morpheus

A set of automatic instructions for an AI assistant working in the Morpheus Lumerin Node code repository, a project for running Morpheus network nodes.

In plain words
What is it for?
Use it when answering Morpheus questions or writing Morpheus code. It tells the assistant which local documentation and reference files to check and which similar services not to confuse.
Why use it?
It reduces mistakes caused by relying on general information that may not match this repository, especially when identifying documentation, APIs, networks, and contract addresses.

Cursor rule for Cursor

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 rules/morpheusais/morpheus-lumerin-node/morpheus
Clone the repo
git clone --depth 1 https://github.com/MorpheusAIs/Morpheus-Lumerin-Node

Made for: Cursor.

Per session 1,081 This file is loaded in full into every session.
When invoked 1,081 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 $0.01081 $0.01081
Opus 5 $0.00541 $0.00541
Sonnet 5 $0.00216 $0.00216
Haiku 4.5 $0.00108 $0.00108

Measured yesterday against content hash 1e21a7bb16d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

morpheus 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 yesterday.

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.

.cursor/rules/morpheus.mdc · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morpheus Lumerin Node — agent rules

This repository has nuance that generic web knowledge gets wrong. Before answering any Morpheus question or writing any Morpheus code, consult the canonical /docs site and the AGENTS.md at the repo root.

Canonical sources

Anti-hallucination rules

  1. Never confuse the proxy-router HTTP API (this repo) with the hosted Morpheus Inference API. The proxy-router API is documented at proxy-router/docs/swagger.yaml. The hosted Morpheus Inference API at apidocs.mor.org (https://api.mor.org/api/v1) is a separate product for users who don't run a node — see docs/inference-api/overview.mdx.
  2. Never invent contract addresses, chain IDs, or token addresses. Use docs/get-started/networks-and-tokens.mdx (BASE Mainnet 8453, Sepolia 84532).
  3. Never invent live values (active model count, bid prices, latency). Link to https://active.mor.org.
  4. Never claim "Morpheus runs the inference." Independent providers run inference; Morpheus is a marketplace coordinated by the Diamond contract on BASE.
  5. Disambiguate the local tinyllama demo from real Morpheus models. Cite docs/ai/local-vs-blockchain-models.mdx.
  6. Opening a session escrows MOR; it does not spend MOR. Unused MOR returns on close. Cite docs/ai/session-states-open-close-recover.mdx.
  7. There is no recover RPC. Closing the session is the recovery path.
  8. For TEE questions, separate Phase 1 (consumer → P-Node) from Phase 2 (P-Node → backend). A v6+ consumer transparently benefits from a v7+ provider's Phase 2 with no client-side upgrade.
  9. The proxy-router :8082 admin/API port must not be exposed publicly. Only :3333 is public, and only on providers.
  10. MorpheusUI mnemonic recovery only works for tier-1 (index 0) addresses. For derived addresses, recommend importing the private key directly.

Read the full file on GitHub · 54 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. yesterday First seen · 54 lines · 1,081 tokens per session scan A 1e21a7bb16d0

Subscribe to this mod's changes

morpheus is a cursor rule published in the GitHub repository MorpheusAIs/Morpheus-Lumerin-Node (21 stars, last pushed 6d ago), licensed MIT. It adds 1,081 tokens to every session, about $0.0054 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 2026-08-30.