Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@EMY Weather MCP Server What's the forecast for Santorini?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server for Greek weather data from EMY — the Hellenic National Meteorological Service (Εθνική Μετεωρολογική Υπηρεσία).
It wraps EMY's public (api.emy.gr) endpoints as MCP tools. No API key is
required, and nothing is hardcoded — locations and data are always fetched
live from EMY.
Tool | What it returns |
| The live directory of ~1035 forecast locations (id, Greek/English name, prefecture, coordinates). Optional name/prefecture filter. |
| Today + up to 3 days for one location, resolved by name, id, or coordinates (nearest point). Temp max/min (°C), wind, precipitation probability, sky condition. |
| Structured CAP alerts (event, severity, urgency, onset/expiry, area). |
| Marine bulletin for Greek seas (METAREA 3): forecast + warnings text. |
| National emergency weather bulletins (text, Greek only — EMY publishes no English variant). |
| All-time Greek climate extremes (temperature, precipitation, wind). |
Related MCP server: WeatherXM Pro MCP Server
This is the tricky part. EMY stores names transliterated from Greek with a
prefecture suffix, e.g. KORINTHOS (M. KORINTHIAS). Three independent problems:
Exonyms vs transliteration — "Corinth" ≠ "Korinthos", "Corfu" ≠ "Kerkyra".
Prefecture suffix on every name — (m. Korinthias).
Greek script + accents — Κόρινθος vs KORINTHOS.
How they're handled:
Greek or Latin name → get_forecast(location=...) or list_locations(query=...).
Names are accent-folded, suffix-stripped, and Greek is transliterated to
Latin using EMY's own scheme, so Κόρινθος, korinthos and KORINTHOS all
match. Fuzzy ranking handles typos and returns alternatives.
English exonyms / anything ambiguous → resolve the place to coordinates
and call get_forecast(latitude=..., longitude=...). This returns the nearest
forecast point regardless of spelling or language (e.g. Corinth's coordinates →
Korinthos, 5 km away). An LLM client typically knows the coordinates already.
Everything is fetched live. Per endpoint:
Fresh window — cached payload is served without refetch for 30 minutes (EMY's forecasts update ~twice daily).
After the window, a refetch is attempted.
If EMY is unreachable, the last-known-good copy is served for up to
24 hours, flagged stale with its age.
After 24 hours with no successful fetch, the call fails with a clear error.
Every tool response includes a source block with fetched_at, age_minutes
and stale.
api.emy.gr serves a valid *.emy.gr certificate but omits the intermediate CA
from the handshake, so standard clients fail with "unable to get local issuer
certificate". The client fetches the intermediate (RapidSSL TLS RSA CA G1)
from the certificate's own AIA URL on first use and caches it under
~/.cache/emy-mcp/. Because a fetched cert is installed as a trusted anchor,
it is pinned by SHA-256 fingerprint — a fetched or cached cert is only
trusted if its fingerprint matches the known-good value, which makes the fetch
safe against tampering and self-heals a corrupt cache. Certificate verification
is not disabled; if EMY ever rotates this CA the pin must be updated.
Sky condition comes from a small icon set (6 values): Sunny, Hot, Partly cloudy, Scattered showers, Cloudy with rain, Thunderstorms — so it's coarse.
Wind speed units are reported by EMY as a bare number; they appear to be m/s and are labelled as such, but EMY does not document this.
There is no live "current observations" feed in EMY's public API — only forecasts, alerts, marine and climate. This server reflects that.
pip install -e . # or: pip install httpx certifi "mcp>=1.2"
# stdio (Claude Desktop, Claude Code, local assistants)
python -m emy_mcp
# streamable-HTTP (hostable)
python -m emy_mcp --http --host 0.0.0.0 --port 8000{
"mcpServers": {
"emy-weather": {
"command": "python",
"args": ["-m", "emy_mcp"]
}
}
}MIT
Get structured CAP weather alerts for Greece.
Args:
language: "en" or "el" for the alert text (falls back to whatever EMY
provides).
active_only: if True, drop alerts whose expires time is in the past.
