"A resource for understanding Claude's context window and how it works" matching MCP tools:

• aboutA

  Nautilinks BacklinksA

  Use this when the user asks what Nautilinks does, how its backlink buying service works, or how an AI agent can use it. Explains the French owned backlink network sold direct, with no reseller, how a purchase flows (prepaid balance or human Stripe checkout -> article drafted & published), the three price shelves (Plancton 5 EUR, Corail 15 EUR, Nautilus 30 EUR), and how authentication works. Call this first if you're not sure what this service does.

  ConnectorNo auth

• describe_protocolA

  nittimA

  How this server works, in full: how a paid call quotes and charges, the two audit tiers, the Nittim Loop and its reward rules and caps, and dispute guidance. Free, no key, no charge, no side effects — it reads static text and calls no model. `section` picks one page; omitted, it returns all of them.

  ConnectorNo auth

• get_principlesA

  turva-mcpA

  Returns turva.dev's engagement principles: async-only, least access, the result shows up in scanner numbers, and open and verifiable. Use this when a user asks how turva.dev works with clients or what rules an engagement follows. For what is sold and what it costs use get_services instead, and for how to start use get_contact. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

  ConnectorNo auth

• get_trip_windowA

  SnowSure — Snow & SkiA

  Historical odds for a SPECIFIC trip window at one resort — 'Whistler on March 27', 'Vail Jan 10–17'. From ~30 years of ERA5 monthly history it blends the window's months (weighted by days) into: the snow-day probability (the headline — for a short window how OFTEN it snows beats how MUCH falls in a season), window-scaled expected snowfall and typical base depth, the same window across the last 5 individual seasons, and the best nearby month (±1) by snow-day odds. Window max 31 days; dates are YYYY-MM-DD. This is HISTORY, not a forecast and not a prediction — for the next 14 days use get_weather_forecast, and for a whole-month question use get_monthly_snow. Windows with under 5 tracked seasons return insufficient rather than thin odds.

  ConnectorNo auth

• zerodust_infoA

  zerodustA

  Explain how a native gas balance can be emptied to exactly zero, what it costs, and how to integrate. Call this when asked how ZeroDust works, why a full balance normally cannot be sent, or what sweeping will cost.

  ConnectorNo auth

• delete_conversion_actionA

  GrowomatA

  Delete a conversion action. Permanently deletes the resource. Irreversible. Refuses with a conflict and names the campaigns when a campaign bids on this action — deleting it would change how that campaign spends. Pass force to delete anyway. Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.

  Connector

  Destructive

  API key

• meeting_overlapA

  Moltline TimeOpsA

  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.

  ConnectorNo auth

• meeting_overlapA

  Moltline TimeOpsA

  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.

  ConnectorNo auth

• how_to_submit_projectA

  renovation-roomA

  Explains how getting quotes from Renovation Room Pros works: the free project-submission wizard, what happens after submitting, and the direct link. Use for general how-does-it-work questions about the Chicago area (including Northwest Indiana and Southern Wisconsin); when the user has already described a specific project, use start_project instead to hand them a prefilled link.

  ConnectorNo auth

• get_contactA

  IIS RescueA

  How to start an engagement with IIS Rescue: the consultation URL and how the process works. Returns a pointer only — it never books anything or collects any personal data.

  ConnectorNo auth

• evictions_get_service_overviewA

  Evictions APIA

  Use this when the person asks what Evictions API is, what is available today, how a real case is handled or who operates it. Takes no input. Returns the service’s description, its current status and who operates it, in the site’s own words, with links to the home and how-it-works pages. Do not use this for fees (use evictions_get_pricing) or for one state’s rules (use evictions_get_state_eviction_facts). No key needed.

  ConnectorNo auth

• fetchA

  OneQAZ Trading IntelligenceA

  Purpose: ChatGPT-connector-standard document fetch by id from `search` results. Namespaces: `tool:{name}` returns the tool's full documentation and how to call it; `resource:{uri}` returns the resource's live data (core resources resolved server-side — also the bridge for clients without MCP resource support, e.g. Gemini); `signal:{market}:{symbol}` returns the symbol's latest combined research signal. Triggers: ChatGPT connectors / Deep Research call this after `search`. Clients without MCP resource support can call it directly with a known resource id, e.g. fetch("resource:market://global/summary"). When to call: whenever the full content behind a search result id is needed. Prerequisites: a valid id — from `search` results or a known namespace id. Next steps: for tool docs, call the named tool via tools/call; for signals, get_signal_detail / explain_decision for deeper evidence. Caveats: uncovered resource uris return description-only text (no fabricated data). `text` is a JSON document for resource/signal ids. Output: {id, title, text, url, metadata, disclaimer, is_investment_advice, data_classification} — flat envelope, OpenAI fixed shape.

  ConnectorNo auth

• get_helpA

  sinoconnection-esim-mcpA

  Answer customer support and policy questions about SinoConnection eSIMs: the REFUND POLICY, how to INSTALL (with step-by-step videos), activation, HOW THE NO-VPN CHINA ACCESS WORKS (roaming / exit IP — see faq.how_no_vpn_works), and how to get support. Call this whenever the customer asks about refunds, cancellations, installation/setup, activation, how it works, what IP / does it bypass the firewall, or help — do NOT answer these from memory (especially the IP/firewall question); relay this authoritative content verbatim in meaning.

