Skip to main content
Glama
grid-screen-mcp

grid-screen-mcp

by omari91

Grid Connection Screening Agent (rt-grid-screening-agent)

PyPI CI M8ven Verified License: MIT

A deployable, physics-grounded Agentic Grid Connection Screening Tool spanning the full Australian vertical voltage continuum (415 V LV → 11–20 kV MV → 132–500 kV NEM Transmission).

Built as the operational software implementation of the PhD research framework (Constraint-Decoupled Dominance across the Vertical Grid Continuum), this package exposes a single deterministic physics core across three interfaces:

  1. MCP Server (grid-screen-mcp) — Plug-and-play Model Context Protocol Interconnection Queue Gatekeeper (stdio, streamable-http, sse) for Claude Desktop, Cursor, Antigravity, and autonomous engineering workflows.

  2. FastAPI Service & Operator Compliance Dashboard (grid-screen-api) — Structured JSON (POST /v1/screen), natural-language intake (POST /v1/screen/intake), live Interconnection Queue telemetry (GET /v1/queue), interactive HTML5 Compliance Dashboard (GET /dashboard), and zero-dependency SVG voltage & envelope plots (POST /v1/screen/plot, POST /v1/screen/intake/plot).

  3. CLI Agent (grid-screen) — Instant terminal triage (grid-screen triage and grid-screen ask with --study-type snapshot | time_series and --svg plot.svg).


Core Architecture: "LLM Orchestrates, Physics Solves, Gate Bounds"

Instead of acting as a generic chatbot wrapper, this tool operates as an Interconnection Queue Backlog Gatekeeper in front of real unbalanced 3-phase OpenDSS and N-1 AC contingency solvers:

flowchart TD
    In["Messy Connection Application (JSON, MCP Tool Call, or Free-Text Inquiry)"] --> Intake["Intake Normalizer & Strict Schema Gate (ConnectionApplication)"]
    Intake --> Dedup{"State-Compression Queue Fingerprint Cache"}
    Dedup -- "Duplicate Sweep (<0.1 ms)" --> Out["Auditable ScreeningVerdict + Cryptographic AuditReceipt (SHA-256)"]
    Dedup -- "New Physical State" --> T1["1. inspect_connection_point (NetworkX Z_th, R/X, S_sc, SHA-256)"]
    T1 --> T2["2. classify_screening_regime (3D Master Vertical Grid Matrix)"]
    T2 --> T3["3. run_tier1_screen (<10 ms Season-Stratified dV/dP + N-1 SCR + Pareto Headroom)"]
    T3 -- "fast_clear_eligible = true" --> Gate["5. Supervisory Physics Sanity Gate + Human-in-the-Loop Flag"]
    T3 -- "N-1 SCR < 2.0 (NER S5.2.5 Override)" --> Mit["4b. propose_connection_envelopes (5kW/3kW SOE, Snapshot DOE, or TX System Strength)"]
    T3 -- "flagged_for_tier2 = true" --> T4["4. run_tier2_ac_study (Isolated Subprocess OpenDSS 3-Phase AC / N-1 AC)"]
    T4 -- "Unconstrained Breach" --> Mit
    T4 -- "Compliant" --> Gate
    Mit --> Gate
    Gate --> Out

Related MCP server: EnergyAtIt MCP Server

Who is this for? (User Personas & Friction)

Standard LLM wrappers fail in power-systems engineering because language models guess voltages, confuse voltage-tier physics, or silently skip non-converged AC power flows. This agent was built to solve specific friction points for the humans and systems who actually run the grid.

1. The Connection Engineer (DNSP / TSO)

  • The Persona: A mid-to-senior planning engineer processing grid connection applications (e.g., Ausgrid, UK Power Networks, 50Hertz, Transpower).

  • The Daily Reality: Drowning in connection requests (such as the 67 GW NEM queue). Manual AC power-flow studies take hours or days per application, forcing reliance on static worst-case heuristics.

  • The Friction:

    • "Safe" Bias: Viable projects get rejected or hit with massive upgrade costs because engineers lack time to evaluate conditional operating envelopes.

    • License Risk: Standard AI (like raw ChatGPT) is unusable because a single hallucinated voltage puts an engineer's professional license and grid safety on the line.

