# Geo-Insights Environmental Data (remote · mcp.geo-insights.nl)

Dutch environmental data + BGI climate adaptation: 12 tools, 44 measures, 35 parameters. No auth.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.geo-insights.nl`: 73/100 (this document), [markdown](https://verifymcp.io/servers/mathisvfr-environmental-data/mcp.md), [page](https://verifymcp.io/servers/mathisvfr-environmental-data/mcp)

## Channel facts

- Endpoint: `https://mcp.geo-insights.nl/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2174 tokens (~155/item across 14 items; 12 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Geo-Insights Environmental Data MCP server?

Geo-Insights Environmental Data is a hosted endpoint at https://mcp.geo-insights.nl/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http mathisvfr-environmental-data 'https://mcp.geo-insights.nl/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "mathisvfr-environmental-data": {
      "url": "https://mcp.geo-insights.nl/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mathisvfr-environmental-data": {
      "type": "http",
      "url": "https://mcp.geo-insights.nl/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.mathisvfr-environmental-data]
url = "https://mcp.geo-insights.nl/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mathisvfr-environmental-data": {
      "type": "remote",
      "url": "https://mcp.geo-insights.nl/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mathisvfr-environmental-data --url 'https://mcp.geo-insights.nl/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  mathisvfr-environmental-data:
    url: "https://mcp.geo-insights.nl/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "mathisvfr-environmental-data": {
      "Transport": "http",
      "Url": "https://mcp.geo-insights.nl/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add mathisvfr-environmental-data -t streamable-http -u 'https://mcp.geo-insights.nl/mcp'
```

### Other

```json
{
  "mcpServers": {
    "mathisvfr-environmental-data": {
      "type": "http",
      "url": "https://mcp.geo-insights.nl/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 71, +1)

- [security] Tool “rank_measures” rewrote its description, which is the text the model reads

### 2026-11-15 (score 70, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-14 (score 70)

First indexed and scored.

## MCP tools (12)

### `list_sources` (~146 tokens)

List Environmental Data Sources

List all environmental data sources with station counts and geographic coverage.

    Call this first to discover which data sources are available and how many
    stations each one has. Returns sources with name, station_count,
    datastream_count, and source_attribution (CC-BY license info).

    Sources include KNMI (weather), Luchtmeetnet (air quality), BRO
    (groundwater), Samen Meten (citizen science), Sensor.Community, and more.

    Typical workflow: list_sources → get_parameters → get_latest_readings.

    On error, returns a structured error with cause (timeout, circuit_breaker_open,
    connection_failed) and retry_after_seconds.

Output parameters:

- `sources` (array)

### `get_parameters` (~121 tokens)

List Environmental Parameters

List all 35 available environmental parameters with units and aliases.

    Returns parameters with name, display_name, unit_display (human-readable),
    unit_ucum (formal UCUM code), definition_url (CF Conventions), and aliases.
    Use aliases in the 'parameter' argument of get_latest_readings or
    get_readings_history (e.g. "pm25", "temperature", "no2").

    No FROST query needed — this is an instant in-memory lookup. Call it to
    discover valid parameter names before querying readings.

Output parameters:

- `parameters` (array)

### `get_latest_readings` (~284 tokens)

Get Latest Environmental Readings

Get the most recent environmental readings near a location.

    Args:
        lat: Latitude in WGS84 (e.g. 51.92 for Rotterdam)
        lon: Longitude in WGS84 (e.g. 4.47 for Rotterdam)
        radius_km: Search radius in kilometers (default 10, max 50)
        parameter: Optional filter by parameter name or alias (e.g. "pm2_5",
                   "temperature", "pm25", "no2"). Use get_parameters() to see
                   all valid names and aliases.
        limit: Maximum number of readings to return (default 100, max 500)

    Returns the single most recent reading per datastream within the radius.
    Each reading includes parameter, value, unit, timestamp, station_name,
    lat, lon, source, and source_attribution.

    For time-range queries, use get_readings_history instead.

    Invalid coordinates return an error with the valid ranges.
    An unrecognized parameter returns an error with the full list of valid names.
    If the data source is unreachable, returns cause (timeout, circuit_breaker_open)
    and retry_after_seconds.

Input parameters:

- `lat` (number, required)
- `limit` (integer)
- `lon` (number, required)
- `parameter`
- `radius_km` (number)

Output parameters:

- `count` (integer)
- `readings` (array)

### `get_readings_history` (~328 tokens)

Get Historical Readings

Get historical environmental readings near a location over a time range.

