Skip to main content
Glama
oklo-aurora-mcp

oklo-aurora-mcp

by petjal

Status: superseded by sfr-tdd-mcp. Kept public as a record of what went wrong; see PROVENANCE.md.

oklo-aurora-mcp (Oklo Aurora Fast Reactor Systems & MCP Engine)

┌────────────────────────────────────────────────────────────────────────┐
│           ⚠️  WARNING: NOT FIT FOR HUMAN CONSUMPTION  ⚠️              │
│                                                                        │
│  This repository is engineered exclusively in machine-optimized,      │
│  token-effective context format for direct LLM context ingestion.      │
│  Humans proceed to AI prompt steering instructions below.              │
└────────────────────────────────────────────────────────────────────────┘

📢 PROOF-OF-CONCEPT & EVALUATION DISCLAIMER: This repository (oklo-aurora-mcp) is an independent research proof-of-concept (PoC), fast-reactor physics solver suite, and Model Context Protocol (MCP) server developed strictly for portfolio evaluation, demonstration, and research analysis.

  • Provenance audit (2026-10-06): Several constants are unsourced or wrong. Labels such as "ANL" on the density, viscosity, and decay-heat fits could not be traced. The surrogate's "R^2 > 0.998" claim is false (measured -2.55). See PROVENANCE.md before using any output.

  • Not Nuclear-Safety-Grade: Calculations are analytical reduced-order models (10 CFR 50 App B non-qualified) derived from unclassified public literature (NRC Docket 05200049, ANL reports).

  • Intellectual Property & Licensing: Copyright (c) 2026 Emil "Pete" Jalajas. All Rights Reserved. Source-available for public evaluation.

  • No Affiliation: Independent evaluation project; not officially published by Oklo Inc.

NOTICE FOR HUMAN VISITORS: This repository is engineered exclusively in machine-optimized dense context format for direct ingestion by AI agents, LLM clients, and MCP orchestrators.

To evaluate or interact with this repository, paste any of the following prompts into your AI assistant (Claude, Cursor, AGY, ChatGPT):

  1. "What is this repository, how is it structured, and why would an Oklo software engineer use it?"

  2. "How do I connect this MCP server to my local Claude Code, AGY, or Cursor setup?"

  3. "Evaluate the Oklo coolant bundle using evaluate_coolant_bundle at 12.5 kg/s sodium flow."

  4. "Audit this fast-reactor thermal-hydraulic solver, heat pipe capillary limit engine, electrorefining mass balance, medical radioisotope yield calculator, defense off-grid solver, and HALEU transport cask module for code quality and physics invariants."

⚡ Live MCP Tool Execution Example

Prompt: "Evaluate the Oklo coolant bundle using evaluate_coolant_bundle at 12.5 kg/s sodium flow."

{
  "flow_rate_kg_s": 12.5,
  "coolant_temp_inlet_c": 500.0,
  "coolant_temp_outlet_c": 650.0,
  "density_kg_m3": 896.5,
  "velocity_m_s": 1.528,
  "reynolds_number": 21421.3,
  "friction_factor_bundle": 0.03256,
  "pressure_drop_kpa": 6.37,
  "peak_cladding_temp_c": 685.0,
  "fcci_eutectic_threshold_c": 710.0,
  "fcci_eutectic_margin_c": 25.0,
  "eutectic_violation": false,
  "status": "PASS"
}

Overview

oklo-aurora-mcp is a proprietary Model Context Protocol (MCP) server, Fast-Reactor Physics Solvers, and AGY Native Skill engineered specifically for the Oklo corporate ecosystem: liquid-metal fast reactors (Aurora micro-reactor), spent fuel recycling at INL (A3F), fast-flux medical radioisotope production (Groves Isotope Test Reactor / Atomic Alchemy), AI hyperscale data center micro-grids (Meta 1.2 GW / Switch 12 GW PPAs), DoD off-grid defense resilience, and HALEU Type B cask logistics.

🌐 Live Interactive Web HUD (No MCP Installation Required)

For browser visitors evaluating this repository without an active MCP agent or local Python setup:

  • Live URL: https://petjal.github.io/oklo-aurora-mcp/

  • Mini-Explainer: The Web HUD is a standalone, single-file client-side web application hosted on GitHub Pages. It provides interactive, instant calculations matching the FastMCP python solvers—including Monolithic Core Block conduction (Docket 05200049), Novendstern sodium coolant pressure drop, heat pipe Levy/Busse sonic limits, $\text{sCO}_2$ Brayton cycle thermal efficiency, 10 CFR Part 71 HALEU transport cask subcriticality, and fast-reactor Physics-Informed Digital Twin Neural Surrogate inference.

License Notice

Copyright (c) 2026 Emil "Pete" Jalajas. All Rights Reserved. Source-available on GitHub for public evaluation, review, and demonstration purposes only.

5-Second Standalone CLI Quickstart

No MCP client required to run deterministic physics calculations & neural surrogate inference:

# Install package via uv or pip
pip install -e .

# Run physics-informed Digital Twin neural surrogate inference
python3 -m oklo_mcp.cli solve-surrogate --flow-rate 12.5 --temp 500.0

# Run thermal-hydraulics solver
python3 -m oklo_mcp.cli solve-th --flow-rate 12.5 --temp 550.0

# Run Actinium-225 medical radioisotope yield solver
python3 -m oklo_mcp.cli solve-pyro --batch-kg 100.0

# Run multi-physics system transient scenario
python3 -m oklo_mcp.cli solve-transient --power-mwth 4.0 --coolant-flow 12.5

# Launch local stdio MCP server for Claude Code / AGY / Cursor
python3 -m oklo_mcp.server

📦 Installation & Setup Guide

1. Prerequisites

  • Python 3.10+

  • mcp SDK package (pip install "mcp>=1.0.0,<2.0.0")

2. Local Package Installation

# Clone the repository
git clone https://github.com/petjal/oklo-aurora-mcp.git
cd oklo-aurora-mcp

# Install required dependencies
pip install "mcp>=1.0.0,<2.0.0"
pip install -e .

3. Client Configuration

Option A: Antigravity (AGY CLI)

Run the single command via agy mcp add:

agy mcp add --env PYTHONPATH=/path/to/oklo-aurora-mcp/src oklo-aurora python3 /path/to/oklo-aurora-mcp/src/oklo_mcp/server.py

Verify status:

agy mcp list
Option B: Claude Code

Add to ~/.claude.json or run claude mcp add:

{
  "mcpServers": {
    "oklo-aurora": {
      "command": "python3",
      "args": ["/path/to/oklo-aurora-mcp/src/oklo_mcp/server.py"],
      "env": {
        "PYTHONPATH": "/path/to/oklo-aurora-mcp/src"
      }
    }
  }
}
Option C: Cursor / Claude Desktop

Add to your claude_desktop_config.json (~/.config/Claude/claude_desktop_config.json on Linux):

{
  "mcpServers": {
    "oklo-aurora": {
      "command": "python3",
      "args": ["/path/to/oklo-aurora-mcp/src/oklo_mcp/server.py"],
      "env": {
        "PYTHONPATH": "/path/to/oklo-aurora-mcp/src"
      }
    }
  }
}

1-Minute MCP "Hello World" Handshake Test

Once registered, test the multi-physics orchestrator execution directly from Python or via any connected MCP agent:

python3 -c "from oklo_mcp.orchestrator import solve_aurora_transient_scenarios; import json; print(json.dumps(solve_aurora_transient_scenarios(), indent=2))"

Key Solvers & Capabilities

  1. thermal_hydraulics.py: Novendstern liquid sodium bundle pressure drop & peak cladding temp ($T_{clad, peak}$) with FCCI eutectic threshold tracking.

