
Connects Claude to OpenCage's geocoding API with forward and reverse lookup tools. You get address-to-coordinates and coordinates-to-address conversion without managing your own API key, handled through Pipeworx's gateway with a 2500 request daily limit on the free tier. The two tools are straightforward: geocode takes an address string, reverse takes lat/long pairs. Runs over streamable HTTP, so no local process needed. Useful when you need location lookups in your Claude workflows but don't want to sign up for yet another API key or hit rate limits on a personal account.
OpenCage MCP — forward + reverse geocoding aggregator (OSM, GeoNames, Who's On First, etc). Free tier 2500 req/day. Key required.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
PLATFORM_OPENCAGE_KEY. BYO: ?_apiKey=….geocode(query, language?, limit?, countrycode?, bounds?, no_annotations?, abbrv?) — forward geocodereverse(lat, lon, language?, no_annotations?, abbrv?) — reverse geocodehttps://api.opencagedata.com/geocode/v1/json
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"opencages": {
"url": "https://gateway.pipeworx.io/opencages/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/opencages/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Opencages data" })
The gateway picks the right tool and fills the arguments automatically.
MIT