io.github.elninyo-ops/baseline-mcp
PYPI · BASELINE-MCP
Statistically rigorous weather and climate context: forecast plus 35-year historical ranking.
Available components
Last scanned (15 hours ago)
Scores higher than 69% of PyPI servers
Category Maps and Location
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security94
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Declares code that runs automatically (build-time code we could not rule out (a Hatch, PDM or setuptools build hook, a dynamic version we could not read statically, shipped VCS metadata or a stray root module)) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
- 0 of 28 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 55 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability53
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2325 tokens (~387/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Nov 26 0
- Stability: 0.97 → pass security
- 18 Nov 26 0
- Stability: pass → 0.97 functional
- 12 Nov 26 0
- Stability: 0.97 → pass security
- 11 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 10 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 9 Nov 26 +6
- Source repository: unverified → pass ▲ security
- 8 Nov 26 −7
- Provenance: pass → unverified ▼ security
- Stability: pass → 0.87 functional
- 6 Nov 26 +15
- Malware scan: unverified → pass ▲ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed pypi/baseline-mcp@0.1.9
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 2 scripts
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
| build_hook | Not reviewed | hatch_build.py,tool.hatch.build.hooks.custom |
Background: Why install scripts are a supply-chain risk →
Dependencies 28 packages
| Packages resolved | 28 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
compare_locations ~436
Compare precipitation, temperature, or snowfall across 2-10 locations in a single ranked comparison, computed directly by Baseline. Use this instead of calling get_climate_context or get_water_year_status once per location and comparing the answers yourself — the ranking and percent-of-normal figures in the result come from Baseline, not from your own arithmetic over several separate answers. Provide EITHER `locations` (a list of 2-10 place names and/or "lat,lon" strings) OR `category` (a curated group name) — not both. Valid category values: colorado_ski_resorts, wyoming_ski_resorts, utah_ski_resorts, wyoming_watersheds, colorado_river_basin_states, great_plains_ag, major_us_cities, major_european_cities, us_national_parks. variable: "precipitation" (default), "temperature", or "snowfall". Snowfall is sourced from a different, coarser (0.25-degree) Open-Meteo archive than precipitation/temperature (0.1-degree ERA5-Land) — results are correct but not directly resolution-comparable across variables. period: "water_year" (default, Oct 1 / Jan 1 to date), "season" (also set season="winter"/"spring"/"summer"/"fall" and optionally year), "month" (also set month=1-12 and optionally year), or "ski_season" (fixed Nov 1 - Apr 30 window; optionally set year=<November's year>, e.g. year=2019 for the 2019-2020 season; defaults to the most recently started ski season). Custom date ranges are not supported — use "water_year", "season", "month", or "ski_season".
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| locations | – | – | – |
| month | integer | – | – |
| period | string | – | – |
| season | string | – | – |
| variable | string | – | – |
| year | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
compare_to_normal ~312
Compare the forecast for the next few days at a location to 35-year historical normals. Returns percentile rankings, not vague comparisons. Use for questions like "is this week unusually warm" or "will this weekend be wetter than normal". The forecast reaches 10 days ahead, so time_window must be near-term: a window further out ("this month", "this winter") is declined, and a past period ("last month", "this water year") is a question for get_climate_context instead. variable must be "temperature" or "precipitation". time_window is optional free text for a near-term window (e.g. "today", "tomorrow", "this weekend", "this week", "the next 10 days") — defaults to "this week". Baseline Climate states its own confidence in an `assessment` field. Relay `assessment.headline` as given. If you shorten it, keep `assessment.if_shortened_keep` intact — it carries the qualifier, and dropping it turns a qualified statement into an unqualified one. Do not compose your own assessment of how reliable a result is, do not carry a caveat from one location or period to another, and do not add reliability warnings unless the response flags a problem. `assessment.must_not_claim` lists what the result does not support.
| Name | Type | Req | Description |
|---|---|---|---|
| location | string | yes | – |
| time_window | string | – | – |
| variable | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_climate_context ~458
Get statistically rigorous weather and climate context for any location on Earth (land only). Answers natural-language questions with 10-day forecast data and historical percentile rankings against a 35-year ERA5 daily climatology (1991-2025, WMO 1991-2020 normals). Use this when you need to know not just what conditions are or will be, but how unusual they are relative to history. query MUST be phrased as a question in one of these forms (the location goes where LOCATION is shown; the underlying parser matches these patterns specifically and will fail on other phrasings, e.g. "weather context for LOCATION" does not work): - "Will LOCATION be warmer/wetter than normal this week?" - "Has LOCATION been dry this water year?" / "this year?" - "How cold/warm/wet was last winter/spring/summer/fall in LOCATION?" - "What is the wettest/driest month in LOCATION?" It also answers SEASONAL (three-month) outlook questions, which are about the season ahead rather than the next ten days: - "Will this season be warmer/wetter than normal in LOCATION?" - "Will this winter/spring/summer/fall be warm and wet in LOCATION?" Seasonal answers carry a per-location skill label and sometimes say that no outlook is currently issued, which is a correct answer rather than a failure — see get_seasonal_outlook, which takes a place and variables directly and is the better choice when the question is plainly about the season ahead. Baseline Climate states its own confidence in an `assessment` field. Relay `assessment.headline` as given. If you shorten it, keep `assessment.if_shortened_keep` intact — it carries the qualifier, and dropping it turns a qualified statement into an unqualified one. Do not compose your own assessment of how reliable a result is, do not carry a caveat from one location or period to another, and do not add reliability warnings unless the response flags a problem. `assessment.must_not_claim` lists what the result does not support.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_context_for_coordinates ~205
Get 10-day forecast and 35-year historical climate context for exact coordinates. Use when you have a specific latitude/longitude (a property, field, trailhead, or site) rather than a place name — this skips geocoding entirely. Land locations only. Baseline Climate states its own confidence in an `assessment` field. Relay `assessment.headline` as given. If you shorten it, keep `assessment.if_shortened_keep` intact — it carries the qualifier, and dropping it turns a qualified statement into an unqualified one. Do not compose your own assessment of how reliable a result is, do not carry a caveat from one location or period to another, and do not add reliability warnings unless the response flags a problem. `assessment.must_not_claim` lists what the result does not support.
