edgegate-mcp

# edgegate-mcp

MCP server for [EdgeGate](https://edgegate.frozo.ai) — set up edge-AI regression gates on Snapdragon devices directly from Claude Code, Cursor, or Claude Desktop.

## What does it do?

EdgeGate runs AI model regression tests on real Snapdragon hardware via Qualcomm AI Hub, then produces signed evidence bundles you can attach to CI gates. This npm package exposes EdgeGate's REST API as 58 MCP tools, plus bundled skills, so you can drive the whole flow from a prompt:

```
> Use the edgegate MCP to set up a CI gate for my MobileNet ONNX model.
> Gates: inference_time_ms ≤ 10, peak_memory_mb ≤ 150.
> Devices: Galaxy S24, Galaxy S23.
```

## Install

```bash
# 1. Generate an API key in the EdgeGate dashboard
# https://edgegate.frozo.ai/workspace/<id>/settings#api-keys

# 2. Run the installer (writes config for Claude Code / Cursor / Desktop)
npx edgegate-mcp-install
```

Restart your MCP client. Done.

## Manual config

If you'd rather edit config files yourself, the server is a standard stdio MCP. Add this to your client's config:

### Claude Code (`~/.claude.json`)

```json
{
  "mcpServers": {
    "edgegate": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "edgegate-mcp"],
      "env": {
        "EDGEGATE_API_KEY": "egk_live_...",
        "EDGEGATE_API_URL": "https://edgegateapi.frozo.ai"
      }
    }
  }
}
```

### Cursor (`~/.cursor/mcp.json`)

Same shape as Claude Code without the `type` field.

### Claude Desktop (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS)

Same shape as Cursor.

## Tools

See [docs/tools.md](./docs/tools.md) for input schemas and examples.

<!-- BEGIN GENERATED TOOL TABLE -->

EdgeGate exposes **58 MCP tools**. This table is generated from `src/server.ts` — run `npm run docs:tools` after adding a tool.