  • How this Agent Solves It: "LLM Orchestrates, Physics Solves" guarantees the LLM never guesses. Requests route to deterministic Python/OpenDSS solvers, giving a <10 ms fast-pass for obvious cases, an isolated 3-phase AC study when needed, and a mandatory "requires_human_review" flag for >=132 kV or non-trivial connections.

2. The Industrial Developer / EPC Contractor

  • The Persona: A project developer sizing a hyperscale data centre, BESS, or commercial EV hub.

  • The Daily Reality: Needs to verify connection viability and reinforcement risk before spending millions on formal feasibility studies.

  • The Friction: Submitting 150 MW on a weak 132 kV fringe (SCR < 2.0) or peak-constrained corridor triggers flat rejection without visibility into staged firm capacity, flexible runback, or BESS/SOE mitigations.

  • How this Agent Solves It: Via FastAPI or MCP, developers can rapidly run "what-if" sweeps across connection capacities and immediately inspect verified mitigations (e.g., 5.0 kW / 3.0 kW SOE, snapshot-bounded DOE, or staged firm MW + system-strength remediation).

3. The Autonomous AI Agent (Claude / Cursor / Antigravity)

  • The Persona: An LLM acting as an engineering copilot over MCP.

  • The Friction: LLMs excel at parsing unstructured inquiries and writing clean reports, but they are mathematically blind on unbalanced 3-phase power flow and N-1 contingencies.

  • How this Agent Solves It: Exposes 10 precision-documented MCP tools and 4 off-context @mcp.resource URIs (grid://...). The LLM parses intent, calls run_tier1_screen, run_tier2_ac_study, triage_connection_cluster, or server-side sweep_connection_capacities, receives compact JSON physics outputs (with heavy trajectory arrays parked off-context), and synthesizes a standards-cited engineering memo. The AI provides the interface; the physics engine provides the truth.

4. The Regulatory Auditor

  • The Persona: A regulator (AER, Ofgem, BNetzA) or utility executive auditing why a connection was cleared, capped, or escalated.

  • The Friction: Neural black boxes cannot be defended in regulatory disputes.

  • How this Agent Solves It: Every verdict is bounded by a Supervisory Physics Sanity Gate and stamped with a Cryptographic Audit Receipt (SHA-256) logging feeder model hashes, solver convergence (solver_failures == 0), human-review triggers, and explicit regulatory overrides ("regulatory_override": "NER S5.2.5 System Strength violation").

The Core Value Proposition: Defensible Speed

User Friction

Architectural Solution

Connection Engineer fears AI hallucination

"LLM Orchestrates, Physics Solves" (isolated OpenDSS worker)

Developer needs rapid pre-application sizing

Tier-1 (<10 ms) vs Tier-2 (AC study + envelope synthesis) routing

AI Agent cannot solve AC power flow

MCP tools enforce deterministic calculation

Regulatory Auditor cannot verify black boxes

SHA-256 cryptographic audit receipts & explicit NER S5.2.5 override flags


Engineering Safeguards & Scope Boundaries

  • Preliminary Screening Scope & Regulatory Disclaimer (VDE-AR-N 4110 / NER S5.2.5):

    IMPORTANT NOTICE: This tool is for preliminary screening only. It does not constitute a conformity assessment under VDE-AR-N 4110. Final certification must be performed by an accredited body.

    In Germany, statutory grid connection conformity requires formal unit certification (Einheitenzertifikat) and plant certification (Anlagenzertifikat) conducted by an accredited certification body (e.g., TÜV, DEKRA, VDE Prüf- und Zertifizierungsinstitut, DNV) and final operational permission (Betriebserlaubnis) from the responsible Network Operator (VNB/ÜNB). In Australia, this tool does not replace formal Generator Performance Standards (GPS) negotiation, R1 dynamic testing, or registration with AEMO and the connecting NSP under National Electricity Rules (NER) Chapter 5.

