Trackio
Provides MCP server functionality for trackio experiment tracking by automatically monkey-patching Gradio applications to expose trackio data through MCP tools. The implementation uses a direct patching approach that activates on import, enabling AI assistants to query experiment projects, runs, metrics, and statistics through a standardized API without requiring code changes to existing trackio workflows. Built for machine learning researchers and developers who want to make their experiment tracking data accessible to AI agents for analysis, comparison, and reporting tasks, with support for deployment to Hugging Face Spaces for remote access.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/fcakyon/trackio-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Trackio from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.