MCP.Market

Overspan MCP server

by overspan.dev·dev.overspan/mcp·v0.1.2

OpenStreetMap queries as MCP tools, served by the Overspan hosted Overpass API.

B78/100grade B
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
Growing

0 stars46 downloads/wk

Reviews

Write one

Nobody has reviewed Overspan yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Overspan tools (5, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • count_features

    Count OpenStreetMap features matching tag filters in an area without returning them. Cheap.

  • features_in_bbox

    Find OpenStreetMap features matching tag filters inside a bounding box (south, west, north, east in decimal degrees).

  • find_nearby

    Find OpenStreetMap features matching tag filters within a radius of a point.

  • get_usage

    Check this API key's tier, its limits, month-to-date quota, and recent request history.

  • overpass_querywrite action

    Run a raw Overpass QL query against the Overspan hosted Overpass API (full-planet OpenStreetMap data, minutes behind live).

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • Code scan10 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 12 days ago15/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year5/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Overspan compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 48,255 servers
Tools
5
the typical server has 7
Tools that change things
20%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
46
more than 38% of 12,191 servers with a package

What its tools let an agent do: 4 read · 1 change

Install Overspan in Claude Code, Cursor or VS Code

Runs npx -y overspan-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y overspan-mcp
Add to Cursor

What the publisher says

From the Overspan repository's README, as published. We do not edit it. Read it on GitHub

overspan-mcp

An MCP (Model Context Protocol) server for Overspan, the hosted Overpass API. It gives Claude, Cursor, and any other MCP client direct, metered access to full-planet OpenStreetMap data: raw Overpass QL plus helper tools for nearby search, bounding-box search, counting, and usage checks.

You need an Overspan API key. Plans start at $19/month at overspan.dev; the key arrives by email after checkout, no account needed.

Quickstart

Claude Code

claude mcp add overspan --env OVERSPAN_API_KEY=YOUR_KEY -- npx -y overspan-mcp

Claude Desktop, Cursor, and other JSON-configured clients

{
  "mcpServers": {
    "overspan": {
      "command": "npx",
      "args": ["-y", "overspan-mcp"],
      "env": {
        "OVERSPAN_API_KEY": "YOUR_KEY"
      }
    }
  }
}

The key must be in the server's env block. MCP clients start servers with their own environment, so a variable exported in your shell profile will not reach it. Treat any config file containing the key as a secret; in Claude Code's .mcp.json you can write "OVERSPANAPIKEY": "${OVERSPAN_KEY}" to keep the key in your environment and out of the file.

Tools

The server also exposes two resources the model can read (overspan://overpass-ql, a QL cheat sheet, and overspan://differences, how Overspan differs from the public servers) and one prompt (write-bounded-overpass-query).

Behaviour worth knowing

  • The key is sent as an Authorization: Bearer header, never in a URL.
  • Every successful tool result carries a quota line ([quota] 49998 of 50000 monthly requests remaining) so an agent can pace itself. get_usage gives the full picture and is free to call.
  • Errors come back in plain language with the gateway's error code, what it means, and whether to retry. Rejected requests do not consume quota, and a runaway loop is bounded by the key's own rate and concurrency caps, never by a larger bill.
  • Oversized responses are trimmed to fit a model's context: for Overpass JSON the element list is cut and the result says how many elements were dropped. Raise the cap with OVERSPANMAXRESPONSE_CHARS if you want more.
  • Queries without [timeout:] get 25 seconds. Set it explicitly for heavy queries, up to your tier's cap.

Environment variables

Data licence

Results are OpenStreetMap data, licensed under the Open Database License. Anything you publish that shows or derives from this data needs a visible credit reaching openstreetmap.org/copyright. Your Overspan subscription pays for hosting and access, not for the data, and does not change those obligations.

Development

npm install
npm run build
npm test

The test suite covers the query builders, response shaping, error mapping, and a full in-memory MCP client round trip.

Links

  • Overspan documentation
  • Error reference
  • Usage dashboard

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Overspan: common questions

Is Overspan MCP server safe?
Mostly: it is graded B (78/100). Read the Overspan safety report
How do I install Overspan?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Overspan need an API key?
Yes. The registry entry asks for OVERSPAN_API_KEY.
Is Overspan maintained?
The last commit was 16 days ago (2026-10-19). The latest release is v0.1.2.
How does Overspan compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); tools 5 (the typical server has 7); tools that change things 20% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.