Skip to main content
Glama
811,251 tools. Updated 2026-11-20 10:34

"How to export LLM chat history from multiple domains" matching MCP tools:

  • Who am I? Returns the signed-in account: email, @handle, plan + limits, counts of sites/domains/drives, and connected DNS providers. Call this first to orient before managing sites or domains.
    ConnectorNo auth
  • Bind the client's own domain to this tenant's chat pages: `https://chat.client.com/` serves the tenant's branded page (or a specific agent's chat), the address bar keeps the client's domain, and the TLS certificate is issued automatically. **Have the client configure DNS first**: add a CNAME at their DNS provider pointing to the `cname_target` in the response (`endpoint.agent4.io`). Key points: - **Subdomains only** (`chat.client.com`). An apex domain (`client.com`) cannot carry a CNAME — have the client use a subdomain, or a DNS provider with CNAME flattening (Cloudflare etc.). - **Cloudflare users must set the record to DNS only (grey cloud)**. With the proxy on (orange cloud) the name resolves to Cloudflare's addresses, verification fails, and `last_error` says so. - Verification is **asynchronous**: checked once immediately on binding; if DNS hasn't propagated it stays `pending` and is re-checked every 10 minutes (calling this tool again also re-triggers). `status` = `active` means live; the certificate is issued on first visit. - **One** domain per tenant; changing the domain re-runs verification, changing only `agent_alias` does not. - Requires a plan that includes custom domains (403 = upgrade needed). `agent_alias` empty → the domain lands on the tenant's branded page (listing available agents); set to an agent's public alias → lands directly on that agent's chat page.
    ConnectorNo auth
  • List body composition entries within a date range. Use when the user asks about their weight history, body fat trend, or any body metrics over time. Maximum range: 31 days per call. For longer periods, make multiple calls with sequential date ranges. INFER — do not ask: - start_date: default to 30 days ago - end_date: default to today BMI in the output is derived from the user's canonical height and that day's resolved weight -- do not recompute it yourself.
    ConnectorOAuth
  • Check your pipeline check credit balance. Shows credits remaining, total purchased, total used, and lifetime free lookups count. Credits are consumed only when unknown domains run through the full analysis pipeline. Known domains (Tranco Top 100K) and cached domains (previously analysed by any Unphurl customer) are always free. If credits_remaining is 0, you can still check known and cached domains for free. To check unknown domains, purchase more credits using the "purchase" tool.
    ConnectorNo auth
  • Returns a paginated list of domains from the tracker database. Results are ordered alphabetically by domain name and support cursor-based pagination for full traversal. Filtering by category and minimum score allows targeted data extraction. Use this tool when: - You want to enumerate all known ad-tech or analytics domains above a risk threshold. - You need a dataset of tracker domains for offline analysis. - You are paginating through a category to build a block list. Do NOT use this tool when: - You need data for a specific domain — use `get_domain` instead. - You are searching by keyword — use `search` instead. - You want domains belonging to a specific company — use `get_entity` instead. Inputs: - `category` (query, optional): Filter by surveillance category. One of: `ad_tech`, `analytics`, `social`, `fingerprinting`, `content`, `cdn`, `other`. - `min_score` (query, optional): Integer 0-100. Exclude domains scoring below this value. - `limit` (query, optional): Number of results per page. Max 100 (paid), 20 (free). Default 50. - `cursor` (query, optional): Pagination cursor from the previous response's `next_cursor` field. Returns: - Array of domain list items (domain, category, score, prevalence, entity summary). - `meta.has_more`: true if more pages exist. - `meta.next_cursor`: pass as `cursor` to get the next page. - `meta.count`: number of results in this page. Cost: - Free tier: up to 20 results/page. Anonymous (no key): 10/min, 100/day. Free key: 50/day. Pro/enterprise: up to 100 results/page, included in plan. Latency: - Typical: <200ms, p99: <500ms.
    ConnectorNo auth
  • How has this on-chain metric moved over time? Returns the full TIME SERIES of one on-chain metric from the Bitcoin Research Kit — date/value pairs in ascending order, with history back to 2009 for most series. Use it for trend and percentile work; for the single current reading call arena_get_onchain_latest, and to discover valid series_ids call arena_list_onchain_series. Values are as-reported: on-chain metrics can be revised retroactively, so this is not a point-in-time vintage. Range capped by tier — the response carries a `range` block (requested_days, granted_days, clamped, clamp_reason, tier), so a clamped window announces itself instead of silently looking like the full history. [Free 30d / Pro 365d / Power unlimited]
    ConnectorNo auth

