A practical MCP workflow
Research species and biodiversity records with MCP
Search for the scientific name, inspect candidate taxonomy records and use the returned backbone occurrence taxon key for a filtered summary. Preserve source links and treat record counts as an overview of reported observations rather than a population estimate.
Built for: Researchers, educators and agents investigating biodiversity records and taxonomy.
What to connect
Create a ToolCargo account and use OAuth or an API key with a supported MCP client. Hosted connectors share your plan’s call quota; connect each required MCP endpoint separately. Review provider permissions before starting.
Run the workflow
1. Find candidate names
Call gbif_search_species with a specific scientific name. Search spans different checklists; inspect the dataset, rank, taxonomic status and accepted-name references. Similar names and synonyms require review.
2. Inspect taxonomy and the occurrence key
Use gbif_species_details with the exact candidate key. Keep classification and checklist provenance. Use occurrenceTaxonKey for the occurrence summary; a checklist record key is not automatically a GBIF backbone occurrence key.
3. Request a bounded summary
Call gbif_occurrence_summary with occurrenceTaxonKey set to that returned backbone key and your country or year filters. Preserve count and reported facets. The summary does not fetch raw observations, people, coordinates or media.
4. Review source data before drawing conclusions
Reported record counts can include duplicates and uneven sampling. Partial top facets are not complete distributions. Zero records does not establish absence, and records do not establish current presence or a population estimate. Review original datasets, quality flags, licenses and GBIF citation instructions for further analysis.
A prompt to try
Find Panthera leo in GBIF, inspect candidate taxonomy records and confirm the occurrenceTaxonKey. Summarize reported occurrences for South Africa (ZA). Retain source links and explain why record counts do not estimate population or establish current presence.
What a useful result looks like
Candidate scientific names with taxonomic status and source checklist identifiers. Exact taxonomy details with a backbone occurrence key when supplied. Filtered count and bounded occurrence-year and record-basis facets. Source links and explicit limitations for subsequent dataset review.
Know the limits
The GBIF catalogue is dynamic; classification and indexed records can change. Search ranking is not a scientific-name resolution or identification of an organism. The summary does not verify taxon identity in an additional request; inspect taxonomy first. No raw observations, coordinates, images, bulk downloads or citation DOI are generated.
Common questions
Does a zero count mean the species is absent?
No. It means no indexed records matched that request at lookup time. Sampling gaps, filters and taxon-key choice can affect the result.
Can I cite the summary as a GBIF download?
No download DOI is created. Follow GBIF citation instructions and inspect the contributing datasets and their licenses before publication or reuse.
References and tool documentation
Use the provider’s documentation to check the underlying concepts, and ToolCargo’s references for the exact tools, inputs and limits.
- GBIF API reference
Check public API access, source attribution guidance and paging limitations.
- GBIF Species API
Review taxonomy search, scientific-name keys and checklist records.
- GBIF Occurrence API
Review occurrence filters and count/facet semantics.
Tool references for this workflow
Continue with the tools
Related workflows
- Find image candidates and inspect their credits with AI and MCP
- How to run an SEO audit with an AI agent and MCP
- Find keyword opportunities with Google Search Console and MCP
- Compare npm and PyPI packages with an AI agent
- Monitor SEO changes after launch with an AI agent and MCP
- Find research papers and verify DOI metadata with an AI agent
- Check npm and PyPI package vulnerabilities with an AI agent
- Find life-sciences publications with Europe PMC and MCP
- Find research datasets with an AI agent and DataCite MCP
- Review Rust crate versions and dependencies with MCP
- Compare public AI model and dataset metadata with MCP
- Find books and compare editions with MCP
- Resolve entities and review Wikidata statements with MCP
- Review US weather forecasts with an AI agent and MCP
- Compare country indicators with AI and World Bank MCP