grid-screen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Optional Gemini API key for LLM-synthesized engineering memo narrative (default model: gemini-2.5-flash). | |
| OPENAI_API_KEY | No | Optional OpenAI API key for LLM-synthesized engineering memo narrative (default model: gpt-4o-mini). | |
| OPENAI_BASE_URL | No | Optional base URL to use a local Ollama/vLLM compatible endpoint with the OpenAI provider. | |
| GRID_AGENT_MODEL | No | Override the default LLM model name for memo synthesis. | |
| ANTHROPIC_API_KEY | No | Optional Anthropic API key for LLM-synthesized engineering memo narrative (default model: claude-sonnet-4-20250514). | |
| GRID_AGENT_AIRGAPPED | No | Set to `1` to enable Air-Gapped Utility Mode, blocking all outbound cloud LLM HTTP calls even when API keys exist in the environment (only local loopback endpoints or deterministic memos are permitted). | |
| GRID_AGENT_API_TOKEN | No | Remote Bearer token enforced via constant-time MCPAuthMiddleware when using `sse` or `streamable-http` transports. | |
| GRID_AGENT_MCP_SCOPE | No | Dynamically restricts exposed MCP tools. Set to `tier1_only` or `readonly` to omit child-process Tier-2 AC and batch sweep tools from untrusted agent registries; `full` exposes all tools. | |
| GRID_AGENT_MAX_DSS_WORKERS | No | Maximum number of concurrent isolated OpenDSS child-process workers (BoundedSemaphore concurrency limit). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_networksA | 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. |
| inspect_connection_pointA | 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. |
| classify_screening_regimeB | 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. |
| search_toolsB | Search available MCP screening tools by keyword, returning cost tier and scope metadata. |
| run_tier1_screenA | 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 |
| run_tier2_ac_studyA | 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: |
| propose_mitigationsC | Synthesize OpenDSS-verified Static Operating Envelopes (5kW/3kW), snapshot-bounded DOEs, or TX system-strength options. Note: The Dynamic Operating Envelope ( |
| screen_connection_applicationC | Execute end-to-end progressive-fidelity triage with Supervisory Sanity Gate, By default, |
| sweep_connection_capacitiesB | 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 ( |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Supported Grid Networks | Complete catalog of 415 V LV feeders, 11-20 kV MV benchmarks, and NEM 132-500 kV substations. |
| Interconnection Queue Telemetry | Live backlog deduplication statistics, fast-track counts, and recent SHA-256 audit entries. |
TDQS
Scored across 9 tools
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.
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.
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.
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.