Is the pypi:fiftyone-mcp-server MCP server safe to use?
Independent trust grade A- (92/100). Static analysis of PyPI package fiftyone-mcp-server@0.1.12 (source: github.com/voxel51/fiftyone-mcp-server) — stdio server, no remote endpoint. Runtime behavior not measured. wmcp.sh continuously watches pypi:fiftyone-mcp-server for tool drift and rug-pulls. The grade is free and identical whether or not the operator pays.
What it offers — 29 tools · Government & Data
count_values
distinct
bounds
mean
sum
std
histogram_values
get_values
get_app_config
get_color_scheme
set_color_scheme
get_sidebar_groups
set_sidebar_groups
set_active_fields
list_datasets
load_dataset
dataset_summary
list_brain_runs
+11 more tools
Spec / packaging20%100
✓ depends on an MCP SDK (mcp/fastmcp)
✓ 29 tool(s) detected in source
Security (OWASP MCP)30%90
no high-risk patterns in sampled source
scanned 6 source files from GitHub
Maintenance / popularity20%100
published within 90 days
13 releases, 107 downloads/wk
Tool hygiene15%80
3 declared deps
public repo
Transparency / provenance15%85
✓ repo: github.com/voxel51/fiftyone-mcp-server
✓ Apache-2.0 license
Findings
INFO Static analysis of PyPI package fiftyone-mcp-server@0.1.12 (source: github.com/voxel51/fiftyone-mcp-server) — stdio server, no remote endpoint. Runtime behavior not measured.
We re-grade pypi:fiftyone-mcp-server on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.
Share this report card
A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.
A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.
Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:
https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.