mcp-zenodo
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZENODO_API_TOKEN | Yes | Your Zenodo API token for authentication |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_recordsB | |
| get_citationA | Get a citation for a Zenodo record in the specified format. |
| detect_data_typeA | Determine if a Zenodo record is a dataset, software, or article. |
| get_metadataB | Retrieve detailed metadata for a Zenodo record. |
| list_filesA | List all files available in a Zenodo record. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct aspect: search_records for querying, get_citation for citations, detect_data_type for classification, get_metadata for detailed metadata, and list_files for files. There is no meaningful overlap between their purposes.
All tool names follow a consistent verb_noun pattern in snake_case (search_records, get_citation, detect_data_type, get_metadata, list_files). The verbs clearly indicate the action, and the nouns indicate the resource aspect.
Five tools is well-scoped for a server focused on searching and retrieving Zenodo records. Each tool earns its place, and the count is within the ideal 3-15 range without feeling thin or bloated.
The tool set covers the core read-only workflow: search, retrieve metadata, list files, get citations, and detect data types. Minor gaps exist (e.g., no direct record download, no deposit/update functionality), but for a read-oriented server the surface is largely complete.