junai Pipeline MCP
Quality Score
82
/100
Agentic pipeline orchestration MCP server for AI-driven development workflows.
§01 Install
Claude Desktop (uvx)
{
"mcpServers": {
"junai-mcp": {
"command": "uvx",
"args": [
"junai-mcp"
],
"env": {
"PIPELINE_STATE_PATH": "<pipeline_state_path>",
"JUNAI_WORKSPACE_ROOT": "<junai_workspace_root>"
}
}
}
}§02 Environment variables
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.
§03 MCP Quality Score · methodology
freshness
22
completeness
15
installability
25
documentation
15
stability
5
§04 Alternatives in Cloud Storage
ai.aliengiraffe/spotdb
ai.aliengiraffe/spotdb
Ephemeral data sandbox for AI workflows with guardrails and security
ai.smithery/STUzhy-py_execute_mcp
ai.smithery/STUzhy-py_execute_mcp
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
ai.smithery/flight505-mcp_dincoder
ai.smithery/flight505-mcp_dincoder
Driven Intent Negotiation — Contract-Oriented Deterministic Executable Runtime DinCoder brings the…