Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@NetSpectre WebMCP Challenge Edition Get the case briefing and list the top prioritized signals."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
NetSpectre Challenge Edition is a standalone, browser-based demonstration of human-agent collaboration in a defensive cyber investigation. It was created for the 2026 WebMCP Challenge and uses synthetic data exclusively.
This repository is not the NetSpectre commercial desktop product. It does not contain NetSpectre's private investigation engine, production data, customer information, credentials, or proprietary detection logic.
Live demonstration: https://netspectre-webmcp.stuhall44.chatgpt.site
The included fictional case concerns a supplier-impersonation and payment- diversion attempt. A person and their agent share the same visible case state:
The agent obtains a concise case briefing.
It reviews preserved evidence metadata without opening or executing files.
It explains prioritised signals and their evidence links.
It prepares a finding as a draft.
The investigator explicitly reviews and approves the finding.
The agent generates a summary that reflects the recorded human decision.
Related MCP server: @brightbeamai/chap-coordinator-mcp
Tool | Behaviour |
| Reads the active case, risk, confidence, and state. |
| Reads safe metadata for synthetic evidence. |
| Reads explainable signals above an optional confidence threshold. |
| Creates a visible draft that still requires human approval. |
| Reads a summary of the current visible review state. |
The app feature-detects document.modelContext.registerTool, so its normal
interface continues to work in browsers without WebMCP support.
Synthetic evidence only.
No live scanning, network requests, shell execution, or arbitrary file access.
Evidence metadata is read-only and no suspicious material is executed.
Agent-created findings remain drafts until a person approves them visibly.
Tool inputs use narrow JSON schemas.
Tool activity is reflected in the visible activity record.
Outputs support rather than replace professional human judgement.
Use Node.js 22.13 or newer.
npm install
npm run devOpen the printed local URL. For WebMCP discovery, use ChatGPT's built-in browser or a supported Chrome build with WebMCP testing enabled.
npm run buildThis standalone WebMCP demonstration was created during the WebMCP Challenge submission period. NetSpectre existed previously as a private Windows-first desktop product; judges should evaluate the work in this repository as the new challenge extension and demonstration.
The MIT licence in this repository applies only to the files contained in this challenge-edition repository. It does not grant rights to the separate NetSpectre commercial desktop application, its private source, data, brands, or other proprietary materials.
This server cannot be deployed
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Task and planning workspace for humans collaborating with AI agents
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Multi-expert decision intelligence with transparent synthesis and auditable workflows.