  • Zero-Mutation Subprocess OpenDSS Isolation, Bounded Concurrency & Hard Timeout: opendssdirect.py uses a C-level process singleton and relative .dss redirects. All 415 V unbalanced 3-phase AC studies execute in an isolated child process (grid_screening_agent.physics._dss_runner) guarded by BoundedSemaphore (GRID_AGENT_MAX_DSS_WORKERS), with cwd scoped strictly to the worker, post-Volt-VAr reactive current (I_q) thermal re-measurement, and a hard subprocess.run(..., timeout=solver_timeout_sec) guard. Any worker timeout or non-convergence routes deterministically to ABSTAIN_DATA_OR_SOLVER_FAULT.

  • Zero-Trust MCP & Subprocess Sandboxing:

    • Typed MCP outputSchema, Tool Annotations & Dynamic Scope (GRID_AGENT_MCP_SCOPE): Every tool on grid-screen-mcp publishes both strict Literal JSON-Schema input enums and explicit Pydantic outputSchema definitions (structuredContent) with openWorldHint=false. Setting GRID_AGENT_MCP_SCOPE=tier1_only or readonly dynamically omits child-process Tier-2 AC and batch sweep tools from untrusted agent registries.

    • Off-Context @mcp.resource Trajectory Parking & Native Capacity Sweeps: Heavy interval voltage arrays are pruned from MCP tool payloads by default (include_trajectory=false) and served on-demand via grid://verdicts/{fingerprint}/trajectory and grid://verdicts/{fingerprint}/plot.svg, while sweep_connection_capacities runs N-point sizing sweeps natively in Python without N sequential LLM round-trips.

    • Credential Scrubbing, Privilege Demotion & Child Socket Denial: Host API keys and remote Bearer tokens (GRID_AGENT_API_TOKEN, enforced via constant-time MCPAuthMiddleware on sse/streamable-http) stay strictly in host memory/headers—stripped from child worker environments (build_sanitized_worker_env), while opendss_worker.py drops privileges (UID 10001 gridagent) and _dss_runner.py late-imports opendssdirect and disables socket.socket at startup (install_network_socket_sandbox).

    • Semantic Wash Air-Lock, Resilient Intake Bounce-Back & Instruction Sandwiching: Free-text inquiries are extracted via GridConnectionIntent (intake.py 3-attempt Pydantic cross-field bounce-back loop with deterministic parse_intent_airgapped fallback) and ConnectionApplication, discarding raw untrusted prose before memo synthesis, wrapping context in 128-bit per-call random nonces, and sandwiching immutable directives at the bottom of the prompt.

  • State-Compression Queue Fingerprint Deduplication (<0.1 ms): Developers and AI agents routinely submit duplicate or repeated sizing queries against the same bus, capacity, inverter mode, and season set. InterconnectionQueueTracker computes a canonical SHA-256 queue_fingerprint over the physical inputs and intercepts backlog duplicates in <0.1 ms without re-spawning child OpenDSS workers, while issuing a fresh timestamped AuditReceipt (cache_hit=true) with an identical reproducibility_sha256.

  • Decoupled Constraint Codes & Dual SHA-256 Reproducibility: Every ScreeningVerdict returns typed binding_constraints (NONE, SYSTEM_STRENGTH_SCR_N1, THERMAL_AMPACITY, STEADY_STATE_VOLTAGE, SOLVER_OR_DATA_FAULT) alongside dual cryptographic digests in AuditReceipt: feeder_model_sha256 (raw .dss topology) and reproducibility_sha256 (canonical sorted digest over normalized inputs, feeder hash, runtime versions, and verified physics verdict—identical across runs on different days). Every module and function includes architectural "Why" docstrings explaining the physical and security rationale in-place.

  • Explicit Tier-2 AC Study Scope (snapshot vs time_series):

    • --study-type snapshot (default) checks selected worst-case seasonal peak states (17 synchronized Ausgrid critical peaks on LV; 8 N-0/N-1 seasonal states on MV/TX).

    • --study-type time_series runs the chronological 48-interval (30-min) diurnal Summer peak-solar trajectory plus seasonal peaks (63–65 LV states; 96 MV/TX contingency intervals).

    • Transparency note: Neither synchronous mode runs a full 17,520- or 35,040-interval full-year telemetry simulation; tier2.study_scope explicitly reports the exact state count evaluated on every call.