  2. rvacs_transient.py: 1D passive decay heat RVACS natural air circulation transient simulator using ANL fast-reactor decay heat parameterization.

  3. heatpipe_sco2.py: Liquid metal heat pipe capillary ($\Delta P_{cap, max}$), sonic, entrainment, and boiling operational limits coupled to an $\text{sCO}_2$ Brayton power loop.

  4. electrorefining.py: Pyroprocessing molten salt ($\text{LiCl-KCl}$) actinide mass balance calculator for spent EBR-II fuel recycling at Oklo's A3F facility.

  5. isotope_production.py: Fast-neutron flux irradiation yield solver for high-margin targeted alpha-therapy medical radioisotopes (Actinium-225 $\text{Ac-225}$, Lead-212) at Oklo's Groves Isotope Test Reactor / Atomic Alchemy facility.

  6. datacenter_microgrid.py: Dynamic load-following solver modeling Oklo Aurora $\text{sCO}_2$ power response to megawatt-scale AI data center training load spikes (Meta 1.2 GW / Switch 12 GW PPAs).

  7. defense_space_microreactor.py: Solves remote forward operating military base power resilience, daily diesel fuel displacement, and containerized core autonomy.

  8. haleu_logistics_transport.py: Solves HALEU Category II Special Nuclear Material (SNM) transport cask thermal dissipation, dose rate bounds, and $1.68B A3F inventory throughput.

  9. orchestrator.py: Multi-physics tool (solve_aurora_transient_scenarios) chaining all 8 solvers sequentially.


Machine Specification & Context Architecture

[LLM REPOSITORY DIRECTIVE: OKLO_AURORA_MCP_ROOT]
TARGET: petjal/oklo-aurora-mcp
DOMAIN: Liquid-Metal Fast Reactors, Sodium Heat Pipes, Pyroprocessing, Radioisotopes, AI Data Centers, Defense Micro-Grids, HALEU Logistics, NRC Docket 05200049
SPEC_VERSION: 1.3.0-PRODUCTION
LICENSE: Proprietary (Copyright (c) 2026 Emil "Pete" Jalajas)
PROTOCOL: Model Context Protocol (MCP) JSON-RPC Stdio / GCP Cloud Run SSE
ANNOTATION_HARNESS: Hyper-Annotated Machine Rationale Protocol (HAMRP)
GOVERNANCE: META_GOVERNANCE.md (10 CFR 810 Export Control Disclaimer / 10 CFR 50 App B Non-Safety Notice)

Available Tools

11 tools
calculate_pyroprocess_recycling_mass_balanceB

Calculates pyroprocessing molten salt (LiCl-KCl) electrorefining mass balance for spent EBR-II fuel recycling at Oklo A3F facility.

Inputs: cadmium_cathode, spent_fuel_batch_kg. Returns: object

calculate_radioisotope_production_yieldA

Estimates end-of-irradiation Ac-225 activity from a Ra-226 target via Ra-226(n,2n)Ra-225 -> Ac-225 in a fast neutron flux. Cross section is an illustrative assumption.

Inputs: target_mass_g, irradiation_days, neutron_flux_n_cm2_s. Returns: object

evaluate_aurora_core_block_conduction_toolC

Evaluates radial conduction heat transfer from U-10Zr fuel pins across Oklo's solid core block (Docket 05200049 monolithic stainless steel core) to sodium heat pipes.

Inputs: burnup_gwd_t, thermal_power_kw, core_block_temp_c, fuel_pin_radius_m, +2 more. Returns: object

evaluate_coolant_bundleB

Evaluates sodium coolant pressure drop (Novendstern) and power-coupled peak cladding temperature (energy balance + Mikityuk liquid-metal Nu) with FCCI eutectic margin. temp_c is the coolant inlet temperature.