Each alert includes event, severity, urgency, certainty, onset/expiry, headline, description and affected areas.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | en | |
| active_only | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It explains the language fallback and active_only filtering behavior, and lists output fields. However, it misses potential details like rate limits or that data is real-time, and does not explicitly state it is a read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (6 lines), front-loaded with the main purpose, then details parameters, then output fields. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with two optional parameters and an output schema, the description is fairly complete. It covers input and output details. Could be improved by mentioning that alerts are current or that no authentication is needed, but overall adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description fully explains both parameters. It specifies the allowed values for language ('en' or 'el') with fallback behavior, and explains that active_only drops expired alerts, adding significant meaning beyond the schema's defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get structured CAP weather alerts for Greece', specifying the verb (Get), resource (CAP weather alerts), and location (Greece). It is distinct from sibling tools like get_forecast or get_warnings by focusing on alert data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as get_warnings. It does not mention use cases, prerequisites, or context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all-time Greek climate extreme values (temperature, precipitation, wind).
Each record reports the value, the date, and the location where it occurred.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the output includes value, date, and location, implying a read-only operation. However, it lacks details on data freshness, rate limits, or constraints. The behavior is adequately implied but not explicitly disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and followed by a clear detail on record contents. No unnecessary words, perfect conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and an output schema (though not detailed), the description is nearly complete. It explains what records contain. However, it could mention if results are sorted or how extreme values are defined, but overall sufficient for a simple list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters, the schema already covers all inputs. The description adds meaning by explaining the output format (value, date, location), which is not present in the empty schema. Baseline for no parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: retrieving all-time Greek climate extreme values for temperature, precipitation, and wind. It specifies the resource (climate records), scope (Greek), and time range (all-time), distinguishing it from siblings like get_forecast or get_alerts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. With siblings like get_forecast and get_warnings, it fails to clarify scenarios where this historical climate data is appropriate or when to prefer sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the EMY forecast (today + up to 3 days) for one location.
Resolve the location in ONE of three ways (most reliable first): * latitude + longitude : returns the nearest forecast point (best for English/exonym place names — resolve the name to coordinates first). * location_id : an exact EMY location id (from list_locations). * location : a name to match (Greek or Latin script).
Args: location: place name to match (e.g. "Korinthos", "Κόρινθος", "Athina"). location_id: exact EMY id. latitude, longitude: decimal degrees; returns the nearest point. days: optional cap on the number of forecast days returned.
Each day reports max/min temperature (°C), wind speed (m/s) and direction, precipitation probability (%), and a summarised sky condition. The response echoes which location was matched (with distance/score and alternatives) so the caller can confirm or refine.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| latitude | No | ||
| location | No | ||
| longitude | No | ||
| location_id | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It explains input resolution behavior (returns nearest point for coordinates, matches by name) and output structure (temperature, wind, precipitation, sky condition). It mentions echoing the matched location for confirmation. Lacks explicit statement about read-only or idempotency, but the forecast nature implies safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured: one-line summary, numbered resolution methods, args list, output summary. It is slightly lengthy but every sentence adds value. Formatting (newlines, bullets) aids readability. Could be trimmed slightly, but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 optional parameters, no enums, and an output schema exists, the description covers all key aspects: location resolution options, output fields, and response echoing. It explicitly mentions the forecast range (today+3 days). It does not require additional details like timezone or date format, as the output schema likely covers them. The description is complete for an agent to correctly invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 0% description coverage, so the description must compensate. It fully explains each parameter: location (with Greek/Latin examples), location_id (reference to list_locations), latitude/longitude (decimal degrees, returns nearest point), days (optional cap). It adds ordering advice (most reliable first) and example values, adding significant value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves the EMY forecast for a single location for today plus up to 3 days. It specifies three distinct resolution methods (lat/lng, location_id, location name) and distinguishes itself from sibling tools like get_alerts or get_warnings which deal with alerts, not forecasts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides detailed guidance on how to resolve the location using three methods, ranked by reliability, and gives tips (e.g., 'best for English/exonym place names'). It also explains output details like echoed location matching. However, it does not explicitly state when not to use the tool or point to alternatives like get_alerts for warnings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the marine weather bulletin for Greek seas (METAREA 3).
Args: language: "en" or "el".
Returns the regular marine forecast and any marine warnings as text (winds in Beaufort, sea state, per-sea-area outlook).