  • Snapshot-Bounded DOE vs Predictive WLT: In offline connection screening, DOE_SNAPSHOT_ENVELOPE computes a deterministic static ceiling/floor over the evaluated AC states (telemetry_forecast_active=false). Real-time Warning Lead Time (WLT) dispatch requires live SCADA/AMI telemetry streaming (SSID-Kalman forecasting) and is never falsely claimed from static snapshot screening.

  • 3D Master Vertical Grid Matrix Routing:

    Voltage Tier

    Representative Network / Bus

    Typical R/X or X/R

    Governing Physical Driver

    Primary Binding Constraint

    415 V LV (Suburban Radial)

    CSIRO Network R (3110858)

    Segment R/X ≈ 4.04 (Path 0.97)

    Event Magnitude (r = 0.902) for V; Operating State (r = 0.907) for I

    Steady-State Over-Voltage (>1.10 pu, AS/NZS 61000.3.100)

    415 V LV (Compact Urban)

    CSIRO Network H (08 feeder)

    R_th < 0.08 Ω

    Topologically Voltage-Immune (V ≈ 1.05 pu at 6.0x)

    Conductor / Transformer Thermal Ampacity

    11–20 kV MV

    CIGRE_MV_Rudolstadt, Aus_MV_11kV_Suburban

    R/X ≈ 0.85–1.08

    Background Operating State (r = -0.99)

    State-Dependent Voltage & Thermal Margin

    132 kV Sub-TX (Data Centre & Fringe)

    BrokenHill_132kV (S_sc = 290 MVA), EasternCreek_132kV (S_sc = 606 MVA)

    X/R ≈ 4.5–6.5

    Post-Contingency Fault Level (N-1 SCR) & Multi-Party Interaction

    Weak-Grid System Strength (SCR_N1 < 2.0, NER S5.2.5)

    220–500 kV Bulk EHV & Hubs

    SydneyWest_330kV, KempsCreek_330kV, MelbourneWest_220kV, Bayswater_500kV

    X/R ≈ 9.5–14

    Regional Corridor Transfer & Cluster Headroom

    N-1 Thermal Transfer Headroom & Effective SCR Dilution


Quickstart

1. Install (Python >= 3.10)

# From PyPI (CLI + MCP server + FastAPI service)
pip install grid-screen-mcp

# Or from source for development
uv sync --extra dev

(Or with standard pip: python3 -m venv .venv && ./.venv/bin/pip install -e ".[dev]")

Bundled portable fixtures (~160 KB of CSIRO R & H OpenDSS models + synchronized Ausgrid seasonal/diurnal profiles and NEM substation catalogs) run out-of-the-box with zero external data downloads or API keys.

2. Run CLI Triage

# List all supported LV feeders, MV benchmarks, and NEM 132-500 kV substations
grid-screen networks

# Fast-track LV clear (<10 ms Tier-1 short-circuit, skips OpenDSS, requires_human_review=false)
grid-screen triage --network R --kw 3.0 --scale 3.0

# Stressed LV solar + BESS inquiry with diurnal time-series OpenDSS sweep
grid-screen ask "Can we connect 25 kW solar + 15 kW BESS on Network R at 6.0x scale?" --study-type time_series

# Weak-grid 132 kV hyperscale data centre (triggers regulatory_override="NER S5.2.5 System Strength violation")
grid-screen ask "Screen a 150 MW hyperscale data centre at Broken Hill 132 kV"

3. Run FastAPI Service & Operator Compliance Dashboard

grid-screen-api --host 127.0.0.1 --port 8000
  • Open http://127.0.0.1:8000/dashboard in any browser for the zero-dependency Interconnection Queue & Compliance Dashboard (live backlog KPIs, interactive 10-network submission form, inline SVG voltage trajectory, and SHA-256 regulatory audit ledger).

  • Inspect live queue metrics via GET http://127.0.0.1:8000/v1/queue or OpenAPI docs at http://127.0.0.1:8000/docs.

  • Query via curl:

curl -s http://127.0.0.1:8000/v1/screen/intake \
  -H "Content-Type: application/json" \
  -d '{"inquiry": "Connect 15 kW rooftop solar on Network R bus 3110858 at 6x background solar", "study_type": "snapshot"}' | jq .

