How to Use the GBIF MCP in Claude Code

Q: How do I use Claude Code to get GBIF data for a list of species from a file?

Use a standard shell loop. while read sp; do claude mcp call gbif-mcp searchgbifspecies --name "$sp"; done

Q: What's the fastest way to find a species key from the terminal?

Pipe the output to jq to extract the field you need. claude mcp call gbif-mcp searchgbifspecies --name "Loxodonta africana" jq .result.key. This gives you just the key, ready to be used in a variable.

Q: Can I use Claude Code to monitor GBIF for new observations?

Yes. Set up a cron job that runs a shell script. The script would use getgbifoccurrences, check the eventDate of the latest records, and trigger an alert if new ones appear. It's a perfect use case for this MCP server.

Q: What does the getgbifoccurrences tool return?

It returns a JSON array of occurrence objects. Each object contains fields like decimalLatitude, decimalLongitude, eventDate, and the dataset key. It's raw, structured data ready for processing with tools like jq or miller.

Q: How does the GBIF MCP Server handle security for Claude Code in CI/CD?

Your Vinkius endpoint token is the only secret. The connection is over TLS, and the server itself is ephemeral—it doesn't store any data from your queries, like the species names you search for. It's built for secure, headless environments.

Query 2.4 billion GBIF records from the command line. Pipe species data into any script with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GBIF MCP to Claude Code

Create your Vinkius account to connect GBIF to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup GBIF with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Ecological Data Pipelines

Run `claude mcp call gbif-mcp search_gbif_species --name "Panthera leo"` and pipe the output directly to jq. You get a clean JSON object with the species key and full taxonomy, ready for the next step in your script. This is built for headless execution in your CI/CD pipeline. No browser, no GUI, just raw data flowing through your terminal.

Script Species Occurrence Lookups

Chain commands together in any shell script. Get a species key with `search_gbif_species`, then feed that key into a second call to `get_gbif_occurrences` to pull all observation coordinates worldwide. You can automate nightly checks for new sightings of a species of interest. Pipe the results to another service, write them to a database, or trigger an alert. It's all done from the command line.

Query GBIF from any Terminal with this MCP Server

This MCP server turns the massive GBIF database into a set of simple command-line tools. You don't need to handle OAuth or rotate API keys. Just connect Claude Code once. After that, you can run `get_gbif_species` from a Docker container, an SSH session, or a GitHub Action to get taxonomic details on the fly. It just works.

Setup guide

Set up GBIF MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see gbif-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest GBIF transactions." It will automatically discover and invoke the available GBIF tools.

Terminal

claude mcp add --transport http gbif-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the GBIF MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "gbif-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by GBIF. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect GBIF now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about GBIF MCP in Claude Code

Use a standard shell loop. `while read sp; do claude mcp call gbif-mcp search_gbif_species --name "$sp"; done < species.txt`. This is exactly what Claude Code is for—integrating MCP tools into standard Unix workflows.

Pipe the output to jq to extract the field you need. `claude mcp call gbif-mcp search_gbif_species --name "Loxodonta africana" | jq .result.key`. This gives you just the key, ready to be used in a variable.

Yes. Set up a cron job that runs a shell script. The script would use `get_gbif_occurrences`, check the `eventDate` of the latest records, and trigger an alert if new ones appear. It's a perfect use case for this MCP server.

It returns a JSON array of occurrence objects. Each object contains fields like `decimalLatitude`, `decimalLongitude`, `eventDate`, and the dataset key. It's raw, structured data ready for processing with tools like jq or miller.

Your Vinkius endpoint token is the only secret. The connection is over TLS, and the server itself is ephemeral—it doesn't store any data from your queries, like the species names you search for. It's built for secure, headless environments.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript