# Massed Compute

> 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.

- Canonical: https://www.anchorterminal.com/tools/massed-compute
- Markdown: https://www.anchorterminal.com/tools/massed-compute.md (~8,900 tokens)
- Slim: https://www.anchorterminal.com/tools/massed-compute.min.md (~1,930 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/massed-compute.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-10

## Overview

**Grade 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

| Field | Value |
| --- | --- |
| Vendor | Massed Compute (https://massedcompute.com) |
| Kind | HTTP API |
| Category | GPU & serverless compute (https://www.anchorterminal.com/categories/gpu-compute) |
| Transport | HTTP, Streamable HTTP |
| Endpoint | `https://vm.massedcompute.com/api/v1` |
| Auth | OAuth or key · Self-serve. The owner signs up in a browser, verifies an email address and creates a named API token at vm.massedcompute.com/settings/api, choosing Full access or Read only. The token is shown once, travels as a Bearer header and is revoked from the token table. The same token works for the REST API and the MCP server. MCP clients that send no token get a 401 with an OAuth challenge, and the owner signs in and approves full or read-only access. Grants are listed and revoked under Connected Apps. The older marketplace API on `api.massedcompute.com` issues keys only through support. |
| Pricing | Pay per use (Pay per use) · No free tier or trial credit was found. The owner adds a card or pays in crypto, makes a first deposit and sets an auto-recharge threshold of at least $5 before any launch. Running VMs are debited every minute at a published hourly rate. On 9 October 2026 a single A30 was $0.35 an hour, an RTX A6000 $0.57, an L40S $0.97, an A100 80 GB $1.35 and an H100 80 GB $2.73. No bandwidth charge per the pricing page. Bare metal, clusters and the marketplace API are by quote (https://vm.massedcompute.com/pricing). |
| x402 | No · No x402, MPP or L402 in the docs, the two OpenAPI files, the MCP server card or the pricing page. The billing docs describe crypto top-ups made by the account owner, which is not a machine payment protocol (checked 2026-10-09). |
| Licence | Proprietary service under Massed Compute's Terms & Conditions and End User Licence Agreement. The `massed-compute-mcp` wrapper on GitHub is MIT |
| Tools exposed | 17 |
| Packages | npm: `massed-compute-mcp`; pypi: `massed-compute-mcp` |
| MCP registry name | `io.github.Massed-Compute/mcp` |
| Source | https://github.com/Massed-Compute/massed-compute-mcp |
| Docs | https://vm-docs.massedcompute.com |
| llms.txt | https://massedcompute.com/llms.txt |
| Last release | 2026-07-24 |
| GitHub stars | 1 (as of 2026-10-09) |
| 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 |
| Capabilities | compute.gpu |
| Tags | hosted, usage-priced, openapi, mcp, oauth, api-key, read-only-keys, node, python, card-required, crypto-payments, closed-source |
| JSON | https://www.anchorterminal.com/api/v1/tools/massed-compute.json |

## Score breakdown (methodology v0.4, October 2026 research run)

Assessed 2026-10-09 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points.

| Category | Weight | This run | Score (0–100) | Points |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 20 | 20 | 4.0 |
| Performance | 10% | pending | pending | n/a |
| Schema & documentation | 13% | 16.2 | 69 | 11.2 |
| Agent ergonomics | 13% | 16.2 | 56 | 9.1 |
| Security & auth | 14% | 17.5 | 61 | 10.7 |
| Payments & pricing | 10% | 12.5 | 20 | 2.5 |
| Task success | 10% | pending | pending | n/a |
| Maintenance & community | 7% | 8.8 | 51 | 4.5 |
| Transparency & trust (editorial 53, provenance 68) | 7% | 8.8 | 61 | 5.3 |
| Negative events | up to −15 | up to −15 | 8 June 2026. The `instances_list` and `instances_get` MCP tools returned the cleartext VM password although their descriptions said it was redacted. Fixed in `massed-compute-mcp` 1.0.3 and later moved server-side, with rotation advice in the changelog. No GitHub advisory is published. Fixed and documented, so 3 points (https://github.com/Massed-Compute/massed-compute-mcp/blob/main/CHANGELOG.md). 9 October 2026. The product page lists SDKs for Go and a Terraform provider, webhooks and per-project quotas. None appears in the docs, the OpenAPI file or the vendor's public GitHub organisation. 2 points (https://massedcompute.com/products/inventory-api/).  | -5 |
| **Total** | | | | **42.3 → E** |

