---

Tools

4 tools for querying global earthquake data from USGS and EMSC:

earthquake_get_feed

Fetch a USGS pre-computed real-time earthquake feed by magnitude tier and time window.

• CDN-cached by USGS — faster and more available than the FDSN query API
• Five magnitude tiers: all (microseisms), 1.0, 2.5, 4.5, and significant (USGS-curated by magnitude, felt reports, and PAGER impact)
• Four time windows: hour, day, week, month
• Returns event list with counts and the source feed URL
• Paged with an opaque cursor: limit bounds a page (default 100, max 1000), totalCount reports the whole feed, and nextCursor retrieves the rest — the broad tiers run past 10,000 events for month
• The cursor is opaque because these feeds have no upstream paging parameter and USGS regenerates them about once a minute; a numeric offset across two calls would skip or repeat events
• Best for real-time "what's happening now" queries; use earthquake_search for historical or filtered queries

---

earthquake_search

Search earthquakes by time range, magnitude, depth, location radius, PAGER alert level, or felt reports.

• Dual-source: USGS (global, richer metadata) or EMSC (an independent global catalog from the European-Mediterranean Seismological Centre, for cross-verification anywhere)
• Full FDSN ComCat query API parameters: time range, magnitude, depth, location radius
• USGS-specific filters: PAGER alert level (green/yellow/orange/red), DYFI felt reports count, significance score, event type
• Every event carries an event_type in one vocabulary whichever source served it — the QuakeML names USGS publishes (earthquake, quarry blast, explosion, ice quake); EMSC's two-character code is decoded to the same names, with how sure EMSC was kept beside it in event_certainty — and the event_type filter narrows to one of them on USGS
• Location-based queries: provide latitude, longitude, and radius_km together
• Rectangular study areas: min_latitude, max_latitude, min_longitude, max_longitude, each independently optional and forwarded to both sources; combining a box with the radius circle intersects the two. Longitude accepts up to ±360 so a box can cross the antimeridian
• Sort by time (newest first) or magnitude (largest first), ascending or descending
• One call returns at most 20,000 events; page beyond that with offset, forwarded straight to the upstream FDSN offset parameter on both sources
• offset counts from 1, matching both upstream APIs — a capped result carries totalCount and the nextOffset to pass on the following call, and says so with countUnavailable when the follow-up count query failed rather than leaving the total silently absent
• Use earthquake_count first to gauge result size
• USGS-specific filters are not supported by EMSC — when source=emsc they are dropped and named in ignoredFilters, so an unconstrained result set is never mistaken for a filtered one

---

earthquake_count

Count earthquakes matching filters without fetching full records.

• Lightweight alternative to earthquake_search for statistical queries ("how many M5+ events in 2025?")
• Same filter surface as earthquake_search: time, magnitude, depth, location radius, bounding box, PAGER, DYFI, significance, event type
• A radius over a mining region counts quarry blasts alongside earthquakes — pass event_type="earthquake" on USGS to exclude them
• Returns exceeds_limit flag when count exceeds 20,000 — signals a full search needs paging
• Echoes the effective query back as queryEcho, including the resolved time window — omitting start_time counts only the last 30 days
• USGS returns the max_allowed cap (20,000); EMSC count endpoint does not expose this field (max_allowed will be null)
• USGS-specific filters are dropped and named in ignoredFilters when source=emsc, the same as on earthquake_search

---

earthquake_get_event

Fetch complete detail for a specific earthquake by USGS event ID.

• Returns the normalized event a search result already carries, plus detail — a projection of the analysis products only the single-event response holds
• detail groups: PAGER alert and report link, ShakeMap peak MMI/PGA/PGV and intensity map, DYFI response count and max CDI, moment-tensor scalar moment and nodal planes, landslide and liquefaction alerts, origin quality (azimuthal gap, station count, location and depth uncertainty), finite-fault rupture length and width
• A group is omitted when USGS produced no such product — a small automatic event usually has none, a large reviewed one has most of them
• Event IDs appear in the id field of earthquake_get_feed and earthquake_search results (e.g. us6000sznj, hv74966427)
• USGS-only — EMSC events have no per-event detail endpoint

Resources

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per tool, framework handles registration and validation
• Unified error handling across all tools
• Pluggable auth (none, jwt, oauth)
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• Runs locally (stdio/HTTP) or on Cloudflare Workers from the same codebase

Earthquake-specific:

• Two independent global data sources: USGS ComCat (full metadata) and EMSC SeismicPortal (an independent catalog from the European-Mediterranean Seismological Centre, with no PAGER/DYFI/ShakeMap metadata and station coverage densest around Europe and the Mediterranean)
• USGS real-time GeoJSON feeds (CDN-cached, fast availability) plus FDSN event query API
• EMSC FDSN-WS event and count endpoints
• No API key required — both USGS and EMSC are fully public

Agent-friendly output:

• Source attribution on every response (usgs / emsc) so agents can reason about data provenance
• exceeds_limit flag on count responses surfaces truncation risk before a full search
• Fields a source does not publish come back null, never as a fabricated zero — tsunami and status are null on EMSC events, and the rendered text says "not published by source" rather than "no tsunami" or "reviewed"
• source_catalog and auth carry provenance (which catalog and which authoritative agency produced a solution) so agents can weigh two sources against each other
• USGS-only filters dropped for an EMSC query are named in ignoredFilters on both earthquake_search and earthquake_count
• An upstream rejection surfaces the service's own explanation (the offending parameter and its accepted format) in the error message, not just a status code; when the service explains nothing, the error says so under its own reason rather than passing the raw upstream body through
• event_type travels with every event, so a quarry blast or explosion is never silently read as an earthquake, and event_certainty keeps a suspected one from reading as confirmed

Getting started

Public Hosted Instance

A public instance is available at https://earthquake.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "earthquake-mcp-server": {
      "type": "streamable-http",
      "url": "https://earthquake.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "earthquake-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/earthquake-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "earthquake-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/earthquake-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "earthquake-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/earthquake-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.3.0 or higher.
• No API keys required — USGS and EMSC data is fully public.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/earthquake-mcp-server.git

2. Navigate into the directory:

cd earthquake-mcp-server

3. Install dependencies:

bun install

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

Running the server

Local development

• Build and run the production version:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:http
  # or
  bun run start:stdio
  

• Run checks and tests:

  bun run devcheck  # Lints, formats, type-checks, and more
  bun run test      # Runs the test suite
  

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for logging, ctx.state for storage
• Register new tools and resources in the createApp() arrays

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.