junai Pipeline MCP
Agentic pipeline orchestration MCP server for AI-driven development workflows.
Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
PIPELINE_STATE_PATHPath to pipeline-state.json. Defaults to .github/pipeline-state.json relative to the workspace root (detected by searching upward from the current directory for a .github folder).
JUNAI_WORKSPACE_ROOTExplicit workspace root path override. Use if automatic detection (searching upward for .github) does not find the correct root.
Ephemeral data sandbox for AI workflows with guardrails and security
Driverless delivery.
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…