Matching MCP Servers

Matching MCP Connectors

  • Video how-to search for AI agents: 2,000+ video skills, tutorials and FFmpeg recipes. No key.

  • L'Ufficio Export di Wines Export dentro la tua chat: buyer, spedizioni, documenti.

  • FREE. Full catalog of Quantum Artificer: the 5 domains, their operations, input-spec shapes, limits, and prices. Call this first to learn how to build the `spec` for the paid compute tools. No wallet needed.
    ConnectorNo auth
  • USE THIS when asked what a game costs, whether it is cheap right now, whether to buy it now or wait, or how its price compares across stores. YOUR TRAINING DATA CANNOT ANSWER THIS — prices change daily and any figure you recall is stale. Do not answer from memory. Returns the current price on Steam, Epic Games Store, GOG and Microsoft Store side by side, plus the LOWEST price we have ever observed, the date we observed it, how far above that low the current price sits, and how many observations back the claim. History runs from 2012. Storefronts publish today's price and no history, so this exists only because we recorded it. Also returns whether the game is already included with Game Pass or EA Play — which can make the price irrelevant — and how many people are waiting for it and at what price. Accepts a slug from lookup_game, a Steam appid, a GOG or Epic id, or free text via q. Regions: US, GB, DE, BR. PAID (~$0.01) PER QUERY. Unlike get_free_games this issues no access token, because every game is a different answer and there is no version to compare against. Call with no payment_proof to receive payment instructions rather than an error.
    ConnectorNo auth
  • Delete EVERY object of one type from the user's graph, however many there are: what to reach for when they ask to clear out a whole category ('delete all my HubSpot contacts') rather than one record. Pass import_id instead to delete everything one import added (its contacts, companies, notes and files, the uploaded file and the import itself); imports are graph objects of type 'import_run'. Pass source 'linkedin_import' instead to delete every connection a LinkedIn export loaded and the people made from them. Deleting one object is delete_graph_object instead. This delete is permanent, and at this scale it is the only kind that helps: a synced portal can be millions of records. Use only when the user explicitly asked for these to go, never on your own initiative, and name one type, import or source per call. In chat this tool deletes nothing: it counts the records and returns what to tell the user, and their click starts the deletion.
    Connector
    Destructive
    No auth
  • Use this when the user wants to apply or discard multiple Autopilot/repository-sync suggestions at once. Destructive state-changing action: bulk apply can update multiple Space documents, and bulk discard removes suggestions from active review after authorization. Requires suggestion IDs from list-space-suggestions; bulk apply requires Enterprise access.
    Connector
    Destructive
    OAuth
  • Export the exact previewed owned ticket to Jira or Linear, using expected_export_hash from preview_ticket_export and the same destination. Requires explicit integrations:write, tickets:write, and independent human approval of the complete preview. Persists the operation before possible remote writes. After an uncertain response, inspect list_ticket_provider_effects and reconcile the original intent; never blindly export again. Remote confirmation is observed, not atomic protection against concurrent remote writers.
    ConnectorNo auth
  • Domain rank and Ahrefs DR only, for up to 1,000 domains in one call. The cheap way to rate a list. Use when: "rate these domains", "which of these sites are worth a link", filtering a prospect list by authority. Not for: traffic numbers, use seo_get_traffic_estimates (10x the cost). A full profile of one domain, use seo_get_domain_overview or seo_get_backlink_summary. Returns: List. rows[]: domain, domain_rank (0 to 1000 on DataForSEO, for the host as given; 0 for a domain the index does not know), ahrefs_dr (Ahrefs Domain Rating, 0 to 100, always for the registered domain, so www.github.com and gist.github.com both get github.com's; 0 for a domain Ahrefs does not know, null when it did not answer). One row per distinct domain, in the order first given: duplicates and case variants are merged, and a full URL is rated by its host. ahrefs_status says what a null ahrefs_dr means: ok (Ahrefs has no rating), partial (the domains in ahrefs_unanswered got no answer), failed or not_configured (Ahrefs did not answer; the null says nothing). ahrefs_attribution: wherever you show ahrefs_dr, show its text linked to its url next to it. errors[] lists inputs that were not valid domains. Cost: 7 + 2.5 per 100 domains, for domain_rank; ahrefs_dr adds nothing. Default 100 domains = 10 credits. Cached 7 days, or 1 hour when ahrefs_status is not ok. Example: {"targets": ["example.com", "competitor.com", "blog.example.net"]}
