mcpelevator AGENTS.md

Project instructions for mcpelevator, a self-hosted service that turns command-line MCP servers into authenticated HTTP endpoints and includes a web interface.

In plain words
What is it for?
Use them when developing, testing, type-checking, building, or running mcpelevator locally or with Docker.
Why use it?
They give coding agents the commands, architecture, and conventions needed to work on the backend and frontend without guessing.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/pacnpal/mcpelevator/agents-md
Clone the repo
git clone --depth 1 https://github.com/pacnpal/mcpelevator

Made for: Codex, OpenCode.

Per session 1,557 This file is loaded in full into every session.
When invoked 1,557 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01557 $0.01557
Opus 5 $0.00779 $0.00779
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00156 $0.00156

Measured 3d ago against content hash 4426834821e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpelevator AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcpelevator — self-hosted control plane that elevates stdio MCP servers into authenticated HTTP endpoints

One container runs stdio (or already-remote) MCP servers and exposes each as a remote Streamable-HTTP endpoint (/s/<slug>/mcp) with a SvelteKit UI, process supervision, and auth.

Commands

Run backend commands from backend/, frontend commands from frontend/. The Makefile wraps the common ones.

  • Backend dev (autoreload, http://127.0.0.1:8080): cd backend && uv run uvicorn app.main:app --reload --port 8080make dev-backend
  • Frontend dev (HMR, http://localhost:5173, proxies /api and /s to :8080): cd frontend && npm install && npm run devmake dev-frontend
  • Build SPA into frontend/build: cd frontend && npm ci && npm run buildmake build
  • Backend tests: cd backend && uv run pytest -qmake test
  • Frontend tests: cd frontend && npm run test (vitest)
  • Frontend typecheck: cd frontend && npm run check (svelte-check)
  • Refresh the uv lockfile: cd backend && uv lockmake lock
  • Build + run everything in Docker: docker compose up --buildmake docker

Architecture

One FastAPI process serves three surfaces in a single port (backend/app/main.py): /api/* control plane, /s/<slug>/mcp reverse proxy, and the built SPA as a catch-all mount.

  • Desired-state reconciliation. SQLite is the source of truth. A background supervisor task (supervisor/) converges running processes to the desired state (Kubernetes-style), so the system is idempotent and survives restarts.
  • One bridge process per enabled server (bridge/, runners/): each runs its own uvicorn on a loopback port hosting a FastMCP proxy of the stdio command (or an upstream HTTP/SSE URL), fault-isolated with a real PID and logs.
  • Upstream OAuth (auth/oauth_store.py, auth/oauth_flow.py): a remote server can authenticate to its upstream via OAuth instead of static env headers. The interactive authorization-code grant (DCR + PKCE) runs in the control plane (/api/servers/{id}/oauth/authorize → public /api/oauth/callback, anchored on the OAuth state) using the MCP SDK's OAuthClientProvider; tokens land in a 0600 file store (<data_dir>/oauth/<id>.json) shared with the bridge, which reads them and auto-refreshes. Tokens live off the DB, so authenticating never re-hashes the row or bounces the bridge.
  • Runners (runners/): npx, uvx, command, remote (proxy an already-remote MCP URL), and docker (image-packaged servers — opt-in + root-equivalent behind the docker_runner setting). Each runner is a pure Server -> ProcessSpec builder; docker stores the canonical image+container-args+env shape and synthesizes a hardened docker run (the bridge scrubs the child env for docker units so a -e KEY passthrough can't reach the control plane's secrets).
  • Groups (groups/): a SQLite-backed registry maps each group name to "*" or an ordered list of server IDs and serves it at /g/<name>/mcp; all is an ordinary, unreserved group name. GroupHub converges one namespaced FastMCP bundle per group from the running supervisor topology after each reconcile. Auth reuses enforce() with synthetic group:<name> identities, so bearer tokens may be scoped to that group or all; members whose effective auth is stricter than the group are excluded to prevent an auth downgrade.
  • Auth (auth/): two independent layers per request — a Host/Origin allowlist middleware (DNS-rebinding defense) plus pluggable per-server bearer auth on /s and control-plane bearer auth that gates the sensitive /api routers only when enforcement is on (default auto: when the box is exposed off-host); /api/health* and /api/auth/status stay public. See README "Security" for the full model.
  • Catalog (catalog/): backend proxies public MCP directories (official registry, Glama) into reviewable launch specs; the SPA stays same-origin.
  • Frontend (frontend/src/): SvelteKit (Svelte 5) SPA, adapter-static, no SSR — rendered entirely in the browser, served by the backend catch-all.

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 83 lines · 1,557 tokens per session scan A 4426834821e2

Subscribe to this mod's changes

mcpelevator AGENTS.md is an instructions file published in the GitHub repository pacnpal/mcpelevator (5 stars, last pushed 11d ago), licensed MIT. It adds 1,557 tokens to every session, about $0.0078 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.