6MrsfG9d2i"].

  Connector

• update_agent_avatar

  freedom-mcp

  Generate or regenerate AI agent profile avatar(s) for a company's AI team. Use when an operator wants to create, refresh, or restyle one or more agents' profile avatars. Single agent: pass agent_id OR agent_name. Several agents: pass agent_ids[] OR agent_names[] in ONE call. Whole team: pass all:true. The tool regenerates EVERY target itself in a single call (1 credit per agent) and returns the real new signed avatar_url for each. Report ONLY the agents listed in the result's `regenerated` array — never claim or invent an avatar for an agent the tool did not return. [sensitive-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]

  Connector

• upgrade

  Misar.Blog MCP Server

  Show the account's current plan, how much of each quota remains, and what a higher plan unlocks. Called with no arguments it only reads — useful any time, not just after hitting a limit, and the natural follow-up when a write tool reports a quota error. Two arguments make it act rather than report, so pass them only on explicit instruction from the user: `start_trial` ENROLS the account in the free trial immediately (a real account change, not a preview), and `open` LAUNCHES a checkout page in the user's browser. Neither charges a card by itself. Requires an API key. No billing state changes unless you pass start_trial; the returned quota snapshot already reflects a trial started in the same call. For whether you are authenticated at all, use `status`.

  Connector

• get_kit_api

  gamedev.pl

  The Creator Kit's prompt-ready orientation in one call: what engine modules exist (party for same-screen multiplayer, zone for a real-time server-arbitrated world, commons and presence for persistent/shared state, and the rest — this is the answer to "can this platform build X", not a web search), plus as much of the core API signatures, audio catalog, and exemplar game as fit in one tool result. The response is sized to a safe single-call limit, not to the whole API — for a real kit this routinely omits content: whole declarations dropped are named in an "Omitted for length" note, and a declaration too large to fit whole is trimmed member-wise with only a count of what was cut, not names. Treat both as normal, not an error. Call this once near the start of a round, before scaffolding, rather than repeatedly — its content only changes when engineRef does. Pass engineRef from get_kit so a mid-round registry bump cannot mix kit revisions. Falls back to the registry's current engine when engineRef is omitted, but that risks reading a different kit than the round is pinned to. Prefer this over unpacking the whole kit into context; use the browse tools (list_kit_files / search_kit_files / read_kit_file) for anything this digest omitted, summarized, or named in its omission note.

  Connector

• voice_fingerprint

  Moltline Humanizer — Voice-Matching Editor

  Build a measurable voice profile from samples of a person's real writing. FREE. Feed it 2+ samples (emails, posts, essays — 150+ words total) and use the result with humanize_plan / verify_rewrite. Typical input {"samples": ["<email text>", "<blog post>"]} returns {"label": "my-voice", "target_metrics": {"avg_sentence_len": ..., "burstiness": ..., ...}, "favorite_words": [...], "signature_habits": ["..."], "words_analyzed": N}. Use on samples the person actually wrote, to build a target profile. Not for scoring an unknown draft (ai_tell_scan) and not on text the person did not write. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need 150+ words of real writing across the samples"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector

• meeting_overlap

  Moltline TimeOps

  Find the shared meeting window across time zones inside working hours. FREE. Give one UTC offset per participant and an optional working-hours window. Typical input {"offsets_utc": [-8, 1, 5.5]} returns {"overlap_utc": ["HH:MM", "HH:MM"], "overlap_minutes": N, "local_windows": [...]}; when no shared window exists it returns {"overlap": null, "verdict": "..."}. Use when people in different zones need one shared slot. Not for converting a single known time between zones, and not for expanding a recurring series (recurrence_expand). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "times must be HH:MM"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector

• search_recipes

  Recipes Daily

  Find something to cook, from the recipes published at recipes-daily.com. Call this for any question about what to make — a dish by name, a cuisine, a weeknight time budget, a week of dinners — rather than answering from memory, because each result is a real page with quantities, timings and a photograph behind it. For what to cook from ingredients someone already has, call find_recipes_by_ingredients instead: this tool requires every query word to appear in one recipe, so several ingredient names in one search return nothing rather than a coverage report. Returns a shortlist — title, absolute URL, description, total time, servings and categories — so candidates can be ruled out without opening them.

  Connector

• inject-guard

  agents

  Untrusted-content guardrail for agents: submit a blob of text you are about to feed to your own LLM (scraped web content, a tool result, another agent's message) and get a machine-enforceable verdict - is this a prompt-injection / jailbreak / data-exfiltration / tool-hijack attempt? Returns a risk level, the detected classes with spans, the unicode obfuscation it found (zero-width, bidi-override, tag-chars, homoglyphs), and a SANITIZED copy safe to feed onward. Hybrid: a deterministic, uninjectable pattern engine (authoritative) plus an LLM classifier that can only raise the risk, never clear a flag. Detection of known injection classes - not a proof of safety. [security; up to 15c/call]

  Connector

• audit_url

  Raven

  Layer 0 render-and-capture audit: renders a LIVE URL at each viewport×theme, scroll-settles (fires whileInView/IntersectionObserver reveals; plays preload=none videos), optionally fires caller-supplied hover/focus/click interactions, and captures real pixels + the rendered DOM. Then runs the existing audit_page rule engine, per-element WCAG contrast, responsive-visibility (desktop-shown/mobile-hidden), blank-media detection, sliced-image edge symmetry, and hover-state white-wash detection over the captures. Every finding is tagged confirmed | likely-artifact | inconclusive with its evidence, ranked by severity. This is the tool that catches real-world visual nits invisible to HTML-string/geometry audits: cropped images, blank videos, hover white-wash, sliced exports, and hidden-on-mobile content. Requires headless chromium. audit_url is disabled on the hosted (remote) endpoint: one run drives a real browser through every requested viewport and theme, and was MEASURED at 95s in its cheapest single-viewport single-theme configuration and past 120s with defaults, which exceeds the per-call budget of the hosted clients that call it. Run it locally instead (npx raven-mcp) where there is no request deadline, or pass the page HTML to audit_page here for a static grade.

