erddap-mcp

by mrfentmen

Overview Schema Source Related Servers Discussions Admin

Python

Remote

query_griddap

Query gridded satellite SST or analysis datasets at a point or lat/lon box, defaulting to the latest grid time.

Instructions

Query a gridded dataset (satellite SST, analysis fields) at a point or lat/lon box; time defaults to the latest grid.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "query_griddap"
  }
}

Input Schema

Name	Required	Description
`time`	No	'last' (default), 'first', a row index, or ISO timestamp.
`depth`	No	Optional depth/altitude value.
`server`	No	Server nickname or URL.
`stride`	No	Take every Nth grid cell (default 1; raise it for wide boxes).
`lat_max`	No	Latitude upper bound.
`lat_min`	No	Latitude lower bound.
`lon_max`	No	Longitude upper bound.
`lon_min`	No	Longitude lower bound.
`variable`	No	One data variable, e.g. 'analysed_sst'.
`dataset_id`	No	Dataset ID (must be a Grid dataset).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 30, 2026

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden and mostly does not: only the time default ("time defaults to the latest grid") is disclosed. Nothing is said about read-only semantics, response size for wide boxes, whether stride silently subsamples results, error behavior for invalid dataset_id, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the resource first and the default-behavior caveat second; no filler and nothing that restates the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with no annotations and no output schema, the description is thin: it omits dataset_id discovery, server selection, and any sense of the returned structure or size. The schema covers parameters well, but the behavioral and entry-point context an agent needs is largely absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does add the useful framing that lat/lon bounds define a box (or a degenerate point), which the flat schema doesn't state, but it gives no guidance on the required combination of lat/lon pairs, the variable choice, or how stride interacts with box size.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Query a gridded dataset") plus concretely what data types it covers (satellite SST, analysis fields) and the spatial modes (point or lat/lon box). This implicitly separates it from the sibling query_tabledap, but never names that sibling or the dataset-type distinction explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by "gridded dataset ... at a point or lat/lon box," but there is no explicit when-to-use-vs-query_tabledap guidance, no mention of calling search_datasets/dataset_info first to obtain a valid dataset_id, and no prerequisites such as required server auth.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server