    Use this for trend analysis, comparisons, and time-series queries.
    Unlike get_latest_readings (which returns only the most recent value),
    this returns multiple observations per station within the time window.

    Args:
        lat: Latitude in WGS84 (e.g. 51.92 for Rotterdam)
        lon: Longitude in WGS84 (e.g. 4.47 for Rotterdam)
        parameter: Parameter name or alias (required — e.g. "temperature",
                   "pm25", "no2"). Use get_parameters() for valid names.
        start: Start of time range in ISO 8601 (e.g. "2026-11-01T00:00:00Z")
        end: End of time range in ISO 8601 (default: now)
        radius_km: Search radius in kilometers (default 10, max 50)
        limit: Maximum readings per station (default 100, max 1000)

    Returns stations grouped by location, each with a time-ordered array of
    readings, plus parameter info and the actual time range covered.

    Invalid coordinates, unrecognized parameters, or unparseable dates return
    a structured error. Data source failures include cause and retry timing.

Input parameters:

- `end`
- `lat` (number, required)
- `limit` (integer)
- `lon` (number, required)
- `parameter` (string, required)
- `radius_km` (number)
- `start` (string, required)

Output parameters:

- `parameter` (string)
- `period_end` (string)
- `period_start` (string)
- `stations` (array)
- `total_readings` (integer)

### `get_data_freshness` (~144 tokens)

Check Data Freshness

Check how fresh the data is for each of the 10 sources.

    Returns sources with latest_observation timestamp, age_seconds, and a
    status classification: "fresh" (<1h), "stale" (<24h), "offline" (>24h),
    or "unreachable" (query failed for that source).

    Use this to verify data availability before querying readings, or to
    monitor source health. Individual source failures are reported per-source
    (status: "unreachable") rather than failing the entire call.

    This is also the server's health check — if this tool works, the server
    is operational.

Output parameters:

- `sources` (array)

### `search_bgi_measures` (~168 tokens)

Search BGI Measures

Search the Blue-Green Infrastructure measure catalog (44 measures).

    All parameters are optional — call with no args to list all measures.

    Args:
        goal: Filter by climate goal: flood, heat, drought, biodiversity, social
        category: Filter by category: water_retention, heat_mitigation,
                  surface_water, biodiversity
        keyword: Search in name, Dutch name, and description (e.g. "dak", "roof")
        limit: Max results (default 20, max 50)

    Returns measures with goal scores, category, scale, and maintenance level.
    Use get_measure_detail for full specs on a specific measure.

Input parameters:

- `category`
- `goal`
- `keyword`
- `limit` (integer)

Output parameters:

- `count` (integer)
- `last_updated`
- `measures` (array)

### `get_measure_detail` (~140 tokens)

Get BGI Measure Detail

Get full detail for one BGI measure: performance, costs, scores, constraints.

    Args:
        measure_id_or_slug: UUID or slug (e.g. "green-roof", "bioswale",
                           "permeable-paving"). Use search_bgi_measures to find
                           valid slugs.

    Returns complete measure spec: description, all goal scores with confidence,
    performance parameters (retention, cooling, infiltration, etc.) with ranges
    and units, CAPEX/OPEX costs, site requirements, co-benefits, constraint
    compatibility, and evidence count.

Input parameters:

- `measure_id_or_slug` (string, required)

Output parameters:

- `result` (string)

### `get_policy_requirements` (~149 tokens)

Get Municipality Policy Requirements

Get BGI policy requirements for a Dutch municipality.

    Extracted from Officiele Bekendmakingen (official government publications).
    Shows what's required, recommended, or subsidized per gemeente.

    Args:
        gemeente_code_or_name: CBS code (e.g. "GM0599") or municipality name
                              (e.g. "Rotterdam"). Use lookup_municipality to find codes.
        measure_slug: Optional — filter to one measure's requirements

    Returns requirements grouped by type (subsidy, regulation, obligation)
    with document titles, dates, amounts, and source URLs.

Input parameters:

- `gemeente_code_or_name` (string, required)
- `measure_slug`

Output parameters:

- `count` (integer)
- `gemeente_code` (string)
- `gemeente_name` (string)
- `last_updated`
- `requirements` (array)

### `lookup_municipality` (~92 tokens)

Lookup Municipality

Find Dutch municipalities by name or province.

    Returns CBS codes needed for other tools (get_policy_requirements,
    rank_measures). All 342 Dutch municipalities are searchable.

