PETE MCP Gateway
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., "@PETE MCP Gatewayshow consolidated reports across all projects"
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.
PETE MCP Gateway
One remote MCP endpoint (https://mcp.by-pete.com/mcp, Streamable HTTP) that
gives every AI client — Claude, Claude Code, ChatGPT, Gemini CLI, Grok/xAI,
Pete Qwen — the same policy-checked business tools, shared cross-client
memory, durable jobs, and consolidated reporting across the copackers /
bypete / offduty projects plus Bunting and n0v8v operations.
Built to docs/SPEC.md. Status: deployment-sequence step 2 complete (isolated
gateway, auth, policy, memory, jobs, reports, connector adapters, tests);
steps 3–6 are host + credential work (docs/DEPLOY.md).
Layout
Path | What |
| MCP server (FastMCP, stateless Streamable HTTP) + bearer auth ASGI wrapper, |
| project × actor × action grants, daily budgets, cross-client effect keys, audit log |
| shared memory: fact/decision/suggestion, provenance, optimistic versioning |
| durable queue (SKIP LOCKED + leases, bounded retries), registered job types only, RULE_4 verification-or-unverified |
| adapter framework; declarative REST connectors in |
| operator CLI: create-client / grant / revoke / list |
| additive |
| SPEC, CONNECTORS walkthrough, CLIENTS hookup guide, DEPLOY |
Related MCP server: mcp-nexus
Tools
whoami, system_status, connections_status, connector_call,
memory_search, memory_record, memory_supersede, jobs_submit,
jobs_get, jobs_cancel, reports_get.
Adding a REST connector = one entry in gateway/registry.yaml (env var names
only — no secret value ever appears in this repo, per SECURITY_BOUNDARIES).
Quick start
python -m venv .venv && .venv/bin/pip install -r requirements.txt
cp .env.example .env # fill server-side only
.venv/bin/python -m pytest tests/ -q
.venv/bin/python -m gateway.servern0v8v LLC | GP3 methodology
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
Give your business its own AI agent and run it from any MCP client.
Give AI agents identity, scoped access, trusted context, and verifiable actions through MCP.
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceA production-ready MCP gateway and control plane that provides credential vault, policy engine, audit logging, and managed runtime for routing tool calls between AI agents and downstream MCP servers.58-
- AlicenseAqualityAmaintenanceEnables AI harnesses to connect to a single MCP endpoint that routes to multiple downstream MCP servers, discovering and executing capabilities on demand while keeping tool schemas out of context.466 npmApache 2.0
- AlicenseAqualityBmaintenanceAziel Runtime is a node-meshed MCP software orchestration suite for digital forensics, auditing, provenance, research, intelligence-support, and secure agent workflows, with a single gated execution path, compartmentalized engines, verifiable receipts, temporal integrity, and explicit capability refusal. It is not merely an API aggregator or generic tool router.10362Apache 2.0
- AlicenseBqualityCmaintenanceProvides AI agents with durable, searchable project memory, session notes, skills, and bounded context packs over MCP while leaving orchestration to the client.15MIT