4. Connect via MCP (Claude Desktop / Cursor / Antigravity)

Zero-install via uvx from PyPI (package grid-screen-mcp):

{
  "mcpServers": {
    "grid-screening-agent": {
      "command": "uvx",
      "args": ["grid-screen-mcp", "--transport", "stdio"],
      "env": { "GRID_AGENT_MCP_SCOPE": "full" }
    }
  }
}

Or point at a local checkout's virtualenv:

{
  "mcpServers": {
    "grid-screening-agent": {
      "command": "/absolute/path/to/rt-grid-screening-agent/.venv/bin/grid-screen-mcp",
      "args": ["--transport", "stdio"]
    }
  }
}

Exposed MCP tools & off-context resources:

  • list_networks — Catalog lookup across LV, MV, and 132–500 kV tiers (including Western Sydney & Melbourne West data centre nodes).

  • search_tools — Deferred keyword discovery across active scope-permitted tools.

  • inspect_connection_point — Exact Z_th, R/X, S_sc, dV/dP, and SHA-256 feeder hash.

  • classify_screening_regime — 3D Master Vertical Grid Matrix routing.

  • run_tier1_screen — Fast <10 ms short-circuit, season-stratified voltage, and Pareto screen (does NOT run full AC power flow).

  • run_tier2_ac_study — Isolated 3-phase OpenDSS (snapshot or time_series) / N-1 AC contingency solver with hard timeout, 4-quadrant UPS reactive support, and include_trajectory=false pruning.

  • triage_connection_cluster — Vectorized multi-party interconnection queue triage via pre-fault coherence matrix $\mathbf{\Gamma}$ and cluster-adjusted impedance metric $\mathcal{T}_i(\mathcal{K})$ (detecting effective SCR dilution and co-optimizing queue priority across data centres, BESS, and renewables under German Reifegradverfahren and AEMO rules).

  • propose_mitigations — OpenDSS-verified 5 kW/3 kW SOE, snapshot-bounded DOE, 4-quadrant UPS reactive compensation (+62.2 MW headroom), or TX remediation.

  • screen_connection_application — Complete progressive-fidelity verdict with requires_human_review, regulatory_override, and AuditReceipt.

  • sweep_connection_capacities — Server-side N-point capacity sweep returning compact decision points + first breach capacity.

  • Resources: grid://catalog/networks, grid://queue/stats, grid://verdicts/{fingerprint}/trajectory, and grid://verdicts/{fingerprint}/plot.svg.


Optional LLM Memo Synthesis

All numerical calculations, regime routing, sanity-gate overrides, requires_human_review flags, and ClearanceDecision outcomes are 100% deterministic. Setting an optional provider key synthesizes the engineering_memo narrative strictly from verified tool outputs (with XML prompt-injection fencing and deterministic decision verification):

  • GEMINI_API_KEY (default model: gemini-2.5-flash)

  • ANTHROPIC_API_KEY (default model: claude-sonnet-4-20250514)

  • OPENAI_API_KEY (default model: gpt-4o-mini; supports local Ollama/vLLM via OPENAI_BASE_URL)

  • Override model name with GRID_AGENT_MODEL. Without keys, --provider auto runs cleanly in zero-key deterministic mode.

  • Air-Gapped Utility Mode (GRID_AGENT_AIRGAPPED=1): Blocks all outbound cloud LLM HTTP calls even when API keys exist in the environment (allowing only local loopback 127.0.0.1 / localhost endpoints or pure deterministic memos).


Docker Deployment (<300 MB Multi-Stage Non-Root Image) & Enterprise Cloud Templates

docker compose up --build

(Or standalone: docker build -t grid-screening-agent . && docker run --rm --read-only --tmpfs /tmp -p 8000:8000 grid-screening-agent)

For utility/TSO teams archiving signed AuditReceipt records at scale, zero-core-impact infrastructure-as-code templates (7-year SEC 17a-4 S3 Object Lock WORM + DynamoDB TTL hot ledger → SQS DLQ → TTL-filtered Snappy S3 Parquet Lambda + Glue schema evolution → 10 GB-capped Athena Workgroup + GitHub Actions OIDC CI/CD + CloudWatch/SNS Cutoff Alarms) are provided under deploy/aws/ and .github/workflows/.