    Args:
        name: Partial name match (e.g. "Rotter" finds Rotterdam)
        province: Filter by province name (e.g. "Zuid-Holland")

Input parameters:

- `name`
- `province`

Output parameters:

- `count` (integer)
- `municipalities` (array)

### `rank_measures` (~218 tokens)

Rank BGI Measures for Municipality

Rank BGI measures for a municipality using policy-weighted scoring.

    Combines goal alignment, cost-effectiveness, and maintenance into a
    single ranked list. Use different policy profiles to see how priorities
    change the ranking.

    Args:
        gemeente_code: CBS municipality code (e.g. "GM0599" for Rotterdam).
                      Use lookup_municipality to find codes.
        goal: Optional boost for a specific goal (flood, heat, drought,
              biodiversity, social)
        policy_profile: Scoring profile — one of: Balanced, Flood-focused,
                       Heat-focused, Drought-focused, Biodiversity-first,
                       Cost-efficient (default: Balanced)
        limit: Max results (default 10, max 50)

    Premium tool — requires mcp:tools:premium scope when premium gating is
    enabled (MCP_PREMIUM_GATING=true).

Input parameters:

- `gemeente_code` (string, required)
- `goal`
- `limit` (integer)
- `policy_profile` (string)

Output parameters:

- `count` (integer)
- `gemeente_code` (string)
- `gemeente_name` (string)
- `last_updated`
- `measures` (array)
- `policy_profile` (string)

### `get_context_summary` (~116 tokens)

Get Environmental Context for Location

Get environmental and socioeconomic context for a location in the Netherlands.

    Returns the neighborhood (buurt), municipality, population density,
    green space accessibility, health indicators, and livability scores.

    Args:
        lat: Latitude in WGS84 (e.g. 51.92 for Rotterdam)
        lon: Longitude in WGS84 (e.g. 4.47 for Rotterdam)

    Useful for understanding the local context before recommending BGI measures.

Input parameters:

- `lat` (number, required)
- `lon` (number, required)

Output parameters:

- `avg_income`
- `buurt_code`
- `buurt_name`
- `dist_green_km`
- `dist_park_km`
- `dist_water_km`
- `gemeente_code`
- `gemeente_name`
- `good_health_pct`
- `last_updated`
- `leefbaarometer_fysiek`
- `overweight_pct`
- `population_density`
- `wijk_code`
- `woz_value`

### `compare_measures` (~105 tokens)

Compare BGI Measures

Side-by-side comparison of 2-5 BGI measures.

    Args:
        measure_slugs: List of 2-5 measure slugs (e.g. ["green-roof", "bioswale"]).
                      Use search_bgi_measures to find valid slugs.

    Returns aligned comparison with goal scores, key performance parameters
    (retention, cooling, infiltration), costs, maintenance level, and scale.

Input parameters:

- `measure_slugs` (array, required)

Output parameters:

- `count` (integer)
- `last_updated`
- `measures` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/mathisvfr-environmental-data/mcp#diagnostics

## Score history

- 2026-11-21: 73
- 2026-11-20: 72
- 2026-11-19: 72
- 2026-11-18: 71
- 2026-11-17: 71
- 2026-11-16: 70
- 2026-11-15: 70
- 2026-11-14: 70

## Common questions

### What is the Geo-Insights Environmental Data MCP server?

Geo-Insights Environmental Data is an MCP server listed in the public MCP registry as io.github.mathisvfr/environmental-data. Dutch environmental data + BGI climate adaptation: 12 tools, 44 measures, 35 parameters. No auth. This page covers its hosted endpoint (https://mcp.geo-insights.nl/mcp).

### Is the Geo-Insights Environmental Data MCP server safe to use?

Geo-Insights Environmental Data scores 73 out of 100 on VerifyMCP. 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 Geo-Insights Environmental Data MCP server expose?

Geo-Insights Environmental Data exposes 12 tools: list_sources, get_parameters, get_latest_readings, get_readings_history, get_data_freshness, and 7 more. Their descriptions and schemas cost roughly 2,011 tokens of context every time the server is loaded.

### Does the Geo-Insights Environmental Data MCP server require authentication?

No. We connected to Geo-Insights Environmental Data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Geo-Insights Environmental Data MCP server still maintained?

Geo-Insights Environmental Data 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 did VerifyMCP test on the Geo-Insights Environmental Data MCP server?

VerifyMCP ran 13 checks on Geo-Insights Environmental Data, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.geo-insights.nl/mcp
- Changelog RSS feed: https://verifymcp.io/servers/mathisvfr-environmental-data/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mathisvfr-environmental-data/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/mathisvfr-environmental-data/mcp.json
- HTML version of this page: https://verifymcp.io/servers/mathisvfr-environmental-data/mcp
