overspan-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| overpass_queryA | Run a raw Overpass QL query against the Overspan hosted Overpass API (full-planet OpenStreetMap data, minutes behind live). Use this when the helper tools are too narrow. Always bound the query to an area and cap the output (for example: out center 25;). Start with [out:json]. Queries without [timeout:] get 25 seconds. Read the overspan://overpass-ql resource for syntax and the overspan://differences resource for how this server differs from the public ones. |
| find_nearbyA | Find OpenStreetMap features matching tag filters within a radius of a point. Returns up to 'limit' elements with their tags and a centre coordinate. Good first tool for questions like 'what cafes are near X'. For larger or unknown result sets, call count_features first. |
| features_in_bboxA | Find OpenStreetMap features matching tag filters inside a bounding box (south, west, north, east in decimal degrees). Returns up to 'limit' elements with their tags and a centre coordinate. Keep boxes small; for city-sized areas call count_features first. |
| count_featuresA | Count OpenStreetMap features matching tag filters in an area without returning them. Cheap. Use this before pulling data when the result size is unknown. Give either a point (lat, lon, radius_m) or a bounding box (south, west, north, east). |
| get_usageA | Check this API key's tier, its limits, month-to-date quota, and recent request history. Does not consume query quota. Use it to pace yourself when running many queries. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| write-bounded-overpass-query | Turn a geographic question into a cheap, well-bounded Overpass QL query. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| overpass-ql-cheatsheet | The short version of Overpass QL: selectors, tag and spatial filters, output forms, and the habits that keep queries cheap. |
| overspan-differences | Defaults, caps, error shape, and quota headers on the Overspan hosted Overpass API. |
TDQS
Scored across 5 tools
find_nearby and features_in_bbox both fetch OSM features by location, but their radius-vs-bounding-box distinction is clearly explained and they cover different query shapes. overpass_query, count_features, and get_usage are each clearly separate from the helpers and from each other.
Most names use lowercase snake_case, but the conventions vary: overpass_query and features_in_bbox are noun-like, while find_nearby, count_features, and get_usage are verb-led. None are confusing, but there is no single predictable verb_noun pattern across the set.
Five tools is well-scoped for an Overpass API server: one raw query escape hatch, two standard spatial search helpers, a counting tool for sizing result sets, and a usage-monitoring tool. Each tool has a distinct role and none feel redundant.
The tool surface covers the core workflow well: count before pulling data, query by point or bounding box, and fall back to a raw Overpass query when helpers are too narrow. get_usage also covers the operational side of the hosted API, so there are no obvious dead ends.