| Tool | Purpose |
|---|---|
| `edgegate_setup_workspace` | Confirm or list EdgeGate workspaces visible to the API key. Run this first in a fresh conversation to lock in which workspace_id the other tools should use. |
| `edgegate_create_pipeline` | Create a new EdgeGate regression pipeline. Define which model(s), which device(s), and which gates (e.g. inference_time_ms ≤ 10) the pipeline will enforce. For LLMs: set llm_compile_source on a model instead of artifact_id. EdgeGate will compile + link via AI Hub on first run; subsequent runs reuse the cached composite. ttft_ms + tps gates work; both are derived from per-component profile (prompt-role inference_time → TTFT; 1000/token-role inference_time → TPS). Each LLM gate run = 3 AI Hub profile jobs (one per component) ≈ 3× CV cost. |
| `edgegate_run_gate` | Trigger an EdgeGate run against a pipeline. Returns a run_id you can poll with edgegate_check_status. |
| `edgegate_check_status` | Get the current status of an EdgeGate run, including per-device metrics and which gates passed or failed. |
| `edgegate_get_report` | List recent EdgeGate runs in a workspace with status, duration, and trigger. |
| `edgegate_get_audit_report` | Get the signed audit report PDF URL for a completed EdgeGate run. Used for compliance records. |
| `edgegate_setup_github_action` | Generate the GitHub Actions workflow YAML + gh secret commands so every PR runs EdgeGate as a CI gate. |
| `edgegate_compare_runs` | Diff two EdgeGate runs in the same pipeline — metrics delta, gate flips (✓→✗ regressions and ✗→✓ recoveries), per-device breakdown, and an overall verdict (REGRESSION / IMPROVEMENT / NEUTRAL / NO BASELINE). When baseline_run_id is omitted, auto-selects the most recent PASSED run from the same pipeline as the baseline. |
| `edgegate_export_run_report` | Download a human-readable markdown report for an EdgeGate run and save it to disk. Returns the absolute file path plus a preview of the first 30 lines. Optionally includes a run-vs-baseline diff section (include_diff=true). |
| `edgegate_import_huggingface_model` | Import a public Hugging Face model that contains a pre-built ONNX file. EdgeGate downloads the file and registers it as an Artifact. Returns the artifact_id you can pass directly to edgegate_create_pipeline. Polls until the import completes by default (poll_for_completion=true); set to false to return immediately with the job id. |
| `edgegate_predict_npu_coverage` | Predict which ONNX ops will run on the Qualcomm Hexagon NPU vs fall back to CPU, BEFORE spending any AI Hub credits. Returns a compute-weighted NPU coverage % (the latency-honest number), op-count coverage, risk band, per-op CPU fallbacks, and fix recommendations. Heuristic — the real device run remains authoritative. |
| `edgegate_list_promptpacks` | List all promptpacks in an EdgeGate workspace. Returns a markdown table with promptpack_id, version, case count, published status, and creation date. Use include_unpublished=false to hide draft packs. |
| `edgegate_create_promptpack` | Create a new promptpack in an EdgeGate workspace. A promptpack defines the test cases (prompts, expected outputs, per-case overrides) that regression pipelines evaluate. Requires admin role on the workspace. Packs are immutable after creation — bump the version to update. |
| `edgegate_publish_promptpack` | Publish a promptpack version in an EdgeGate workspace so it can be referenced in pipelines. Newly created packs start as unpublished — call this after edgegate_create_promptpack to complete the create → publish → use lifecycle. Requires admin role on the workspace. The operation is idempotent. |
| `edgegate_connect_huggingface` | Store a personal HuggingFace access token for this workspace so the import flow can read private / gated / Qualcomm-org repos (most qualcomm/*, Intel/*, and many Xenova/* repos 401 the anonymous endpoint). The token is validated against HF whoami before encryption and is never echoed in plaintext. If an integration already exists this tool rotates the token. Requires admin role. |
| `edgegate_get_huggingface_integration` | Show whether a personal HuggingFace token is connected to this workspace (and whether it is currently active or disabled). Does not return the token itself. |
| `edgegate_disconnect_huggingface` | Permanently delete the workspace's HuggingFace integration. Future HF imports fall back to anonymous access. Requires owner role. |
| `edgegate_connect_qaihub` | Store a Qualcomm AI Hub API token for this workspace so EdgeGate can submit compile + profile jobs on real Snapdragon devices. The token is encrypted at rest and is never returned in plaintext after the initial connect. If an integration already exists this tool transparently rotates the token. Requires admin role. |
| `edgegate_get_qaihub_integration` | Show whether a Qualcomm AI Hub token is connected to this workspace and whether it is currently active. Does not return the token itself. |
| `edgegate_disconnect_qaihub` | Permanently delete the workspace's Qualcomm AI Hub integration. Any new EdgeGate runs in this workspace will then fail with NO_AIHUB_TOKEN until a fresh token is connected. Requires owner role. |
| `edgegate_create_workspace` | Create a new EdgeGate workspace. The caller automatically becomes the owner. Subject to plan-tier workspace limits. After creation, connect Qualcomm AI Hub and define pipelines as usual. |
| `edgegate_list_api_keys` | List all API keys in this workspace (id, name, prefix...suffix, status, last_used). Plaintext is never returned. Requires owner role. |
| `edgegate_create_api_key` | Create a new API key for this workspace. The plaintext token is returned EXACTLY ONCE in the response — copy it to your CI secrets or local env immediately. Requires Pro tier or above. Requires owner role. |
| `edgegate_revoke_api_key` | Revoke an API key by id. The key is immediately rejected for all subsequent requests; the row is preserved (with revoked_at set) so the audit trail survives. Destructive. Requires owner role. |
| `edgegate_list_members` | List all members of this workspace with their email + role. Requires at least viewer role. |
| `edgegate_list_devices` | List every Qualcomm AI Hub device EdgeGate can target (Snapdragon phones, QRD/CRD reference platforms, IoT Dragonwing, automotive, XR). Returns a markdown table grouped by category. Use the `id` column verbatim when building a `create_pipeline` device matrix. No workspace_id needed — the catalog is global. |
| `edgegate_list_device_targets` | List the customer's OWN connected devices (Jetson, Snapdragon hosts, gateways) with live/offline status computed from each device's heartbeat (30s beat, 90s window). This is the workspace fleet connected via `edgegate-runner agent` — NOT the global AI Hub catalog (use edgegate_list_devices for that). If empty, the response includes copy-paste connect instructions for the customer. |
| `edgegate_run_device_benchmark` | Dispatch an ONNX benchmark to one of the customer's connected devices (Jetson, Snapdragon host, gateway) by name/id. The on-device agent picks it up within ~30s and reports latency/memory results. Multi-silicon: works for any vendor the customer has connected. Requires admin role. |
| `edgegate_invite_member` | Add an existing EdgeGate user to this workspace by email at the given role (owner / admin / viewer). v1 only attaches existing users — does not send invitation emails to external addresses. Requires admin role; only owners can add other owners. |
| `edgegate_change_member_role` | Change a member's role in this workspace. Cannot downgrade the last owner — promote another member to owner first. Requires owner role. |
| `edgegate_remove_member` | Remove a member from this workspace. The user loses access immediately; their pipelines and runs are preserved. Cannot remove the last owner. Destructive. Requires owner role. |
| `edgegate_setup_byo_storage` | Enterprise only. Zero-friction BYO storage setup — creates a pending grant with EdgeGate (returns the External ID) and returns the exact AWS CLI commands the agent should run to create the IAM role in the customer's AWS account. Pair with edgega