Verification Suite & Contributing

Runs 94 automated regression and infrastructure schema-guard tests (1 pandas-gated test skips in the lean core venv) verifying AC solver convergence, multi-party queue cluster triage, post-droop Volt-VAr thermal loading, constraint decoupling, cross-field validation & LLM bounce-back, child-process socket/secret/late-import sandboxing, MCP scope & Bearer auth enforcement, off-context grid:// resource resolution, semantic-wash nonce fencing, air-gapped privacy, queue fingerprint deduplication, Operator Compliance Dashboard rendering, SVG plotting, Glue/Parquet schema evolution, reproducibility digests, and MCP input/output schemas:

pytest -v

Contributions, additional feeder/substation benchmarks, and MCP client integrations are welcome! Please read CONTRIBUTING.md before opening a pull request to ensure zero numerical drift and invariant preservation.

Citation & Academic Research

Technical Note: This is a reproducible research artifact for the ETECOM 2026 paper. It screens the CIGRE MV benchmark and CSIRO LV feeders. It is not a certified conformity tool.

If you use this repository, the underlying OpenDSS models, or the cluster triage engine in academic research, please cite it using CITATION.cff:

@inproceedings{ondieki2026constraint,
  title={Constraint-Decoupled Dominance Across the Vertical Grid Continuum: Physics-Grounded Autonomous Connection Screening},
  author={Ondieki, Clifford},
  booktitle={Proceedings of the IEEE International Conference on Emerging Technologies for Electrical Engineering and Communications (ETECOM 2026)},
  year={2026},
  note={Reproducible research artifact. Screens CIGRE MV benchmark and CSIRO LV feeders. Not a certified conformity tool.}
}

License

Released under the MIT License.

Available Tools

9 tools
classify_screening_regimeB
Read-onlyIdempotent

Apply the 3D Master Vertical Grid Matrix to determine which physical constraint binds first (Voltage, Thermal, or N-1 SCR).

Classifies Constraint-Decoupled Dominance across 415 V LV, 11-20 kV MV, and 132-500 kV Transmission. Does NOT run AC power flow.

Inputs: network_id (required), proposed_capacity_kw (required), asset_type, connection_node. Returns: Constraint-Decoupled Dominance classification from the 3D Master Vertical Grid…

inspect_connection_pointA
Read-onlyIdempotent

Extract deterministic Thevenin impedance (R_th, X_th, Z_th), R/X ratio, fault level S_sc, dV/dP, and SHA-256 hash.

Call this tool FIRST to inspect electrical stiffness at the Point of Common Coupling (PCC). Does NOT run AC power flow.

Inputs: network_id (required), connection_node. Returns: Electrical and topological parameters extracted at the point of common coupling…

list_networksA
Read-onlyIdempotent

List all supported ARENA/CSIRO 415 V LV feeders, 11-20 kV MV benchmarks, and NEM 132-500 kV substations.

Catalog metadata lookup only. Does NOT run short-circuit or AC power-flow calculations.

Inputs: no named parameters. Returns: Typed MCP output schema for `list_networks`.

propose_mitigationsC
Read-onlyIdempotent

Synthesize OpenDSS-verified Static Operating Envelopes (5kW/3kW), snapshot-bounded DOEs, or TX system-strength options.

Note: The Dynamic Operating Envelope (DOE_SNAPSHOT_ENVELOPE) is a static envelope derived from deterministic AC snapshot/diurnal bounds (telemetry_forecast_active=false), NOT a live SSID-Kalman predictive Warning Lead Time (WLT) forecast.

Inputs: network_id (required), proposed_capacity_kw (required), asset_type, study_type, +5 more. Returns: Typed MCP output schema for `propose_mitigations`.

run_tier1_screenA
Read-onlyIdempotent

Calculates fast short-circuit and voltage screening. Returns a pass/fail. Does NOT run full AC power flow.

Executes sub-10ms analytical screening using season-stratified voltage calibration (1.0752 pu), thermal margin, post-contingency N-1 Short Circuit Ratio (NER S5.2.5 SCR >= 2.0), and Pareto joint hosting capacity. Use fast_clear_eligible and flagged_for_tier2 to decide whether to escalate to run_tier2_ac_study.

