MCP servers · aswanisahoo

IPCC AR6 Climate Retrieval

MCP server that answers heat, extreme rain and wind questions for a given location, citing IPCC AR6 pages and refusing when a question falls outside what it can check.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

Given a place name or a latitude and longitude, it places a live forecast beside more than 60 years of ERA5 annual maxima at that point. It fits a Generalized Extreme Value distribution to those maxima and rates the forecast peak against that location's own return-level curve, not a fixed threshold. Each return level comes with a 90% bootstrap confidence interval. Reports also state a confidence based on measured forecast skill at that lead time, the climatology fit and whether a citation supported the answer. A non-stationary fit uses a likelihood-ratio test to check whether the location's climate is warming, and reports effective return levels at the latest year when a trend is found. The IPCC AR6 pages used are cited by number, and the AR6 Chapter 12 projected change for the reference region is quoted verbatim.

It suits questions about heat, extreme rain or wind at a specific place where a sourced, locally calibrated answer is needed. Because it refuses rather than guesses when a claim cannot be checked, it is also meant for cases where an unsupported answer would be worse than none.

The publisher hosts a public demo on Google Cloud Run. The repository documents the known limits, the threat model and the roadmap in separate files.

Limitations and requirements

Locations without a fitted climatology fall back to absolute cutoffs instead of local bands, and the report says so. The publisher refers to LIMITATIONS.md for the full list of limits and SECURITY.md for the threat model.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    IPCC AR6 Climate Retrieval

    Search IPCC AR6 WG1 and answer with page-level citations, or refuse when unsupported.

    v0.1.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026