### Why each score

- Reliability 20: Graded on the hosted lines for the MCP server and the REST API. No status page was found on the site, the docs, the pricing page or the repository (0). No incident history to read (5). The troubleshooting page documents a 429 for request limits with no figures (0). The same page says to wait a minute and retry, and every tool carries an `idempotentHint`, but `instances_launch` has no idempotency key (5 of 15). The on-demand page says 99.999 per cent uptime is guaranteed. No SLA document was found, the End User Licence Agreement promises support only under an order form or SLA, and the Terms & Conditions could not be read (0). The API is `/api/v1`, the server card is version 1.0.0 and nothing is labelled beta (10).
- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.
- Schema & documentation 69: 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). massedcompute.com has an `llms.txt` that indexes marketing pages, and the vendor publishes an agent catalogue, the server card and four Markdown skills files. The docs sites have no `llms.txt` or Markdown copies (6 of 10). Tool descriptions state the purpose, the cost of a launch, when to search recipes first and when to confirm with the user. REST descriptions are one line each (16 of 20). Required fields are marked and extra properties are refused, but there are no enums, `productName` and `regionName` are free strings, and the OpenAPI file's required lists name `image_id` and `couponCode` where the properties are `imageId` and `coupon` (8 of 15). Every REST operation has a response example. Only 200 and 202 are documented, and errors appear only in a troubleshooting table and a deployment errors page (7 of 15). The path is versioned as `/api/v1` and the MCP wrapper has a dated changelog. No API changelog was found (7 of 15).
- Agent ergonomics 56: 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 25). List tools take no arguments, with no pagination, filters or field selection. Only `recipes_search` has a `limit`, default 3 and maximum 10 (4 of 20). The docs explain 401, 402 and 429, the changelog names `-32003 Forbidden` for an out-of-scope call, and six deployment messages have written resolutions. None is in the OpenAPI file (10 of 20). All 17 tools carry `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint`. A launch has no idempotency key (14 of 20). A launch needs three fields and `regionName` accepts `any`. The only official packages are the npm and PyPI MCP wrappers, and the Go SDK and Terraform provider named on the product page were not found (8 of 15).
- Security & auth 61: OAuth with discovery from a 401 challenge, or named API tokens shown once and revoked one at a time. Both come in two tiers, read-only and full access, with no finer scopes. Secrets travel only in a header (26 of 30). The read-only tier blocks launch, restart, terminate and SSH key changes. Destructive tool descriptions ask the model to confirm with the user, and a published skill adds a disclosure step. No server-side confirmation was found (13 of 20). The MCP server redacts VM passwords from tool results. Recipes are vendor-written Markdown that tools tell the model to follow step by step, and the docs give no guidance on untrusted content (9 of 15). Connected Apps lists OAuth grants. No audit log or per-call history was found (3 of 15). The wrapper's SECURITY.md gives a disclosure address, a two-business-day acknowledgement and a 30-day fix target, and its CI runs static analysis and dependency audits. The site claims SOC 2 Type II and HIPAA with no report or trust page, and there is no security.txt or bug bounty (10 of 20).
- Payments & pricing 20: No x402, MPP or L402 in the docs, the OpenAPI files, the server card or the pricing page. Crypto top-ups are made by the account owner in the console (0). Hourly prices for every on-demand configuration are public at vm.massedcompute.com/pricing without a login (20). No free tier or trial credit was found, and a first deposit is needed before a launch (0). Signup, email verification, billing setup and token creation all happen in a browser (0).
- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.
- Maintenance & community 51: The newest release of the MCP wrapper is v1.1.0 of 24 July 2026, 77 days before the check. The hosted server has changed since, with fields in the server card that the July definitions lack, but no dated API changelog records it (20 of 30). One release and one dated changelog entry in the last 90 days (0). A dated wrapper changelog and a Discord server named as the fastest support route. No API changelog, and the repository shows six open issues or pull requests whose answers we did not read (7 of 15). Listed in the official MCP registry as `io.github.Massed-Compute/mcp` at 1.1.0, published 31 July 2026, with current npm and PyPI packages (15). CI tests Node 20 and 22 and Python 3.10 to 3.13 on three operating systems, with Dependabot, static analysis and a nightly check of the hosted endpoint. The npm package has no runtime dependencies (9 of 10).
- Transparency & trust 61: Closed service. The End User Licence Agreement of 15 September 2026 is clear and applies Nevada law, and the wrapper is MIT. The Terms & Conditions, the principal agreement, are drawn by a script we could not read (13 of 30). The privacy policy of 22 July 2026, the DPA of 27 March 2026 and the EULA are published. The EULA says VM data is destroyed at termination and persistent storage is kept at most 60 days after non-payment. The privacy policy is a general template that names a mobile application and gives no retention periods (19 of 30). No deprecation policy was found. The wrapper's changelog documents what 1.1.0 removed, and the older docs site still documents `api.massedcompute.com` while the current docs say not to use it (4 of 20). The sub-processor list names 23 processors with locations, is dated 10 September 2026 and has an RSS feed. The DPA says primary processing is in the United States (17 of 20).

Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (25 items): https://www.anchorterminal.com/fixes/massed-compute.md (JSON https://www.anchorterminal.com/fixes/massed-compute.json)

### What we couldn't check

- The lead named api-docs.massedcompute.com as the docs. That site documents an older marketplace Inventory API on `api.massedcompute.com` with keys issued by support. The API an agent would use is `https://vm.massedcompute.com/api/v1`, documented at vm-docs.massedcompute.com. The MCP address in the lead was right.
- unchecked: the Terms & Conditions. The page embeds a Termly viewer drawn by script, so the principal agreement, any SLA, refund terms and any clause on automated access were not read. `provenance.terms` points at the page, and the policy reader may not be able to read it either.
- unchecked: any request to `https://vm.massedcompute.com/api/`. robots.txt on that host disallows `/api/`, so the live endpoint, its 401 challenge and its OAuth authorisation server metadata were not fetched. Tool definitions come from the public server card.
- unchecked: PyPI and npm download counts and the PyPI release dates. Release dates come from the repository's tags and changelog.
- unchecked: the replies on the repository's six open issues or pull requests.
- The tools reference says a read-only credential does not see write tools. The wrapper's changelog says the tool list is the same for every key and write calls are refused with `-32003`. We could not test which holds.
- The server card's authentication block mentions only Bearer API keys, while the docs describe OAuth as well.
- The sub-processor list names Amazon Web Services for infrastructure while the site says Massed Compute owns and runs all its hardware. Which workloads run on AWS is not stated.
- The SOC 2 Type II, HIPAA, GDPR and Tier III claims have no report, auditor or trust page linked.
- Whether the 8 June 2026 password fix reached npm and PyPI as 1.0.3 is unclear. The registry lists 1.0.2 and 1.1.0, and the repository tag for v1.0.3 is dated 10 July 2026.
- Recipe tool descriptions tell the model to call `recipes_search` and follow recipes step by step. Recorded as a fact about the tool set. No deduction taken.