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | en |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries full burden. It discloses return format (text with Beaufort wind, sea state) and content (forecast + warnings), but lacks details on availability, update frequency, or any side effects. Adequate for a simple read tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief and well-structured: a clear opening sentence, followed by specific parameter info and return content. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, the description adequately covers the tool’s functionality (returns forecast and warnings as text). A minor gap is the lack of mention of forecast validity period or update schedule, but overall sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description compensates by documenting the language parameter's allowed values ('en' or 'el') and its effect. This adds clarity beyond the bare schema, though further formatting details are omitted.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the marine weather bulletin for Greek seas (METAREA 3), specifying a distinct geographical scope. While it does not explicitly contrast with sibling tools, the domain and purpose are unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus siblings like get_alerts, get_warnings, or get_forecast. The description implies use for marine weather but fails to address alternatives or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get EMY's national emergency weather bulletins (free text).
EMY publishes these bulletins only in Greek (there is no English variant), so this tool takes no language argument.
Returns the emergency bulletin and any deterioration-of-weather bulletins.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It mentions the language restriction and return content, which is helpful. But it does not explicitly state that the tool is read-only, nor does it cover auth requirements, rate limits, or potential side effects—though for a simple get operation, this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (4 sentences), front-loaded with the core purpose, and every sentence adds necessary detail (source, language constraint, return content). No superfluous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema required beyond description), the description fully covers what the tool does, its constraints, and what it returns. It is contextually complete for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and schema coverage is 100%. Since there are no parameters, the description does not need to add meaning beyond what the schema provides. The description appropriately notes the absence of a language argument, which adds value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves EMY's national emergency weather bulletins as free text. It distinguishes itself from siblings by specifying the source and content type, though it doesn't explicitly differentiate from its closest sibling 'get_alerts'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: bulletins are only in Greek and the tool takes no language argument. This helps the agent understand when to use it. However, it does not explicitly state when not to use it or offer alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List EMY forecast locations (live directory, ~1035 points across Greece).
Args: query: optional name filter; ranks by similarity. Accepts Greek or Latin script (e.g. "Κόρινθος" or "korinthos"). English exonyms like "Corinth" may not match — use get_forecast with coordinates instead. prefecture: optional case-insensitive prefecture substring filter (e.g. "Korinthias"). limit: maximum number of results.
Returns the matching locations with id, names, prefecture and coordinates.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | ||
| prefecture | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It describes query behavior, prefecture filtering, and returns fields, but lacks details on pagination, rate limits, or authentication. The description is sufficient but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: a clear one-line purpose, a labeled Args section, and a Returns statement. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 parameters, no required, and an output schema, the description covers usage and expected returns. It could mention pagination behavior (e.g., if results are truncated beyond limit), but is otherwise complete for selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must compensate. It adds critical meaning: query is a name filter ranking by similarity, accepts Greek/Latin script, warns about English exonyms; prefecture is case-insensitive substring; limit is max results. This far exceeds minimal schema information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists EMY forecast locations (live directory, ~1035 points across Greece). The verb 'list' and resource are specific, and it distinguishes from siblings like get_forecast by mentioning alternative use for English exonyms.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance on using query vs prefecture, mentions query behavior (ranks by similarity, accepts Greek/Latin script), and suggests using get_forecast with coordinates for English exonyms. However, it does not explicitly exclude usage of other siblings like get_alerts or get_climate_records.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_alertsget_climate_recordsget_forecastget_marineget_warningslist_locationsEach tool targets a distinct weather data type: alerts (CAP format), climate records (historical extremes), forecasts (short-term per location), marine bulletin, text warnings, and location listing. Overlap between alerts and warnings is mitigated by clear descriptions of format differences.
All tool names consistently use snake_case with 'get_' or 'list_' prefixes, and each clearly indicates the resource (e.g., get_alerts, list_locations). No mixed conventions or ambiguous verbs.
With 6 tools covering forecasts, alerts, warnings, marine, climate records, and location listing, the set is well-scoped for a national weather service. Each tool serves a clear purpose without redundancy.
The tool surface covers core weather data needs: forecasts, alerts, warnings, marine, and climate extremes. Missing a dedicated current conditions tool, but forecast provides daily summary. Otherwise, no significant gaps for its domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Global weather via Open-Meteo: forecast, ERA5 archive, marine, air quality, geocoding, elevation.
Weather forecasts from MET Norway (Yr): geocoding plus hourly forecasts worldwide.
Meteostat MCP — historical weather from 11k+ stations (no auth)
Real-time weather conditions and multi-day forecasts via Open-Meteo — free, no API key required
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aristath/EMY-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server