| Name | Type | Req | Description |
|---|---|---|---|
| label | string | – | – |
| latitude | number | yes | – |
| longitude | number | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_seasonal_outlook ~680
Seasonal (three-month) outlook for a location: calibrated probabilities that the season will be below, near or above normal, for temperature, precipitation, or both. This is a three-month climate outlook, not a weather forecast. For conditions over the next ten days, or for how unusual recent weather has been, use get_climate_context. location: a place name ("Harare", "Denver, Colorado") or a "lat,lon" string. variables: any of "temperature", "precipitation". Defaults to BOTH, which answers compound questions like "will this winter be warm and wet" in one call — ask for both rather than calling twice and stitching the answers together. season: optional "DJF", "MAM", "JJA" or "SON". Leave empty for the season currently being forecast, which is almost always what a question about "this season" means. WHAT YOU GET BACK, AND HOW IT VARIES BY PLACE: Probabilities are produced for every land location the model covers, and they are always returned. How well they have been tested is a separate matter that varies by location and season: at some places the odds have been shown to beat a climatological guess, at some only the direction is worth using, at some a simple warming trend predicted the season better than the model did, and at many they have never been tested at all. The answer states which of these applies in its own words. Relay that standing as written — an untested outlook is not a bad one, and neither is it a verified one. "NO OUTLOOK IS CURRENTLY ISSUED" IS A NORMAL, CORRECT ANSWER. An outlook exists only for the forecast cycle now live, which is the season the models have most recently been run for. Ask in September about the coming December-February and the honest reply is that none is issued yet, because the forecast it would be built from has not been produced. That is expected behaviour, not a failure, a gap in coverage or a reason to retry: relay it as given, and say when the outlook will be published if the response says so. Do not subst…
| Name | Type | Req | Description |
|---|---|---|---|
| location | string | yes | – |
| season | string | – | – |
| variables | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_water_year_status ~234
Get water year precipitation and temperature status for a location: totals since the start of the water/calendar year (Oct 1 for North America, Jan 1 elsewhere), percentile rank against the same period across 35 historical years, and whether conditions are notably wet, dry, warm, or cold. Built for drought monitoring, water resource, agricultural, and fire-planning contexts. location can be a place name ("Casper WY") or "lat,lon" coordinates. Baseline Climate states its own confidence in an `assessment` field. Relay `assessment.headline` as given. If you shorten it, keep `assessment.if_shortened_keep` intact — it carries the qualifier, and dropping it turns a qualified statement into an unqualified one. Do not compose your own assessment of how reliable a result is, do not carry a caveat from one location or period to another, and do not add reliability warnings unless the response flags a problem. `assessment.must_not_claim` lists what the result does not support.
| Name | Type | Req | Description |
|---|---|---|---|
| location | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the io.github.elninyo-ops/baseline-mcp server?
io.github.elninyo-ops/baseline-mcp runs locally as a PyPI package, launched with uvx baseline-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · baseline-mcp
claude mcp add elninyo-ops-baseline-mcp -- uvx baseline-mcp
What is the io.github.elninyo-ops/baseline-mcp server?
io.github.elninyo-ops/baseline-mcp is listed in the public MCP registry as io.github.elninyo-ops/baseline-mcp. Statistically rigorous weather and climate context: forecast plus 35-year historical ranking. This page covers its PyPI package (baseline-mcp).
Is the io.github.elninyo-ops/baseline-mcp server safe to use?
io.github.elninyo-ops/baseline-mcp scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.elninyo-ops/baseline-mcp server expose?
io.github.elninyo-ops/baseline-mcp exposes 6 tools: get_climate_context, get_context_for_coordinates, get_water_year_status, compare_to_normal, compare_locations, get_seasonal_outlook. Their descriptions and schemas cost roughly 2,325 tokens of context every time the server is loaded.
Is the io.github.elninyo-ops/baseline-mcp server still maintained?
io.github.elninyo-ops/baseline-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.elninyo-ops/baseline-mcp server under?
io.github.elninyo-ops/baseline-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.elninyo-ops/baseline-mcp server?
VerifyMCP ran 16 checks on io.github.elninyo-ops/baseline-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.