### Sources

- API and MCP product page: <https://massedcompute.com/products/inventory-api/> (seen 2026-10-09)
- on-demand product page with the uptime claim: <https://massedcompute.com/products/on-demand/> (seen 2026-10-09)
- pricing: <https://vm.massedcompute.com/pricing> (seen 2026-10-09)
- MCP overview with OAuth and token paths: <https://vm-docs.massedcompute.com/docs/mcp/overview> (seen 2026-10-09)
- MCP client setup: <https://vm-docs.massedcompute.com/docs/mcp/setup> (seen 2026-10-09)
- MCP tools reference: <https://vm-docs.massedcompute.com/docs/mcp/tools> (seen 2026-10-09)
- Agent Skills: <https://vm-docs.massedcompute.com/docs/mcp/skills> (seen 2026-10-09)
- MCP troubleshooting with 401, 402 and 429: <https://vm-docs.massedcompute.com/docs/mcp/troubleshooting> (seen 2026-10-09)
- API token settings: <https://vm-docs.massedcompute.com/docs/settings/api-settings> (seen 2026-10-09)
- Connected Apps (OAuth grants): <https://vm-docs.massedcompute.com/docs/settings/connected-apps> (seen 2026-10-09)
- team roles and instance groups: <https://vm-docs.massedcompute.com/docs/settings/team> (seen 2026-10-09)
- REST API reference: <https://vm-docs.massedcompute.com/api/v1> (seen 2026-10-09)
- OpenAPI file for the VM API: <https://vm-docs.massedcompute.com/redocusaurus/plugin-redoc-0.yaml> (seen 2026-10-09)
- MCP server card with tool definitions: <https://vm.massedcompute.com/.well-known/mcp/server-card.json> (seen 2026-10-09)
- agent catalogue: <https://vm.massedcompute.com/.well-known/ai-catalog.json> (seen 2026-10-09)
- OAuth protected resource metadata: <https://vm.massedcompute.com/.well-known/oauth-protected-resource> (seen 2026-10-09)
- robots.txt of the API host, which disallows /api/: <https://vm.massedcompute.com/robots.txt> (seen 2026-10-09)
- billing overview: <https://vm-docs.massedcompute.com/docs/billing/overview> (seen 2026-10-09)
- initial billing amounts: <https://vm-docs.massedcompute.com/docs/billing/initial-billing-amounts> (seen 2026-10-09)
- instance states, stop and delete: <https://vm-docs.massedcompute.com/docs/running-instances/instance-elements> (seen 2026-10-09)
- deployment errors: <https://vm-docs.massedcompute.com/docs/deploy/deployment-errors> (seen 2026-10-09)
- older marketplace Inventory API docs: <https://api-docs.massedcompute.com/api/v1> (seen 2026-10-09)
- MCP wrapper repository, changelog, SECURITY.md, CI and tags: <https://github.com/Massed-Compute/massed-compute-mcp> (seen 2026-10-09)
- vendor's public repositories: <https://api.github.com/orgs/Massed-Compute/repos> (seen 2026-10-09)
- official MCP registry entry: <https://registry.modelcontextprotocol.io/v0/servers?search=massed> (seen 2026-10-09)
- npm package: <https://registry.npmjs.org/massed-compute-mcp/latest> (seen 2026-10-09)
- Terms & Conditions page, body unread: <https://massedcompute.com/legal/terms-conditions/> (seen 2026-10-09)
- End User Licence Agreement: <https://massedcompute.com/legal/end-user-license-agreement/> (seen 2026-10-09)
- privacy policy: <https://massedcompute.com/legal/privacy-policy/> (seen 2026-10-09)
- Data Processing Agreement: <https://massedcompute.com/legal/dpa/> (seen 2026-10-09)
- sub-processors: <https://massedcompute.com/legal/subprocessors/> (seen 2026-10-09)
- about page with compliance claims: <https://massedcompute.com/about-us/> (seen 2026-10-09)
- security.txt, answered 404: <https://massedcompute.com/.well-known/security.txt> (seen 2026-10-09)
- RDAP for massedcompute.com: <https://rdap.verisign.com/com/v1/domain/massedcompute.com> (seen 2026-10-09)

## Who's behind it (provenance 68/100, checked 2026-10-09)

| Check | Finding | Points |
| --- | --- | --- |
| Legal entity named | Massed Compute, Inc. | 20/20 |
| Domain age | massedcompute.com, registered 2021-10-28 (4 years) | 7/15 |
| Endpoint on the vendor's domain | vm.massedcompute.com | 15/15 |
| Terms of service | published, but our reader couldn't read it | 7/10 |
| Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 |
| Status page | not found | 0/10 |
| Changelog | published | 10/10 |
| security.txt | not found | 0/10 |

The Terms & Conditions page is the document the DPA calls the Principal Agreement. Its body is an embedded Termly viewer drawn by script, and we could not read it.

The End User Licence Agreement, last updated 15 September 2026, names Massed Compute, Inc. of Las Vegas, Nevada, and applies Nevada law. The older docs site's footer says Massed Compute LLC.

The privacy policy, last updated 22 July 2026, covers the website, a mobile application and the Services in general.

The REST API and the MCP server answer at vm.massedcompute.com, on the vendor domain.

/.well-known/security.txt answers 404 on massedcompute.com and on vm.massedcompute.com.

RDAP for massedcompute.com gives a registration date of 2021-10-28.

No status page was found on the site, the docs or the pricing page.

The changelog linked is the MCP wrapper's. No API changelog was found.

