Listed from the MCP registry; nobody on Odel publishes it.
Is this yours? Claim itRent GPUs, launch spot instances and run serverless inference on the Xcelsior marketplace.
One address for any MCP client. You sign in at xcelsior.ca once, after adding it.
At most: moves money, runs code or commands, deletes data, or sends messages for you.
Odel charges nothing per call. The publisher may charge for its own service.
| Access to | Read | Change |
|---|---|---|
| Artifacts | ||
| Billing | ||
| Email address | ||
| Events | ||
| Gpu | ||
| Inference | ||
| Instances | ||
| Marketplace | ||
| Profile | ||
| Providers | ||
| Reputation | ||
| Ssh | ||
| Volumes |
From the sign-in at xcelsior.ca, as the endpoint publishes it. You approve it there.
Odel could not list its tools without signing in.
Launch it, connect to it, spend on it and tear it down — through scoped MCP tools, without ever opening a browser. Every host admission-gated before it takes work.
graph TB
subgraph clients["Clients"]
dashboard["Dashboard · Next.js"]
sdk["TypeScript SDK"]
cli["CLI"]
end
subgraph platform["Xcelsior Platform"]
api["FastAPI Gateway · public API + dashboard"]
scheduler["Scheduler · Job matching & admission"]
db[("PostgreSQL 16 + SQLite auxiliaries")]
billing["Billing · metering · holds · payouts"]
reputation["Reputation · 6-tier trust scoring"]
end
subgraph hosts["GPU Host Network"]
mesh["Headscale Mesh · Private Overlay"]
worker1["Worker Agent · RTX 4090"]
worker2["Worker Agent · A100 80 GB"]
worker3["Worker Agent · H100 80 GB"]
end
dashboard & sdk & cli -->|HTTPS| api
api --> scheduler
api --> db
api --> billing
api --> reputation
scheduler -->|SSH over mesh| mesh
mesh --- worker1 & worker2 & worker3
| Global supply | Capacity from independent hosts worldwide, ranked on price, availability, hardware, and host reputation. |
| 4-Layer Security | Version gating → least-privilege Docker → egress firewall → gVisor / Kata sandbox. |
| Agent-Native Surface | MCP tools with per-tool scopes — launch, connect, spend, snapshot, terminate. No dashboard step in any of it. |
| Metered Billing | Per-second metering against wallet holds that expire; Stripe, PayPal, and Wise payout rails; spending widened only through an approvable plan. |
| Reputation Engine | Multi-factor scoring with 7-day grace decay. Bronze → Silver → Gold → Platinum → Diamond tiers. |
| Private Mesh | Headscale overlay network — GPU workers never exposed to the public internet. |
| Admission Gating | Hosts must pass version checks + GPU fingerprinting before receiving any work. |
| Spot Instances | Interruptible GPUs at published spot rates (no bidding). Capacity-based preemption when on-demand needs capacity. |
Spot workloads use pricing_mode: "spot" — not an auction. Customers accept the published spot rate at launch; the rate is locked for billing when the job is assigned. Preemption is capacity-driven (on-demand contention or host drain), not bid-based.
# Launch an interruptible spot instance
curl -X POST https://xcelsior.ca/instance \
-H "Authorization: Bearer $XCELSIOR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"name": "embed-batch", "vram_needed_gb": 8, "pricing_mode": "spot", "gpu_model": "RTX 4090"}'
| On-Demand | Spot | |
|---|---|---|
| Availability | Guaranteed while funded | Best-effort; may queue |
| Price | Fixed catalog rate | Published spot rate (typically 40–60% below on-demand) |
| Preemption | Never | Yes — when higher-priority work needs GPUs |
| Billing | Metered at on-demand rate | Metered at spot_rate_cad locked at allocation |
Provider controls: spot_enabled, spot_gpu_slots, spot_min_cents per host. Kill switch: XCELSIOR_SPOT_ENABLED=false disables new spot launches (503). The on-call runbook and the staging/production rollout plan are internal and not in this repository.
