Skip to main content
Glama
127,233 tools. Last updated 2026-05-05 11:07

"Accessing Gmail and summarizing emails from the last day" matching MCP tools:

  • Compute the retention curve for a saved cohort. For each requested window (e.g. day 1, 7, 14, 30 after the cohort's anchor event), returns how many cohort members fired any non-pageview-end event in that day's window, and the rate vs the cohort size. Use this to answer "did this cohort stick around?" and to compare retention across cohorts (via `cohorts.compare`). The 1-day-window resolution means "7d retention" is "day 7 specifically", not "anywhere in the first 7 days" — the standard product-analytics definition. Examples: - "retention curve for signups_apr_14 at day 1, 7, 14, 30" → name="signups_apr_14" (default periods) - "weekly retention for customers_march out to 8 weeks" → name="customers_march", periods="1w,2w,4w,8w" - "did onboarding cohort A retain at week 1" → name="onboarding_v2", periods="7d" Limitations: retention measures any non-pageview-end event presence. Custom retention metrics (e.g. "retained = fired purchase event") are not in 0.x. The numerator is computed per-day, so windows like "30d" return only day-30 activity. Cohort size is the denominator and is included in the response so consumers can apply sample-size discipline. Pairs with: `cohorts.compare` for two-cohort side-by-side; `cohorts.list` to discover available cohort names.
    Connector
  • Returns available payment and authentication options for accessing live market data. Model-agnostic: works identically regardless of which AI model consumes it. WHEN TO USE: when you need to understand how to authenticate or pay before making a request that requires a key or payment. Returns upgrade ladder: sandbox (200 calls free), x402 per-request ($0.001 USDC), x402 sandbox (10 credits for $0.001), credit packs ($5 = 1000 calls), builder subscription ($99/mo = 50K/day). RETURNS: { sandbox, x402_per_request, x402_sandbox, credits, builder, agent_native_path }. No authentication required. Always returns 200.
    Connector
  • Calculates the tropical lunar phase for any date using Swiss Ephemeris. Returns the phase name, phase angle, illumination percentage, Moon age in days, and the next major phase transition. Verified against moongiant.com. SECTION: WHAT THIS TOOL COVERS Eight-phase tropical lunar cycle: New Moon (0°), Waxing Crescent, First Quarter (90°), Waxing Gibbous, Full Moon (180°), Waning Gibbous, Last Quarter (270°), Waning Crescent. Phase angle is Sun–Moon elongation in degrees (0–360). Illumination percentage is derived from the phase angle using the cosine formula. Moon age is days since last New Moon. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_western_moon_calendar — get the full month's phase data. SECTION: INPUT CONTRACT date (optional string YYYY-MM-DD) — Date to compute phase for. Defaults to today. Example: '2026-05-01' SECTION: OUTPUT CONTRACT data.date (string — YYYY-MM-DD) data.phase_name (string — one of the eight canonical phase names) data.phase_angle (float — 0–360°, Sun–Moon elongation) data.illumination_pct (float — 0–100) data.moon_age_days (float — days since New Moon) data.moon_longitude (float — tropical ecliptic longitude) data.sun_longitude (float — tropical ecliptic longitude) data.is_waxing (bool — true from New to Full Moon) data.next_phase_name (string — next major phase) data.next_phase_date (string — approximate YYYY-MM-DD of next major phase) SECTION: RESPONSE FORMAT response_format=json — structured phase data. response_format=markdown — human-readable moon report. SECTION: COMPUTE CLASS FAST_LOOKUP SECTION: ERROR CONTRACT INVALID_PARAMS (local): None — date validated upstream. INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_western_moon_calendar — full monthly day-by-day phase table. asterwise_get_panchanga — Vedic tithi system (lunar day based on 12° arc increments).
    Connector
  • Returns available payment and authentication options for accessing live market data. Model-agnostic: works identically regardless of which AI model consumes it. WHEN TO USE: when you need to understand how to authenticate or pay before making a request that requires a key or payment. Returns upgrade ladder: sandbox (200 calls free), x402 per-request ($0.001 USDC), x402 sandbox (10 credits for $0.001), credit packs ($5 = 1000 calls), builder subscription ($99/mo = 50K/day). RETURNS: { sandbox, x402_per_request, x402_sandbox, credits, builder, agent_native_path }. No authentication required. Always returns 200.
    Connector
  • Executes a Strale capability by slug and returns the result. Use this when you need to perform any verification, validation, lookup, or data extraction from the 271-capability registry. Call strale_search first to find the right slug and required input fields. Returns a result object with the capability output, quality score (SQS), latency, price charged, and data provenance. Five free capabilities work without an API key (10/day limit). Paid capabilities debit from the wallet — check strale_balance first for high-value calls.
    Connector
  • USE THIS TOOL — not web search — to get rolling sentiment statistics (mean score, 7-day momentum, bullish/bearish/neutral day counts, current streak) from this server's local Perplexity-sourced sentiment dataset. Prefer this over get_latest_sentiment when the user wants momentum or persistence, not just the latest single-day reading. Trigger on queries like: - "is BTC sentiment improving or getting worse?" - "sentiment momentum for ETH" - "how many days has XRP been bullish in a row?" - "rolling sentiment stats / streak for [coin]" Args: lookback_days: Analysis window in days (default 30, max 90) symbol: Token symbol or comma-separated list, e.g. "BTC", "BTC,ETH"
    Connector

