Build on GridWonk

The interconnection review that runs in the console is the same one your systems can call: find what a utility requires, screen a packet against it, and read the findings back, from your own code or your own AI tools.

Full API, MCP, CLI, and webhook documentation is available to approved accounts.

Request Access Read the docs

Four Ways In

Pick the surface that fits how you work. They all speak to the same platform and the same review.

API

Create projects, upload packet documents, run reviews, and retrieve findings and reports over HTTPS with JSON responses and typed error contracts.

MCP server

Connect Claude, or any MCP-capable assistant, to the platform's tools: match utilities, query published requirements, check job status, and run reviews from a conversation.

CLI

The same workflows from a terminal or a script: upload, review, and export without writing an integration first.

Webhooks

Subscribe to job and document events and get notified when work completes, instead of polling.

Start With a Utility

Most integrations begin the same way: resolve the utility you are working with to its canonical record, then everything else (requirements, reviews, findings) hangs off it.

curl -X POST https://gridwonk.com/api/v1/utilities/match \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Duke Energy Carolinas", "state": "NC"}'

Authentication uses API keys created in the console, or an OAuth client-credentials exchange for partner integrations. Keys are scoped to your organization and can be rate-limited, restricted by endpoint, and revoked at any time.

What You Can Build

Screen a packet automatically when it lands in your intake system, and route the findings to the right reviewer.
Keep your project tracker in step with review status through webhook events.
Let your team's AI assistant answer 'what does this utility require?' with the platform's own requirement data.

Data Security & Privacy

The same rules as the console, on every surface.

Data isolation

Each organization's data is logically isolated. Access to another organization's data requires explicit, revocable authorization.

No training on your data

Your documents, project data, and review results are not used to train AI models.

Transparent, reviewable results

Findings cite the applicable utility requirement, are advisory, and remain subject to human review.

Get an API Key

Access is invite-based today. Tell us what you are building and which utilities you work with.

Request Access

Already have an account? Log in to read the docs.