Dataset ViewerSAFE
MCP server for Hugging Face dataset viewer
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server for interacting with the Hugging Face Dataset Viewer API, providing capabilities to browse and analyze datasets hosted on the Hugging Face Hub.
Features
Resources
- Uses
dataset://URI scheme for accessing Hugging Face datasets - Supports dataset configurations and splits
- Provides paginated access to dataset contents
- Handles authentication for private datasets
- Supports searching and filtering dataset contents
- Provides dataset statistics and analysis
Tools
The server provides the following tools:
- validate
- Check if a dataset exists and is accessible
- Parameters:
dataset: Dataset identifier (e.g. 'stanfordnlp/imdb')auth_token(optional): For private datasets
- get_info
- Get detailed information about a dataset
- Parameters:
dataset: Dataset identifierauth_token(optional): For private datasets
- get_rows
- Get paginated contents of a dataset
- Parameters:
dataset: Dataset identifierconfig: Configuration namesplit: Split namepage(optional): Page number (0-based)auth_token(optional): For private datasets
- get_first_rows
- Get first rows from a dataset split
- Parameters:
dataset: Dataset identifierconfig: Configuration namesplit: Split nameauth_token(optional): For private datasets
- get_statistics
- Get statistics about a dataset split
- Parameters:
dataset: Dataset identifierconfig: Configuration namesplit: Split nameauth_token(optional): For private datasets
- search_dataset
- Search for text within a dataset
- Parameters:
dataset: Dataset identifierconfig: Configuration namesplit: Split namequery: Text to search forauth_token(optional): For private datasets
8250ff8a8ed9OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add dataset-viewer --env HUGGINGFACE_TOKEN=${HUGGINGFACE_TOKEN} -- uvx dataset-viewer{
"mcpServers": {
"dataset-viewer": {
"command": "uvx",
"args": [
"dataset-viewer"
],
"env": {
"HUGGINGFACE_TOKEN": "${HUGGINGFACE_TOKEN}"
}
}
}
}Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
filter | read | Filter rows in a Hugging Face dataset using SQL-like conditions |
get_first_rows | read | Get first rows from a Hugging Face dataset split |
get_info | read | Get detailed information about a Hugging Face dataset including description, features, splits, and statistics. Run validate first to check if the dataset exists and is accessible. |
get_parquet | read | Export Hugging Face dataset split as Parquet file |
get_rows | read | Get paginated rows from a Hugging Face dataset |
get_statistics | read | Get statistics about a Hugging Face dataset |
search_dataset | read | Search for text within a Hugging Face dataset |
validate | read | Check if a Hugging Face dataset exists and is accessible |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
8250ff8a8ed9full audit observations/trust-audit/mcp-server/privetin__dataset-viewer.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 8250ff8a8ed9 | SAFE | B | 89 | first audit |
Questions
What is the Dataset Viewer MCP server?
MCP server for Hugging Face dataset viewer
What tools does Dataset Viewer expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Dataset Viewer safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Dataset Viewer need?
It reads HUGGINGFACE_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Dataset Viewer run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as dataset-viewer.
How current is this page?
The grade is for one exact copy of the source (8250ff8a8ed9), read on 2026-10-08. The repository is watched and re-audited when it changes.