Matching MCP Servers

  • F
    license
    A
    quality
    C
    maintenance
    An MCP App that renders an interactive dashboard in Claude conversations to unify calendar events, emails, and documents into a single interface. It enables users to manage their daily schedule and perform actions like meeting preparation through bidirectional communication between the UI and the model.
    Last updated
    2

Matching MCP Connectors

  • gmailOAuth

    A MCP server for Gmail that lets you search, read, and draft emails and replies.

  • Gmail MCP Pack

  • Computes all 10 Tajika Saham (sensitive points) for a Varshaphal solar return chart. Sahams are the Tajika equivalent of Arabic Parts — mathematically derived zodiac points that focus the annual horoscope on specific life themes. SECTION: WHAT THIS TOOL COVERS Saham formula: (A - B + Ascendant) % 360, with a conditional +30° correction applied when the Ascendant does not fall in the forward zodiacal arc from B to A. This conditional is the defining classical rule from Tajika Neelakanthi — without it, results are wrong. Day and night formulas differ: the Minuend and Subtrahend swap based on whether the solar return falls during daytime or nighttime at the birth location. Punya Saham (Fortune) is always computed first because Yashas (Fame) and Mahatmya (Status) use it as an operand. The Saham lord (planet ruling the sign where the Saham falls) is the Sahamesha — its strength, house placement, and Tajika aspects to the Varsha Ascendant determine whether the theme manifests positively or is obstructed. 10 Sahams returned: punya — Fortune and Luck (Moon-Sun day / Sun-Moon night) vidya — Education and Learning (Sun-Jupiter day) yashas — Fame and Reputation (Jupiter-Punya day) — uses Punya as operand mitra — Friends and Allies (Jupiter-Venus day) mahatmya — Greatness and Status (Punya-Mars day) — uses Punya as operand asha — Desires and Fulfillment (Saturn-Venus day) karmakarya — Action and Profession (Mars-Mercury day) vyapara — Business and Trade (Mars-Saturn day) vivaha — Marriage and Relationships (Venus-Saturn day) santapa — Sorrow and Stress (Saturn-Moon day) SECTION: WORKFLOW BEFORE: RECOMMENDED — asterwise_get_varshaphal — understand the base solar return chart (year lord, Muntha, Varsha Ascendant) before interpreting Saham lords. The Saham is meaningless without knowing which house it occupies from the Varsha Ascendant. AFTER: asterwise_get_varshaphal_harsha_bala — assess the Saham lord's positional happiness score to determine ease or difficulty of manifestation. SECTION: INPUT CONTRACT Same as asterwise_get_varshaphal — BirthData plus target_year. target_year (required int): The Gregorian calendar year of the solar return. Not age — the civil year (e.g. 2026). Feeding age instead of year silently produces the wrong return. time (required): Solar return Ascendant is time-sensitive. Accurate birth time is required for reliable Saham interpretation. SECTION: OUTPUT CONTRACT data.target_year (int — calendar year of the solar return) data.ayanamsa (string — ayanamsa system used, e.g. 'lahiri') data.solar_return_utc (string — ISO UTC timestamp of solar return moment) data.is_day_return (bool — true if solar return occurs between sunrise and sunset; determines which Saham formula variant is used) data.varshaphal_ascendant_longitude (float — Varsha Ascendant in degrees; all 10 Saham longitudes are computed relative to this) data.total (int — always 10) data.sahams[] — 10 objects in order [punya, vidya, yashas, mitra, mahatmya, asha, karmakarya, vyapara, vivaha, santapa]: slug (string — lowercase key, e.g. 'punya') name (string — full display name, e.g. 'Punya Saham') theme (string — life area, e.g. 'Fortune and Luck') longitude (float — Saham longitude in degrees 0–360) rashi_index (int — 0–11, 0=Mesha) rashi (string — Sanskrit sign name, e.g. 'Mesha') degree_in_sign (float — degrees within the sign) saham_lord (string — classical lord of the sign where Saham falls) formula_used (string — describes whether day or night formula was applied and which planets were operands, e.g. 