Breaking change:
max_bidand spot bidding are removed. Usepricing_mode=spotinstead. See CHANGELOG.md.
git clone https://github.com/aabiro/xcelsior.git && cd xcelsior
uv sync && cp .env.example .env
# API
uvicorn api:app --reload --port 8000
# Worker (separate terminal)
XCELSIOR_HOST_ID=my-gpu XCELSIOR_SCHEDULER_URL=http://localhost:8000 python worker_agent.py
# Submit a job
python cli.py run my-model 8.0
Dashboard →
http://localhost:8000/dashboardHealth →http://localhost:8000/healthzWorker Auth → hosted/prod workers can use eitherXCELSIOR_API_TOKENorXCELSIOR_OAUTH_CLIENT_ID+XCELSIOR_OAUTH_CLIENT_SECRET. If both are set, the worker prefers OAuth.
sequenceDiagram
participant H as GPU Host
participant A as API Gateway
participant S as Security Engine
H->>A: PUT /host (gpu_model, vram, province)
A-->>H: status = pending, admitted = false
H->>A: POST /agent/versions (driver, runc, ctk, docker)
A->>S: admit_node()
S->>S: check_node_versions()
S->>S: recommend_runtime()
S-->>A: admitted = true | rejection reasons
alt Admitted
A-->>H: status = active → enters allocation pool
loop Every 5s
H->>A: POST /agent/telemetry
end
else Rejected
A-->>H: status = pending, reasons logged
end
Minimum versions — runc ≥ 1.1.14 · nvidia-ctk ≥ 1.17.8 · Docker ≥ 24.0 · Driver ≥ 535
api.py FastAPI gateway (public API, SSE, dashboard)
scheduler.py Job queue, host allocation, spot pricing, preemption
worker_agent.py Pull-based GPU agent, telemetry, Docker execution
security.py 4-layer defense: version gating → gVisor/Kata
billing.py metering, wallet holds, escrow, tax, payout rails
events.py Append-only event store, tamper-evident hashing
reputation.py Multi-factor scoring, Bronze→Diamond tiers
privacy.py data retention, consent, export and erasure
verification.py GPU fingerprint verification, re-verification scheduling
artifacts.py Two-tier B2/R2 storage, policy-based routing
db.py PostgreSQL ↔ SQLite dual-write, LISTEN/NOTIFY
cli.py Full CLI for jobs, hosts, billing, marketplace
ai_assistant.py Hexara AI assistant with tool-calling & onboarding wizards
routes/ Modular API route handlers (agent, instances, admin, etc.)
frontend/ Next.js 15 dashboard + marketing site (xcelsior.ca)
wizard/ Onboarding wizard: rent, provide, or SDK setup (TypeScript)
fern/ API documentation (docs.xcelsior.ca)
scripts/ Deployment, install, and bootstrap scripts
tests/ 1400+ backend tests (pytest) + 17 frontend tests (vitest)
Counts and versions the product quotes in more than one place (the MCP tool
count, the wizard release, package versions) each come from the one file that
decides them; core/release_facts.py names each. After
changing one, run python3 api/scripts/generate_release_facts.py to rewrite the
copies that cannot read it at run time (the frontend's
src/lib/release-facts.json, the registry's api/mcp/server.json);
tests/test_release_facts.py fails until you do.
docker compose up --build -d # API + Frontend + Scheduler
curl https://xcelsior.ca/healthz
sudo cp xcelsior-*.service /etc/systemd/system/
sudo systemctl daemon-reload && sudo systemctl enable --now xcelsior-api xcelsior-health
See .env.example for all 50+ configuration variables.
# Backend (1400+ tests)
uv run pytest tests/ -v # full suite
uv run pytest tests/ -v --cov=. # with coverage
# Frontend (17 tests)
cd frontend && npm test # vitest
# Linting
ruff check . && black --check *.py routes/*.py tests/
CI runs automatically on push to main and on PRs — see CI and Frontend CI.
git checkout -b feat/my-feature)See docs.xcelsior.ca for full API reference and integration guides.
Xcelsior is licensed under the Business Source License 1.1 (BSL 1.1) by Xcelsior Compute Inc. — see LICENSE for the full terms.
xcelsior.ca), as well as internal development, testing, benchmarking, and evaluation. Using Xcelsior's hosted services requires no license under this repository.