  ConnectorNo auth

• anansi_price_currentA

  anansi-dataA

  FREE. Current per-token prices for LLMs as recorded at our last poll: usd_per_prompt_token and usd_per_completion_token (USD per single token, not per million), context window in tokens, and the observation timestamp (unix seconds). Use this to check what a model costs right now, or to compare a handful of models before routing. Do NOT use it to see how a price MOVED — it returns only the latest observation; use anansi_price_changes_recent (free) or anansi_price_history (paid). Input: model_id is a substring match, so 'gpt-5' matches every gpt-5 variant; resolve exact IDs with anansi_search.

  ConnectorNo auth

• get_payment_and_delivery_timesA

  BuyUKeSIM — eSIM & UK Number MCPA

  How long a crypto payment actually takes at BuyUKeSIM and what happens after it confirms. Returns measured confirmation times per coin (median, worst case, share confirmed within two minutes) taken from real orders against public blockchain block timestamps, plus the send delay buyers themselves add, plus how delivery works: it is automatic, triggered by the confirmation, with no human approval step. Use this for "how long does it take", "which coin is fastest", "is delivery instant" and "does someone have to approve my order". Read-only.

  ConnectorNo auth

• insights_industriesA

  apis-ioB

  UNDERSTANDING — the demand-side industry rollup: the sectors the profiled companies fall into. Each row carries TWO counts and they answer different questions: `company_count` is the research roster, `profiled_count` is how many of those you can actually read back via find_company_insights(industry:) — size a cohort on profiled_count. The counterpart to find_industries, which counts SUPPLY (providers publishing APIs into a vertical) — this counts DEMAND (companies buying into it). Comparing the two is how you find a sector with buyers and no sellers. Priced B2 (cross-catalog synthesis) — $0.05 per call under pay-as-you-go; included in Understanding and Influence. See apis://prices.

  ConnectorNo auth

• select_modelA

  DaystructB

  Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Given a need -- minimum context window, required capabilities, a price ceiling -- return the models that satisfy it, cheapest input price first, with the corroboration behind each record so you can judge how well-sourced it is. Prices are per million tokens. A model with no published price is returned under undetermined rather than excluded, so an unpriced model never reads as a disqualified one. This returns candidates and their evidence, not a recommendation.

  ConnectorNo auth

• get_usageA

  FlexYield — blockchain RPC gatewayA

  Your account's usage in one of three views. view='report': requests, weighted units, errors and latency per key, method and chain over a look-back window (hours, default 24; optional chain). view='stats': one console report — report='latency' | 'errors' | 'spend' | 'cache' — for a window ('24h', '7d', '30d'). view='volume': request counts over time (optional chain). Use it to answer 'how much did we use, where, and how fast'. Not for invoices (use get_statement), balances (use get_billing_status) or one key's settings (use list_api_keys). Returns JSON: report → since, total_requests, weighted_units, by_class, cache_hits, success_rate, p50/p95_duration_ms, by_key, by_method, by_chain; stats → window, buckets, series, summary and report-specific totals; volume → window, bucket_seconds, buckets. Read-only. Needs your API key.

  ConnectorNo auth

• upload_assetA

  postnextA

  ⚠️ INLINE-BASE64 PATH — RELIABLE ONLY FOR VERY SMALL FILES (~8KB binary or less). For anything larger, USE `request_asset_upload` instead — the inline path silently truncates when the base64 string exceeds Claude's context cap for tool args (typically ~10-15KB chars), producing a corrupt image in the library. The pre-signed URL flow has no such cap. If you do need this: uploads an image or video to your PostNext asset library via base64 and returns a URL for `create_post_draft.mediaUrls`. Max 5MB per upload (server-side cap; Claude's cap is much lower). Allowed types: JPEG, PNG, WebP, GIF, MP4, WebM. Subject to your plan's storage limit. IF EVEN THIS PATH FAILS (e.g. your environment can't reach the MCP server at all, OR every upload tool returns a network/allowlist error): tell the user to upload the file manually at https://app.postnext.io/my-assets and paste back the asset URL, then use that URL in `create_post_draft.mediaUrls`. That's the documented fallback for sandboxes with restricted egress where neither this tool nor `request_asset_upload` can complete the byte transfer.

  ConnectorAPI key

• load_skillA

  AeviaA

  How this Aevia connection works, plus playbooks for results, reports, systems. Returns a skill's playbook as the result; takes no action itself. A playbook is step-by-step guidance for a multi-step job, too long for a description. `connector_guide` covers how this connection works: workspaces, refs, finding data, the library, building, calculating and failures. `assessment_interpretation` covers reading and comparing results: what an indicator result is and is not, a figure's anchors, functional-unit equivalence and comparison discipline. `report_writing` covers writing results up as a document, from a screening note to an ISO 14044 study. `product_system_authoring` covers building a new product system with `lca_compose_assembly` / `lca_compose_linked`: build order, which of the two fits, and failure modes. A loaded playbook stays in context; one load per session suffices. Skills are gated on what the token can call; an unavailable request returns the available list.

  ConnectorAPI key

• get_usageA

  FlexYield — blockchain RPC gatewayA

  Your account's usage in one of three views. view='report': requests, weighted units, errors and latency per key, method and chain over a look-back window (hours, default 24; optional chain). view='stats': one console report — report='latency' | 'errors' | 'spend' | 'cache' — for a window ('24h', '7d', '30d'). view='volume': request counts over time (optional chain). Use it to answer 'how much did we use, where, and how fast'. Not for invoices (use get_statement), balances (use get_billing_status) or one key's settings (use list_api_keys). Returns JSON: report → since, total_requests, weighted_units, by_class, cache_hits, success_rate, p50/p95_duration_ms, by_key, by_method, by_chain; stats → window, buckets, series, summary and report-specific totals; volume → window, bucket_seconds, buckets. Read-only. Needs your API key.

  ConnectorNo auth