
Edgegate Mcp
io.github.frozo-aiPublished by GitHub account frozo-aiv0.19.0Updated Oct 24, 2026
Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.
Overview
MCP server for EdgeGate that lets an assistant set up and run AI model regression gates on real Snapdragon and Jetson hardware, with signed evidence for CI.
- What you can do
- Create and manage workspaces, members, roles and API keys
- Define regression pipelines with device matrices and metric gates, then trigger runs, poll status and compare runs against a baseline
- Import Hugging Face ONNX models, predict NPU coverage, and compile LLMs via Qualcomm AI Hub
- Manage behavioral eval sets, promptpacks, reference captures and behavioral-gate runs
- Fetch signed audit and compliance reports, export run reports, and generate GitHub Actions CI setup
- Connect Qualcomm AI Hub, Hugging Face and BYO S3 storage integrations, and dispatch benchmarks to your own connected devices
- When to use it
- Use it when you want an assistant to wire up edge-AI regression testing end to end: pick devices, set latency or memory gates, run them on real hardware, and attach signed evidence to CI or compliance records.
- Requirements
- Local stdio process installed from the npm package edgegate-mcp (Node.js with npx). Requires an EdgeGate account and the EDGEGATE_API_KEY environment variable; EDGEGATE_API_URL optionally overrides the hosted API for self-hosted deployments. Runs also need a Qualcomm AI Hub token connected to the workspace, and network access.
Installation
In SourceWeft
- Open Edgegate Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
edgegate-mcp
MCP server for EdgeGate — 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 61 MCP tools, plus bundled skills, so you can drive the whole flow from a prompt:
Install
Restart your MCP client. Done.
Use it on the web (claude.ai, ChatGPT)
No install and no API key. Add the hosted endpoint as a custom connector and approve it in your browser:
- Claude — Settings → Connectors → Add custom connector.
- ChatGPT — Settings → Apps & Connectors → enable Developer mode, then create a connector with OAuth authentication.
You sign in to EdgeGate and approve once; disconnect any time under Settings → Connected AI apps in the dashboard. The hosted endpoint has no access to your filesystem, so edgegate_export_run_report returns the report inline instead of writing a file.
Any client that speaks Streamable HTTP can also use it with an API key as a bearer token:
Self-hosting: handleMcpRequest from edgegate-mcp/http is a Web-standard (Request) => Response handler you can mount on any fetch runtime.
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)
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 for input schemas and examples.
EdgeGate exposes 61 MCP tools. This table is generated from src/server.ts — run npm run docs:tools after adding a tool.
Skills
Slash commands you can invoke directly:
/edgegate-init— full onboarding flow (zero → CI gate)/edgegate-gate— trigger a run on an existing pipeline/edgegate-status— check a run's status + metrics/edgegate-audit— fetch the evidence bundle for a run/edgegate-compare— diff two runs (auto-baseline) with REGRESSION/IMPROVEMENT/NEUTRAL verdict/edgegate-export— save a run report as a markdown file (for PR comments, Slack, compliance)/edgegate-import— import a Hugging Face ONNX model (anonymous, or workspace-token for private / gated / qualcomm-org repos)/edgegate-connect-huggingface— attach a personal HuggingFace token to the workspace so the import flow can read private / gated / qualcomm-org repos/edgegate-connect-qaihub— connect a Qualcomm AI Hub token so runs can actually compile and profile on Snapdragon devices/edgegate-workspace-setup— bootstrap a brand-new workspace end-to-end (create → connect AI Hub → API key → invite teammates)/edgegate-members— list / invite / change role / remove workspace members/edgegate-promptpacks— list existing promptpacks or create a new one with generated test cases/edgegate-byo-storage— Enterprise BYO storage onboarding (register grant → paste External ID → verify probe → first artifact → first run → audit log)
License
MIT — see LICENSE.
Source: README.md at commit e47608a
Tools
0Version history
1- v0.19.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts