# Massed Compute (slim)

> Massed Compute is a US GPU cloud that rents NVIDIA GPU virtual machines by the hour from hardware it owns, with bare metal and clusters by quote. Agents use its REST API or a hosted MCP server.

- Full: https://www.anchorterminal.com/tools/massed-compute.md (~8,900 tokens) · this version ~1,930 tokens · JSON https://www.anchorterminal.com/tools/massed-compute.json · canonical https://www.anchorterminal.com/tools/massed-compute
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

**E · 42.3/100 · rank #896 of 950 · #18 in GPU & serverless compute · not agent-ready · confidence medium**


Assessment: The hosted MCP server and REST API accept OAuth grants or API tokens in read-only and full-access tiers, and all 17 tools carry typed schemas and safety annotations in a public server card. No status page, rate limit figures or API changelog were found, a launch has no idempotency key, and the governing terms could not be read.

## Facts

- Kind: HTTP API · vendor: Massed Compute · category: GPU & serverless compute · legal entity: Massed Compute, Inc. · provenance 68/100
- Endpoint: `https://vm.massedcompute.com/api/v1` (HTTP, Streamable HTTP)
- Auth: OAuth or key · pricing: Pay per use · x402: no · licence: Proprietary service under Massed Compute's Terms & Conditions and End User Licence Agreement. The `massed-compute-mcp` wrapper on GitHub is MIT
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: The hosted MCP server at https://vm.massedcompute.com/api/mcp together with the REST API at https://vm.massedcompute.com/api/v1 (OpenAPI 3.0, 14 operations). Tool definitions were read from the public server card
- MCP server: Hosted, Streamable HTTP, Bearer token or OAuth. 17 tools. `gpu_inventory_list`, `images_list`, `instances_list`, `instances_get`, `instances_launch`, `instances_restart`, `instances_terminate`, `coupon_information`, `coupon_accepted_products`, `account_token_validation`, `account_billing`, `ssh_keys_list`, `ssh_keys_create`, `ssh_keys_delete`, `recipes_list`, `recipes_search`, `recipes_get`. 37 recipes as resources
- Local wrapper: `massed-compute-mcp` 1.1.0 on npm (Node 20 or newer) and PyPI (Python 3.10 or newer), MIT. A stdio proxy that forwards every JSON-RPC message to the hosted endpoint and stores the key in a 0600 file
- Credentials: API tokens in Full access or Read only, shown once, revoked in the console. OAuth grants in the same two tiers, listed under Connected Apps
- Free tier: None found. A first deposit and an auto-recharge threshold of at least $5 are needed before a launch
- GPUs: A30, RTX A5000, RTX A6000, RTX 6000 Ada, L40, L40S, A100, H100, H200, RTX PRO 4500 and 6000 Blackwell, B200 and B300, in 1, 2, 4 or 8 GPU shapes per the pricing page
- Scale to zero: No. VMs bill until terminated, and a stopped VM is billed at the full rate
- Cold start: No measured figure. The site says about 90 seconds in one place and under four minutes in another
- Billing basis: Per minute while the VM exists, debited from a prepaid balance. No bandwidth charge per the pricing page
- Rate limits: A 429 is documented with the advice to wait a minute. No figures found
- Errors: 401 for a bad token, 402 when billing is not set up, 429 for rate limits and `-32003 Forbidden` for a read-only credential calling a write tool. The OpenAPI file documents only 200 and 202
- Regions: `regionName` takes `any`. The older API's examples name us-central-1 in Wichita, Kansas. No region list found
- Team access: Owner, Admin and Member roles with instance groups that limit who sees each VM. Members never see billing
- Status: No status page found
- Prices: A30 24 GB VM $0.35 per GPU-hour; RTX A5000 24 GB VM $0.44 per GPU-hour; RTX A6000 48 GB VM $0.57 per GPU-hour; RTX 6000 Ada 48 GB VM $0.79 per GPU-hour; L40 48 GB VM $0.86 per GPU-hour; RTX PRO 4500 Blackwell 32 GB VM $0.92 per GPU-hour; L40S 48 GB VM $0.97 per GPU-hour; A100 80 GB VM $1.35 per GPU-hour; RTX PRO 6000 Blackwell 96 GB VM $2.19 per GPU-hour; H100 80 GB VM $2.73 per GPU-hour; H200 NVL 141 GB VM $3.62 per GPU-hour; B200 SXM6 VM, 8 GPUs $5.43 per GPU-hour; B300 SXM6 VM, 8 GPUs $6.60 per GPU-hour

- Scores: Reliability 20, Performance pending, Schema & documentation 69, Agent ergonomics 56, Security & auth 61, Payments & pricing 20, Task success pending, Maintenance & community 51, Transparency & trust 61 · negative events -5 · total over the 7 assessed categories
- Why: Reliability, Graded on the hosted lines for the MCP server and the REST API. · Schema & documentation, A public OpenAPI 3.0 file covers the 14 REST operations, and a public server card lists all 17 MCP tools with JSON Schema inputs (25). · Agent ergonomics, 17 tools whose definitions total about 10.5 KB in the server card, and a read-only credential cannot use the six write tools (15 plus 5 of 2… · Security & auth, OAuth with discovery from a 401 challenge, or named API tokens shown once and revoked one at a time. · Payments & pricing, No x402, MPP or L402 in the docs, the OpenAPI files, the server card or the pricing page. · Maintenance & community, The newest release of the MCP wrapper is v1.1.0 of 24 July 2026, 77 days before the check. · Transparency & trust, Closed service.
- Sources: 34, open questions: 11, both in the full twin
- Capabilities: compute.gpu
- JSON: https://www.anchorterminal.com/api/v1/tools/massed-compute.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/massed-compute.svg` or a link to https://www.anchorterminal.com/tools/massed-compute from a page on massedcompute.com or one of its subdomains, or the README of github.com/Massed-Compute/massed-compute-mcp, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Use `https://vm.massedcompute.com/api/v1`. The older docs at api-docs.massedcompute.com describe a separate marketplace API on `api.massedcompute.com` whose keys come from support.
2. Ask the owner for a read-only token unless the task must launch or terminate. Read-only credentials cannot call launch, restart, terminate or SSH key changes.
3. Call `gpu_inventory_list` and `images_list` before `instances_launch`. Product names and image IDs are free values, and SXM-only images do not run on PCIe cards.
4. Expect 402 on launch until the owner has added credit and set a recharge amount and threshold. List instances before retrying a launch.
5. Terminate to end billing. Stopping keeps the full hourly charge, and termination deletes the instance data.

## Connect

```bash
npm install -g massed-compute-mcp
```

```bash
claude mcp add --transport http massed-compute https://vm.massedcompute.com/api/mcp --header "Authorization: Bearer MC_TOKEN"
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/massed-compute

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Nebius AI Cloud | B | 67.2 | compute.gpu | https://www.anchorterminal.com/tools/nebius-ai-cloud.min.md |
| Baseten | B | 66.5 | compute.gpu | https://www.anchorterminal.com/tools/baseten.min.md |
| Hugging Face Inference Endpoints | B | 64.5 | compute.gpu | https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.min.md |
| Modal | B | 63.6 | compute.gpu | https://www.anchorterminal.com/tools/modal.min.md |
| Replicate Deployments | B | 63.6 | compute.gpu | https://www.anchorterminal.com/tools/replicate-deploy.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)