    ConnectorAPI key
  • Use this when the user wants to export their saved data center sites for offline analysis, a spreadsheet, or ingestion into another tool (needs a full-access key). Example: "Export my saved sites as GeoJSON for QGIS." — export_dataset format=geojson. Params: format ("csv" default, or "geojson"). Returns: the full file contents as text — CSV rows or a GeoJSON FeatureCollection of your saved sites with DCPI score, target MW, market, coordinates, and notes. Do NOT use to list sites in-chat (use list_saved_sites) or to save a new one (use save_site); this is the bulk-download path. For multi-step data center or energy questions, start with execute_plan.
    ConnectorNo auth
  • Records workouts the user has ALREADY FINISHED into their MoveMate history — "log yesterday's workout: bench 4x8 at 80 kg, squats 3x5 at 100", or a short history the user is moving over from notes or another app. Send whole sessions with the sets actually done, up to 20 workouts per call. Not a live tracker: if the user wants to log set by set while training, point them to the workout tracker in the MoveMate app (rest timer, weight suggestions) instead of calling this after every set. Dates: a workout from before the user joined MoveMate is history and may have any date; a workout from since they joined must be from today or the last 14 days. For a future date use create_planned_workout. At most 300 past workouts can be moved in through chat in total; for a longer history or an export file from another app (Hevy, Strong and others), tell the user about the workout import in the MoveMate app instead. Every exercise_id must come from search_exercises or create_custom_exercise — never invented. Each exercise is measured by its exercise_type (from search_exercises); send the fields that type uses: default = weight and reps (most strength work, and bodyweight work with reps such as pull-ups or hill sprints); time = duration only (planks, dead hangs, skipping); time_weight = duration and weight (weighted plank, farmer hold); distance_time = distance and duration (outdoor running, cycling or swimming, rowing machine, SkiErg — anything whose monitor shows distance rather than km/h); weight_distance = weight and distance (farmer walk, sled push); cardio_machine = speed in km/h, the machine level (incline or resistance) and duration — treadmill, stationary bike, stepmill; distance is derived from speed and time. Continuous cardio (cardio_machine, distance_time) is ONE set per session — a 20-minute treadmill walk is a single set of 1200 seconds, not three. If you had to guess any exercise, weight, rep count or date, read the workouts back and get the user's agreement before calling. Safe to retry: a workout already in the history (same date, start time and title) is not added twice. Free accounts can finish 3 workouts in total (in the app and here together); workouts from before they joined do not count. A refusal for that reason says so and must not be retried.
    ConnectorOAuth
  • Build a risk-optimized portfolio from a list of tickers — fast, synchronous, no LLM. THE DEFAULT optimizer route. Returns the result directly and almost instantly (no task id, no polling). Reach for `optimize_portfolio` instead only when you explicitly want the slower LLM-curated variant layered on top of the optimizers. Symbols are validated against the covered universe; unsupported tickers come back in `missing`, and in-universe tickers with too little price history come back in `dropped`. No auth required (public endpoint). Synchronous. Returns: {"status": "OK", # or "SKIPPED"/"EMPTY" when too few usable symbols remain "holdings": [{"symbol", "source_strategies", "summary", "conviction_level"}, ...], "optimizer_results": {"mvo": {...weights+diagnostics}, "hrp": {...}, "mcvar": {...}}, "risk_profiles": {"profiles": [...], "recommended": "..."}, # present only when status == "OK" "dropped": [...], # in-universe but insufficient price history "missing": [...]} # not in the covered universe