Inputs: network_id (required), proposed_capacity_kw (required), asset_type, bess_power_kw, +4 more. Returns: Millisecond analytical screening result with season-stratified calibration.

run_tier2_ac_studyA
Read-onlyIdempotent

Run isolated child-process unbalanced 3-phase OpenDSS AC power flow (LV) or exact 2-bus N-0/N-1 AC contingency solve (MV/TX).

Study scope: study_type='snapshot' evaluates selected worst-case seasonal peak states (17 LV / 8 MV-TX states); study_type='time_series' evaluates the chronological 30-min diurnal trajectory + seasonal peaks. Does NOT run a synchronous 17,520/35,040-interval full-year telemetry simulation. Enforces a hard subprocess timeout. By default, include_trajectory=False prunes the raw trajectory array to protect LLM context tokens and returns trajectory_resource_uri (grid://verdicts/{fingerprint}/trajectory) for on-demand inspection.

Inputs: network_id (required), proposed_capacity_kw (required), asset_type, study_type, +8 more. Returns: Unbalanced 3-phase AC OpenDSS simulation result run in an isolated worker proce…

screen_connection_applicationC
Idempotent

Execute end-to-end progressive-fidelity triage with Supervisory Sanity Gate, requires_human_review, regulatory_override, and SHA-256 AuditReceipt.

By default, include_trajectory=False omits raw Tier-2 voltage arrays to save LLM context tokens while preserving the exact reproducibility_sha256 digest and exposing grid://verdicts/{queue_fingerprint}/trajectory & plot.svg.

Inputs: asset_type, network_id, study_type, force_tier2, +8 more. Returns: Complete auditable connection screening verdict.

search_toolsB
Read-onlyIdempotent

Search available MCP screening tools by keyword, returning cost tier and scope metadata.

Inputs: query. Returns: Typed MCP output schema for `search_tools`.

sweep_connection_capacitiesB
Idempotent

Execute a server-side N-point hosting-capacity sweep to locate the exact constraint inflection point.

Shields the LLM context window from N sequential tool round-trips by evaluating candidate capacities natively in Python (1 <= steps <= 20) and returning a compact inflection table.

Inputs: end_kw (required), start_kw (required), network_id (required), steps, +7 more. Returns: Typed MCP output schema for `sweep_connection_capacities` (shielding LLM contex…

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 9 tools

    Disambiguation4/5

    Most tools have clearly distinct roles: catalog lookup, connection-point inspection, regime classification, Tier-1 screening, Tier-2 AC study, mitigation proposal, end-to-end triage, and capacity sweep. There is some overlap between `screen_connection_application` and manually chaining `run_tier1_screen` / `run_tier2_ac_study`, and `search_tools` is a meta-tool that stands apart from the domain workflow, but descriptions make the progressive-fidelity boundaries understandable.

    Naming Consistency5/5

    All tools use snake_case with a clear verb-first pattern such as `list_networks`, `inspect_connection_point`, `classify_screening_regime`, `run_tier1_screen`, and `propose_mitigations`. Tier and domain qualifiers are used consistently enough that the naming remains predictable.

    Tool Count5/5

    Nine tools are well scoped for a grid-screening server, with each covering a distinct stage from catalog discovery through screening, detailed study, mitigation, end-to-end triage, and capacity sweep. The set is neither thin nor bloated.

    Completeness4/5

    The surface covers the core lifecycle: network catalog, PCC inspection, regime classification, fast and detailed screening, mitigation synthesis, end-to-end application screening, and hosting-capacity sweep. Minor gaps remain around explicit artifact/result retrieval or standalone audit/export operations, though the end-to-end tool returns audit receipts and resource URIs.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables conversational power system analysis by connecting Claude AI with EPRI's OpenDSS simulator. Allows distribution planning engineers to perform sophisticated electrical grid studies through natural language instead of complex scripting.
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Connects AI agents to energy infrastructure with 30+ tools for managing sites, assets, dispatch, settlements, compliance, and carbon tracking.
      34
      50 npm
      1
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides deterministic, standards-based calculations for data center critical power infrastructure. Enables site selection, generator sizing, UPS sizing, NFPA 110 compliance, and more via 50+ AI agents and 8 compound chains.
      -
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables multi-agent orchestration of distributed energy resources through MCP tools, including simulation, real-time telemetry, dispatch control, and deterministic safety gatekeeping for grid support and demand response.
      1
      -