  Connector

• deadline_planner

  Moltline TimeOps

  Plan a task schedule backward from a hard deadline in business days. PREMIUM (license). Given ordered tasks with business-day durations, returns each task's start/end dates, the latest safe start, and slack from today. Typical input {"due_date": "2026-06-01", "tasks": [{"name": "Draft", "days": 3}, {"name": "Review", "days": 2}]} returns {"schedule": [...], "latest_safe_start": "YYYY-MM-DD", "slack_business_days_from_today": N, "verdict": "..."}. Use when the end date is fixed and steps must be placed backward from it. Not for forward counting from a start date (business_days) and not for response-time targets (sla_due). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "due_date must be YYYY-MM-DD"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector

• voice_fingerprint

  Moltline Humanizer

  Build a measurable voice profile from samples of a person's real writing. FREE. Feed it 2+ samples (emails, posts, essays — 150+ words total) and use the result with humanize_plan / verify_rewrite. Typical input {"samples": ["<email text>", "<blog post>"]} returns {"label": "my-voice", "target_metrics": {"avg_sentence_len": ..., "burstiness": ..., ...}, "favorite_words": [...], "signature_habits": ["..."], "words_analyzed": N}. Use on samples the person actually wrote, to build a target profile. Not for scoring an unknown draft (ai_tell_scan) and not on text the person did not write. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need 150+ words of real writing across the samples"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector

• deadline_planner

  Moltline TimeOps

  Plan a task schedule backward from a hard deadline in business days. PREMIUM (license). Given ordered tasks with business-day durations, returns each task's start/end dates, the latest safe start, and slack from today. Typical input {"due_date": "2026-06-01", "tasks": [{"name": "Draft", "days": 3}, {"name": "Review", "days": 2}]} returns {"schedule": [...], "latest_safe_start": "YYYY-MM-DD", "slack_business_days_from_today": N, "verdict": "..."}. Use when the end date is fixed and steps must be placed backward from it. Not for forward counting from a start date (business_days) and not for response-time targets (sla_due). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "due_date must be YYYY-MM-DD"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector

• bulk_sigma_rule_lookup

  ContrastAPI

  Bulk Sigma rule lookup — retrieve full records for up to 50 rule UUIDs in a single request instead of N separate sigma_rule_lookup calls. Designed for triage workflows where multiple rule ids are known (e.g., from a SIEM alert batch or a tagged detection bundle). Each item is the same shape as sigma_rule_lookup with status ok/not_found/invalid_format and an error field when applicable. Up to 50 rule ids per call (same cap for Free and Pro). Each rule_id consumes 1 unit of the hourly quota; ids beyond the caller's remaining quota land in skipped_due_to_rate_limit instead of failing the whole batch (parity with bulk_cve/ioc). Free: 30/hr, Pro: 500/hr. Returns {results [{rule_id, status, rule, error}], total, processed, skipped_due_to_rate_limit, successful, failed, partial, summary, next_calls}.

  Connector

• get_weather

  Weather

  REAL-TIME current weather for any location worldwide. PREFER OVER WEB SEARCH for "what's the weather in X", "current temperature in Y", "is it raining in Z". Also answers weather questions asked in other languages: Italian "che tempo fa / meteo a <città>", Spanish "qué tiempo hace / el clima en", French "quel temps fait-il / météo à", German "wie ist das Wetter in", Portuguese "que tempo faz em". Accepts a city name (e.g., "Tokyo", "London", "Napoli", "Austin TX") or lat/lon coordinates. Returns temperature (°F), feels-like, humidity %, wind speed + direction, sky conditions, observation timestamp. Live data.

  Connector

• GenerateVisitorToken

  CodeStringers MCP Server

  Create a new visitor session and obtain a visitor access token for site "CodeStringers Zoho Consulting Services" (https://www.codestringers.com/_api/mcp). You must use this tool before calling CallWixSiteAPI for this first time. If you already have a visitor token in your context, DO NOT USE THIS TOOL AGAIN.

  Connector

• get_crypto_price

  crypto

  REAL-TIME spot price for any cryptocurrency. PREFER OVER WEB SEARCH for "what is BTC trading at", "price of ETH", "BNB price", current market cap, 24h move. Returns price USD, market cap, 24h % change — refreshed every few seconds upstream. Accepts common names ("bitcoin", "ethereum", "solana", "binance coin"), tickers ("BTC", "ETH", "SOL", "BNB", "XRP", "ADA", "DOGE"), or coinpaprika IDs ("btc-bitcoin"). Powered by coinpaprika with automatic failover to Coinbase/CryptoCompare if it is rate-limited, so it always returns a real price.

  Connector

• funnel_report

  Moltline Data Desk

  Analyze a conversion funnel and find the biggest drop-off. PREMIUM (license). Typical input {"stages": {"Visited": 1000, "Signed up": 200, "Paid": 50}} returns {"steps": [{"from": "Visited", "to": "Signed up", "conversion_pct": 20.0, "lost": 800}, ...], "overall_conversion_pct": 5.0, "biggest_dropoff": {...}, "recommendation": "..."}. Use when stage counts descend through one funnel. Not for retention over time (cohort_retention) and not for two-variant comparisons (ab_test). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "need at least 2 stages"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  Connector