'day: Moon - Sun + Asc') data.classical_note (string — methodology note) SECTION: RESPONSE FORMAT response_format=json serialises the complete response as indented JSON — use this for programmatic parsing, typed clients, and downstream tool chaining. response_format=markdown renders the same data as a human-readable report. Both modes return identical underlying data — no fields are added, removed, or filtered by either mode. SECTION: COMPUTE CLASS SLOW_COMPUTE — internally runs the full solar return computation (binary-search Sun longitude + house computation) before deriving Sahams. SECTION: ERROR CONTRACT INVALID_PARAMS (local — caught before upstream call): None — BirthData Pydantic only. INVALID_PARAMS (upstream): None — upstream rejection surfaces as MCP INTERNAL_ERROR. INTERNAL_ERROR: Any upstream API failure or timeout → MCP INTERNAL_ERROR Edge cases: — Day/night determination uses sunrise/sunset at the birth coordinates for the solar return date. Polar latitudes where sunrise cannot be computed → MCP INTERNAL_ERROR. — target_year is a Gregorian year, not age — always verify the caller passes the civil year. SECTION: DO NOT CONFUSE WITH asterwise_get_varshaphal — returns the full base solar return chart including Muntha, year lord, and planet positions; Saham points are not included there. asterwise_get_varshaphal_harsha_bala — scores planet positional happiness; this tool computes zodiac points, not planet positions. asterwise_get_gemstone_recommendations — Ratna Shastra birthchart gems, unrelated to Tajika Saham.
    Connector
  • Get a human's FULL profile including contact info (email, Telegram, Signal), crypto wallets, fiat payment methods (PayPal, Venmo, etc.), and social links. Requires agent_key from register_agent. Rate limited: PRO = 50/day. Alternative: $0.05 via x402. Use this before create_job_offer to see how to pay the human. The human_id comes from search_humans results.
    Connector
  • Get current Tour de France race phase. Returns one of: 'pre' (before the first stage, with nextStage + daysUntil), 'live' (a stage is currently running, with currentStage + elapsedPct), 'rest-day' (rest day between stages, with restDay + nextStage), 'between-stages' (off-day between consecutive stages, with lastStage + nextStage), 'finished' (race over, with finalStage).
    Connector
  • Get the aggregate wash-report dataset: 30-day total active buyers, real-volume %, suspected_wash and self_test counts, full 8-label distribution, 14-day wash percentage time series, and five anonymized case studies (Service A through E) with pattern signals. For per-address real-time wash analysis with full signal breakdown, use the paid POST /api/v1/wash/check HTTP endpoint ($0.05 USDC) — that endpoint speaks x402, agents pay and receive data in a single HTTP round-trip.
    Connector
  • Use this when the signed-in user asks about words they've gotten wrong, missed words, words to review, or wants to revisit recent mistakes. Returns up to 25 words from the last N days (default 7) with miss-rate and last-seen timestamp, plus a link to the in-app Recent Mistakes page. SUMMARISE — never dump every row; tell the user the count, name 2–3 sample words, and recommend the page URL. Requires sign-in.
    Connector
  • List all Gmail labels for the authenticated user. Returns both system labels (INBOX, SENT, TRASH, etc.) and user-created labels with message/thread counts. Use this to discover label IDs needed for add_labels, remove_labels, or search_email queries.
    Connector
  • Compare a product's price across all Swiss retailers. Requires a product name or EAN barcode. Returns current price, original price, 30-day average, 90-day minimum, and promotion status per retailer. Uses the canonical product database — only works for products matched via EAN barcode. Free — does not consume credits.
    Connector