    ConnectorOAuth
  • List the raw conversion events recorded for the workspace (from the website SDK and server-to-server calls), most recent first, one row per event with its attribution uuids and its `properties` returned as recorded. Use it to verify that conversion tracking works, to read one visitor's event history (`distinct_id`) or to export rows. For counts, revenue or rankings use get_analytics_events_summary instead, which aggregates; for signature views and clicks use get_analytics_views / get_analytics_clicks; for visitor profiles use list_visitors. Events are ingested asynchronously, so one tracked seconds ago may not show yet. Read-only; needs the analytics:read scope and a plan with event tracking (403 otherwise). Returns one page (default 50, max 100); set `auto_paginate` to fetch up to `max_pages`, and `truncated: true` means more remain.
    ConnectorOAuth
  • Create a new question the till can ask, with its choices. THIS ALONE DOES NOTHING AT THE TILL — follow it with link_modifier_to_category, or the modifier sits unused. Choose selectionType carefully, because it CANNOT be changed afterwards: "single" = pick exactly one (milk, cooking temperature); "multiple" = tick any number of different choices (toppings); "multiple" with allowQuantity true = tick choices AND say how many of each; "quantity" = every choice is a stepper (extra shots). The last two count UNITS, not distinct choices. allowQuantity is only accepted on "multiple" and is refused on the others. Names must be unique for the merchant, ignoring case.
    ConnectorOAuth
  • Mark AccountHub chat messages you have shown the user as read — a one-to-one chat (only your incoming direct-message notices; shared project notices, likes and other notices are unchanged) or a group chat (a shared project: your read position moves up to the newest of these messages, never back). Pass the chat_id and the item_ids from read_chat / list_unread_chats. To read messages use read_chat; this only marks them read.
    ConnectorOAuth
  • Permanently delete a site — its subdomain row, all version snapshots, all content_items, all submissions, the alias history, attached custom domains (removed from Vercel), any active billing for the site (cancelled), and any media in the storage bucket. IRREVERSIBLE. Use this when the user explicitly asks to scrap a site (e.g. 'delete my-portfolio-3947, I don't want it' or 'I created the wrong template, throw it away'). Requires `confirm: true` to be deliberate. Do NOT call this on user-said-something-vague — ask 'are you sure you want to delete {subdomain} permanently?' first and only call after explicit yes. There is no undo. If the billing cancellation fails, the entire delete is aborted so the user is never charged for a deleted site.
    Connector
    Destructive
    OAuth
  • App-only adapter for the panel's Restore and Undo restore buttons, used after the user chooses a history entry. Replaces the current scene with a checkpoint and can discard subsequent manual or AI edits. Supply checkpoint_id or before_request_id from the history records. undo_restore also requires expected_current_checkpoint_id to reject a changed current scene. Returns updated history and the restore result; cross-file restoration is refused. Use view_history to read the panel history, or scene_checkpoints for model-driven history actions.
    Connector
    Destructive
    OAuth
  • Change a WhatsApp chat in the team inbox without sending anything to the customer: hand it to a teammate or department, add or remove labels, resolve or reopen it, leave an internal note, or mark it read or unread. The customer sees none of it. Your team sees the change, and your account's chat webhooks are notified. Available actions: - assign: give the chat to agentId, agentEmail or departmentId (departments need a plan that includes them). A pending chat becomes active. - unassign: take the chat off its agent and department. It goes back to pending. - add_labels / remove_labels: the labels must already exist on the number, create them first with manage_whatsapp_labels. The chat keeps any label you do not mention. - resolve: close the conversation. - reopen: back to active if someone owns the chat, pending otherwise. - add_note: private note only your team can see (2 to 6000 characters). authorId writes it as that teammate. - mark_read / mark_unread: marking a resolved chat as unread reopens it. To write to the customer, use send_whatsapp_message instead.
    ConnectorNo auth