33GOD Pipeline MCP Hub
Click on "Deploy 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., "@33GOD Pipeline MCP Hub list available domains"
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.
33GOD Pipeline MCP Hub
A multi-domain MCP server that fronts many tool domains (Plane, BloodBank, ticket-lifecycle, …) behind one small, stable surface — so an agent isn't flooded with hundreds of tool schemas / millions of tokens.
Served at https://mcp.delo.sh/mcp (header-PAT auth).
How it works — discovery + dispatcher gating
The hub exposes only three tools to clients:
Tool | Purpose |
| List available domains (name, description, tool_count). Start here. |
| Load + list one domain's tools, each with its |
| Invoke a specific domain tool; |
Underlying domain tools are held in an internal registry and are never advertised
directly, so the per-request tool-schema cost stays tiny and constant. This works on
any MCP client regardless of notifications/tools/list_changed support.
Trade-off: domain tools are invoked through
call_domain_tool(...)rather than as native function calls. The hub validates arguments against the real tool schema and returns clear errors. (A future "native passthrough" mode could expose real prefixed tools for clients that already defer schemas, like Claude Code.)
Related MCP server: fastmcp-gateway
Domains
plane — reuses
plane-mcp-server's tools in-process (work items, projects, cycles, epics, etc.). Auth + Plane API calls use the caller's PAT from the request context.bloodbank (Phase 1) — publish/trace events on the BloodBank NATS bus.
lifecycle (Phase 2) — opinionated ticket state machine (pull → triage → … → done).
Auth
HTTP mode uses the same header scheme as plane-mcp-server:
Authorization: Bearer <PLANE_PAT>x-workspace-slug: <workspace-slug>
Run locally
# Install the hub + the plane domain dependency (from the local checkout)
uv pip install -e .
uv pip install -e ../../plane-mcp-server
# stdio (no auth; Plane tools use env fallback)
PLANE_API_KEY=... PLANE_WORKSPACE_SLUG=... python -m mcp_hub stdio
# http (header-PAT auth) on :8998 at /mcp
PLANE_INTERNAL_BASE_URL=http://localhost:8000 python -m mcp_hub httpDeploy (DeLoNET)
Docker stack at ~/docker/stacks/ai/pipeline-mcp-hub/. It builds this repo and pulls the
plane-mcp-server source via a named build context, joins the proxy network, and is
routed by Traefik at Host(mcp.delo.sh). *.delo.sh already wildcards through the
Cloudflare tunnel → Traefik.
cd ~/docker/stacks/ai/pipeline-mcp-hub
docker compose up -d --buildRequires Docker Compose ≥ v2.17 (for build.additional_contexts).
Key env
Var | Default | Purpose |
|
| Listen port inside the container |
| — | Server-to-server Plane API base; set to |
|
| Fallback Plane API base |
Phase 0 needs no secrets — the Plane PAT arrives per-request in the client's headers.
Available Tools
2 toolscall_domain_toolA
Invoke a specific tool within a domain and return its result.
arguments is a JSON object that must conform to that tool's input_schema
(from list_domain_tools(domain)). Example:
call_domain_tool("plane", "list_projects", {})
Inputs: tool (required), domain (required), arguments.
list_domainsA
List the tool domains available in this hub. START HERE.
Each domain bundles many underlying tools that are intentionally NOT loaded into your context yet. Returns each domain's name, title, description, tool_count, and load status. To use a domain, call list_domain_tools(domain) to load its tool schemas, then invoke a tool with call_domain_tool(domain, tool, arguments).
Inputs: no named parameters. Returns: Generic wrapper for non-object return types.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: list_domains for discovery and call_domain_tool for invocation. No overlap at all.
Both tools follow a consistent verb_noun snake_case pattern (list_domains, call_domain_tool), making them predictable and clear.
With only 2 tools, the set feels thin, but for a hub server that delegates to domains, this minimal surface is acceptable and focused.
The hub is missing the list_domain_tools tool, which is advertised in list_domains' description. Without it, users cannot discover and invoke tools within domains, causing a critical gap.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for progressive tool usage at any scale (see https://klavis.ai)
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA progressive-disclosure gateway for MCP servers that keeps tool lists small by exposing one top-level tool per server, allowing agents to search, list, inspect, and call underlying tools within a selected domain.14MIT
- AlicenseNot gradedqualityBmaintenanceAggregates tools from multiple upstream MCP servers and exposes them through 4 meta-tools, enabling LLMs to discover and use hundreds of tools without loading all schemas upfront.113 PyPI3Apache 2.0
- AlicenseAqualityDmaintenanceAggregates tools from multiple MCP servers, acting as a proxy to provide unified access to various AI agents and tools.1020 npm3MIT

MetaMCPofficial
AlicenseAqualityBmaintenanceAggregates multiple MCP servers into a single interface, reducing token overhead and simplifying tool management for LLMs.619Apache 2.0