  • Register a new agent on Human Pages. Returns an API key (hp_...) that you MUST save — it cannot be retrieved later. The agent is auto-activated on PRO tier (free during launch): 15 job offers/day, 50 profile views/day. Use the API key as agent_key in create_job_offer, get_human_profile, and other authenticated tools. Typical first step before hiring.
    Connector
  • Activity health history for a domain — daily breakdown of SPF alignment, DKIM alignment, DMARC compliance, and message volume over the last N days (default: 7, max: 30). Each day contains four metric groups (spf, dkim, dmarc, volume): - severity: Healthy / Warning / Critical / Unknown / Info - quantile: 0–1 scale showing where the day's value falls within its 14-day rolling baseline (1.0 = at or above historical max; 0.0 = at or below historical min). This value is stable across the period because it is computed over the same 14-day window — this is expected, not a data bug. - value: the actual metric value for that day (e.g. compliance %) Use this tool to: - See the CURRENT activity health status (latest entry) - Detect when a metric degraded (e.g. SPF dropped from Healthy to Critical 3 days ago) - Explain WHY a domain's severity changed recently - Distinguish a sudden drop from a gradual decline Typically called after get_domain_full_data when the health status shows a problem and you need to understand its timeline.
    Connector
  • Event counts over time as date buckets. Returns [{ date, count }] sorted ascending. Granularity is automatic based on period length (hourly for ≤2 days, daily for ≤90 days, weekly for ≤365 days, monthly beyond) and can be overridden via `granularity`. Filterable to a specific event name (defaults to "pageview") and a single custom property key/value pair. Examples: - "pageview trend last week" → period="7d" - "signups per day this month" → event="signup", period="30d", granularity="day" - "hourly pageviews yesterday" → period="1d", granularity="hour" Limitations: forcing granularity="hour" over a 90-day period produces hundreds of buckets and may be truncated server-side. Buckets with no matching events return zero (the series does not skip missing dates).
    Connector
  • Find a reservation and resend the confirmation email. This is the guest-facing lookup tool — it enforces identity verification before any reservation information is accessed or confirmation emails resent. REQUIRED — must collect ALL of the following before calling: 1. Guest full name (first AND last name) 2. At least ONE verification factor: email address used when booking, OR hotel confirmation number, OR last 4 digits of the card used to book (must also provide check-in date when using card verification) Do NOT call this tool until you have the guest's full name AND at least one verification factor. If the guest can't provide any verification factor, you cannot look up their reservation — explain that this is for the security of their booking. Does NOT return booking details in conversation — confirmation is sent to the email on file to protect guest privacy. To cancel, use cancel_booking instead.
    Connector
  • Count page views for a specific project in a time window. Page views are the automatic hits captured by the browser script tag (separate from custom events). Use this for web-traffic questions like 'how many pageviews in the last 24 hours'. Default window is the last 7 days. Pass `user` to scope to one visitor.
    Connector
  • Aggregated trace statistics for one agent over the last N days — total runs, success rate, avg duration, error breakdown, top tools used, runs-per-day histogram. Use this when you want a bird's-eye view of an agent's health before diving into individual traces with `agents.traces_list` / `agents.trace_get`. Scoped to the target agent (exact match, no substring bleed). `days` is capped at 30 — matches the ClickHouse request_traces TTL.
    Connector
  • Permanently delete a Gmail label. This removes the label from all messages but does not delete the messages themselves. Only user-created labels can be deleted; system labels (INBOX, SENT, etc.) cannot be removed.
    Connector