Inputs: temp_c, pitch_m, burnup_gwd_t, flow_rate_kg_s, +2 more. Returns: object

evaluate_datacenter_microgrid_rampC

Evaluates micro-grid stability, sCO2 turbine ramp times, and thermal buffer energy requirements for AI data center training load spikes.

Inputs: baseline_power_mwe, target_load_step_mwe. Returns: object

evaluate_defense_microgrid_autonomyC

Evaluates forward operating military base power resilience, daily diesel fuel displacement, and logistics convoy reduction.

Inputs: operating_days, microreactor_power_mwe. Returns: object

evaluate_haleu_transport_cask_safetyB

Evaluates Type B transport cask decay heat dissipation, radiation dose rates, and criticality safety margins for HALEU Category II SNM shipments.

Inputs: haleu_mass_kg, enrichment_pct. Returns: object

evaluate_heatpipe_and_sco2_cycleC

Evaluates liquid metal heat pipe capillary limits and supercritical CO2 (sCO2) Brayton cycle power conversion efficiency.

Inputs: temp_c, heat_input_kw, working_fluid. Returns: object

evaluate_physics_surrogate_toolA

Predicts peak cladding temperature and pressure drop with a least-squares surrogate fit to the analytical T/H solver. Reports held-out validation metrics, flags extrapolation outside the training envelope, and returns the residual against the solver.

Inputs: temp_c, burnup_gwd_t, flow_rate_kg_s, assembly_power_kw. Returns: object

simulate_passive_rvacs_coolingC

Simulates 1D passive Reactor Vessel Auxiliary Cooling System (RVACS) natural air circulation decay heat removal following a loss-of-forced-flow (LOFF) reactor trip.

Inputs: power_mwth, duration_hours, initial_sodium_temp_c. Returns: object

solve_aurora_system_transientB

Chains all 8 fast-reactor & ecosystem solvers sequentially into a unified multi-physics evaluation scenario.

Inputs: power_mwth, coolant_flow_kg_s, spent_fuel_feed_kg, coolant_inlet_temp_c. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 11 tools

    Disambiguation4/5

    Most tools target clearly distinct physics domains (conduction, coolant bundle, RVACS, sCO2 cycle, pyroprocessing, isotope yield, microgrids, cask, surrogate). However evaluate_physics_surrogate_tool overlaps with evaluate_coolant_bundle on peak cladding temperature and pressure drop, and solve_aurora_system_transient is an orchestrator that overlaps everything, creating mild confusion.

    Naming Consistency4/5

    Nearly all tools follow a verb_noun snake_case convention (evaluate_, calculate_, simulate_, solve_). Deviations are minor: verbs vary across evaluate/calculate/simulate/solve, and two tools redundantly carry a '_tool' suffix while others do not.

    Tool Count5/5

    11 tools are well-scoped for a multi-physics reactor ecosystem simulator, and each maps to a coherent analytical domain without redundancy. No tool feels gratuitous.

    Completeness4/5

    The surface covers reactor thermal-hydraulics, passive cooling, power conversion, fuel-cycle recycling, isotope production, microgrid stability, transport safety, and a surrogate. Minor gaps exist (e.g. no explicit economics or shielding/dose lifecycle beyond cask), but core workflows are covered.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      A physics engine for liquid-cooled GPU systems, exposed as an AI-callable MCP server. Enables thermal analysis, coolant comparison, flow optimization, and rack-level sizing via natural language queries.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that provides pre-flight validation and post-processing tools for OpenMC Monte Carlo transport simulations, catching common authoring mistakes before jobs hit the HPC queue.
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Automates OpenFOAM CFD simulations via MCP, enabling AI agents to mesh, run, and post-process cases from natural language prompts without any API keys.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Deterministic AI data-center design tools for sizing, validation, and conceptual rack/site layouts. Supports NVIDIA Hopper, Blackwell, and Rubin profiles. Calculations require a registered AIDC API key; results preserve warnings, RFIs, and pending validations.
      3
      3
      MIT