junai-mcp
This server provides a pipeline orchestration and execution engine for managing AI-driven development workflows through a structured, stateful pipeline.
Pipeline Lifecycle
pipeline_init— Initialize a new pipeline state (requires explicit confirmation)pipeline_reset— Reset an existing pipeline for a new feature or after a failed runget_pipeline_status— Query current state and get the next recommended transition
Stage Control & Navigation
notify_orchestrator— Record stage completion and get the deterministic next transitionskip_stage— Skip the current stage (auto-approving any gates it would have satisfied)replay_stage— Reset a single stage tonot_startedfor re-execution (supervised mode only)
Supervision & Gating
set_pipeline_mode— Switch betweensupervised,assisted, andautopilotmodessatisfy_gate— Manually mark a supervision gate as satisfied to allow the pipeline to proceed
State & Notes Management
update_notes— Safely merge key-value pairs into the pipeline's_notessection (prevents concurrent-write conflicts)validate_deferred_paths— Validate and attempt automatic correction of file paths for deferred pipeline items
Command Execution
run_command— Execute arbitrary shell commands in the workspace root (e.g.,pytest,ruff,black, build steps) with configurable timeouts and output limits
Allows AI agents to manage a deterministic software development pipeline through GitHub Copilot Chat, with tools for pipeline initialization, state management, mode switching, gate approval, and command execution.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@junai-mcpStart a new pipeline for feature: dark mode"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
caddis — a Claude Code harness
caddis is a Claude Code harness — a plugin (plus a shared pool of skills, subagents,
slash-commands, and hooks) that makes a single Claude Code session dramatically more capable and much
harder to derail. It's agent-agnostic: the same pool is exported to other AI CLIs (Codex,
Antigravity, Copilot), and CLAUDE.md↔AGENTS.md are mirrors so every agent reads the same
conventions.
This repository is the published marketplace mirror: it hosts the caddis and caddis-extras
Claude Code plugins, the portable per-harness bundles under bundles/, and the shared pool. It is
generated and pushed by the caddis authoring repo's exporter — issues are welcome here, but code
changes land upstream and are synced in.
Install (Claude Code)
# 1. Register this repo as a plugin marketplace (once)
claude plugin marketplace add saajunaid/caddis-plugin
# 2. Install the core plugin (always-on, lean context)
claude plugin install caddis@caddis
# 3. (optional) Add the long-tail skill library — cloud/data/media/etc. Disabled by default,
# so it costs zero always-on context until you enable it.
claude plugin install caddis-extras@caddisThen, in any repo:
/caddis:setup-project-ai # deploy the harness into the projectA normal working loop looks like:
/feature-plan # (or /prd first) → writes .caddis/plans/<slug>.md, the durable spine
/implement # executes the plan phase-by-phase, TDD, commit per phase
/ship # express lane: commit → push → CI (hotfixes); feature work: /ship-pr then /ship-merge
/handoff # ALWAYS end a session with this — writes the resume docThe one habit that matters most: end every session with /handoff. It writes
.caddis/relay.md, which is re-injected automatically at the next session start — you resume with
zero re-discovery instead of a cold, forgetful session.
See USERGUIDE.md for the full command/skill/hook reference and the mental models.
Related MCP server: Bernstein - Multi-agent orchestration
What you get
Slash-commands —
/feature-plan,/prd,/implement,/tdd,/ship·/ship-pr·/ship-merge,/handoff,/kb,/digress·/resume,/cross-review,/usage-review,/mermaid-db·/excalidraw-db,/setup-project-ai,/migrate-dir.Subagents — lean, own-context helpers:
anchor(evidence-first verification),code-reviewer,preflight(plan-vs-codebase validation),tester,debug,codebase-audit,security-analyst,data-engineer,sql-expert,knowledge-transfer.A four-layer memory model — session relay (
relay.md), automatic Dream Memory (memory.jsonl), a per-repo knowledge base (.caddis/kb/+DOC-MAP.md), and cross-repo memory.Hooks & safety — a PreToolUse guard for secret/destructive writes, auto-lint on edit, and the SessionStart/Stop hooks behind relay + memory.
Tiered skills — the core dev set ships in
caddis; the long tail (cloud, data, media, productivity) lives incaddis-extras, off by default.
Installing outside Claude Code (Codex, Antigravity, …)
The knowledge layer (skills + AGENTS.md conventions) works in any harness. Per-harness bundles are
published under bundles/ and installed with caddis-init:
# from a checkout of this repo (the installer ships in plugin/scripts/)
python plugin/scripts/claudster_init.py --target codex --dest /path/to/project
python plugin/scripts/claudster_init.py --target antigravity --dest /path/to/projectSafe by design: a sha256 manifest tracks what the installer wrote; re-runs update only unmodified files, and anything you edited locally is reported as a conflict, never overwritten.
Repo layout
Path | What it is |
| The marketplace manifest ( |
| The core |
| The |
| Portable per-harness exports (codex, antigravity) for |
| The shared pool: skills, agents, prompts, instructions, tools |
| The build/sync machinery |
A note on names
caddis was previously published as claudster (and, before that, this repo hosted the junai
Copilot pipeline — see the pre-1.2 entries in CHANGELOG.md). Repos set up under
the old name have a .claudster/ artifact dir; everything reads both .caddis/ and .claudster/
and writes where the repo already lives, so nothing breaks. Run /caddis:migrate-dir when you
want a repo converted. The ~/.claudster/ user scope (keys, install records) is permanent.
License
MIT. The published plugin bundles (caddis / caddis-extras) carry the same license
in their manifests.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/saajunaid/caddis-plugin'
If you have feedback or need assistance with the MCP directory API, please join our Discord server