# Idigbio

> Idigbio is a freemium MCP server for health and science. Search and retrieve digitized natural-history museum specimen records via an MCP server. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $49 a month
- **Platforms:** API, CLI, self-hosted
- **Website:** https://pipeworx.io/packs/idigbio
- **Repository:** https://github.com/pipeworx-io/mcp-idigbio
- **MCP Registry name:** io.github.pipeworx-io/idigbio
- **Categories:** [health and science](https://ai-powered.com/categories/health-and-science)
- **Listing updated:** 2026-11-18

## About

The server gives AI clients access to iDigBio, an index of roughly 150 million digitized specimen records from US natural-history collections covering plants, animals and fossils. Searches can be filtered by taxonomy and locality, though at least one filter is required. A separate lookup returns the full normalized record for a single specimen by its UUID, and a counting tool groups specimens by a chosen field to show top values and totals.

The README describes it as a thin stdio bridge to the Pipeworx gateway, so calls are forwarded to a hosted endpoint rather than run locally. Connections are anonymous by default with a daily call cap; an optional Pipeworx API key raises the limit. The endpoint also lists shared gateway meta-tools such as ask_pipeworx alongside the three pack tools.

It suits researchers, curators and developers who want an agent to query museum occurrence data without building their own iDigBio integration. The project is an unofficial integration and is not affiliated with iDigBio.

## Features

- **Specimen search by filters:** Find records by combining taxonomy and locality filters, with at least one filter required.
- **Single record lookup:** Fetch the full normalized record for one specimen using its UUID.
- **Grouped specimen counts:** Count specimens by a chosen field and see the top values with totals, optionally scoped by filters.
- **Anonymous or keyed access:** Works without a key at a daily cap, and an optional Pipeworx API key raises the limit.
- **Multiple connection options:** Can be used via a remote streamable-http endpoint or a local npx stdio bridge.

## Good for

- Finding museum specimens of a given species within a region
- Pulling the full record for a specific specimen UUID for citation or verification
- Summarizing how specimen records are distributed across taxa or localities
- Letting an AI assistant answer biodiversity occurrence questions from iDigBio data

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http idigbio https://gateway.pipeworx.io/idigbio/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://gateway.pipeworx.io/idigbio/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "idigbio": {
      "url": "https://gateway.pipeworx.io/idigbio/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "idigbio": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/idigbio/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "idigbio": {
      "serverUrl": "https://gateway.pipeworx.io/idigbio/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "idigbio": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/idigbio/mcp"
    }
  }
}
```

## Tools

- `search_specimens`: Search digitized natural-history specimen records from US collections by taxonomy and locality filters.
- `get_specimen`: Get the full normalized record for a single specimen by UUID.
- `count_by_field`: Get grouped specimen counts by a field with optional taxonomy and locality filters.

## FAQ

### Do I need an API key to use it?

No. The README says calls are anonymous without a key and capped at 50 per day; a free Pipeworx account raises the cap to 200 per day.

### Does the server only expose the iDigBio tools?

The README says the hosted endpoint also lists shared Pipeworx meta-tools such as ask_pipeworx. The npm bridge lists only the pack's tools unless PIPEWORX_META_TOOLS=1 is set.

### Can I search without any filter?

No. The search tool requires at least one taxonomy or locality filter.

### Is Idigbio free?

Idigbio has a free plan, with paid plans for more usage or features. Paid plans start at $49 a month.

### How do I add Idigbio to Claude Code?

Run this command in your terminal: claude mcp add --transport http idigbio https://gateway.pipeworx.io/idigbio/mcp

### What are the best alternatives to Idigbio?

The closest alternatives to Idigbio are Gdc, Ensembl, Ebi Ols, Opentreeoflife and Science.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Gdc](https://ai-powered.com/mcp/gdc): Gdc is a freemium MCP server for health and science.
- [Ensembl](https://ai-powered.com/mcp/ensembl): Ensembl is a freemium MCP server for health and science.
- [Ebi Ols](https://ai-powered.com/mcp/ebi-ols): Ebi Ols is a freemium MCP server for health and science.
- [Opentreeoflife](https://ai-powered.com/mcp/opentreeoflife): Opentreeoflife is a freemium MCP server for health and science.
- [Science](https://ai-powered.com/mcp/science): Science is a freemium MCP server for health and science.
- [Npi Registry](https://ai-powered.com/mcp/npi-registry): Npi Registry is a freemium MCP server for health and science.
- [Complex Portal](https://ai-powered.com/mcp/complex-portal): Complex Portal is a freemium MCP server for health and science.

---
Source: https://ai-powered.com/mcp/idigbio