A Data Processing Agreement, last modified 27 March 2026, and a sub-processor list, last updated 10 September 2026, are published.

### Terms and privacy, as read

A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.

**Terms of service** (https://massedcompute.com/legal/terms-conditions/), read 2026-10-09. Our reader couldn't read it (the page has 231 words of text without a browser, so the document is drawn by script or sits elsewhere).


**Privacy policy** (https://massedcompute.com/legal/privacy-policy/), read 2026-10-09, dated 2026-07-22, states 7 of the 8 things a reader expects.

- Gives the date it was last updated. Last updated 2026-07-22.
- Says how long data is kept. For as long as needed, with no period named.
- Says whether personal data is sold or shared for advertising. Says it does not sell personal data.
- Gives a privacy contact. Gives an email address, hidden from our reader by the page.
- Not found in the text. Says where data is transferred or stored.
- Also in the text (2026-10-08). Conversations with the website chatbot may be logged and reviewed. "Chatbot conversations may be logged and reviewed to improve the quality, accuracy, security, and performance of the service."
- Also in the text (2026-10-08). The notice says chatbot conversations are not used to train the vendor’s own AI models. "We do not use chatbot conversations to train our own AI models."

## Live (updated 2026-10-10 02:07 UTC)

- Right now: up, HTTP 200, 559 ms, checked 2026-10-10 02:07 UTC (get on `https://vm.massedcompute.com/api/v1`)
- Uptime 24h 100.0% (107 probes) · 30 days 100.0% (107 probes) · p50 563 ms · p95 1.6 s
- github `Massed-Compute/massed-compute-mcp` v1.1.0, released 2026-07-24
- npm `massed-compute-mcp` 1.1.0
- pypi `massed-compute-mcp` 1.1.0, released 2026-07-24
- Watching changelog <https://raw.githubusercontent.com/Massed-Compute/massed-compute-mcp/main/CHANGELOG.md>
- Watching pricing <https://vm.massedcompute.com/pricing>
- Watching privacy <https://massedcompute.com/legal/privacy-policy/>
- Watching terms <https://massedcompute.com/legal/terms-conditions/>
- Always current: https://www.anchorterminal.com/api/v1/live/massed-compute.json

## Probe metrics

Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.

## Prices

| Item | Price | Unit | Note |
| --- | --- | --- | --- |
| A30 24 GB VM | $0.35 | per GPU-hour | Billed per minute |
| RTX A5000 24 GB VM | $0.44 | per GPU-hour | Billed per minute |
| RTX A6000 48 GB VM | $0.57 | per GPU-hour | Billed per minute. An alternative configuration is $0.55 |
| RTX 6000 Ada 48 GB VM | $0.79 | per GPU-hour | Billed per minute |
| L40 48 GB VM | $0.86 | per GPU-hour | Billed per minute |
| RTX PRO 4500 Blackwell 32 GB VM | $0.92 | per GPU-hour | Billed per minute |
| L40S 48 GB VM | $0.97 | per GPU-hour | Billed per minute |
| A100 80 GB VM | $1.35 | per GPU-hour | Billed per minute. SXM4 and DGX variants are $1.38 |
| RTX PRO 6000 Blackwell 96 GB VM | $2.19 | per GPU-hour | Billed per minute |
| H100 80 GB VM | $2.73 | per GPU-hour | Billed per minute. H100 NVL is $3.11 and H100 SXM5 $3.14 |
| H200 NVL 141 GB VM | $3.62 | per GPU-hour | Billed per minute |
| B200 SXM6 VM, 8 GPUs | $5.43 | per GPU-hour | Sold only as eight GPUs at $43.46 an hour. Our division, rounded |
| B300 SXM6 VM, 8 GPUs | $6.60 | per GPU-hour | Sold only as eight GPUs at $52.80 an hour. Our division |

Across all listings: https://www.anchorterminal.com/prices/index.md

## Strengths

- API tokens and OAuth grants come in read-only and full-access tiers, and tokens are revoked one at a time in the console
- A public server card lists all 17 MCP tools with JSON Schema inputs and `readOnlyHint`, `destructiveHint` and `idempotentHint` annotations
- Hourly prices for 23 GPU configurations, from $0.35 for an A30 to $52.80 for eight B300s, are public without a login
- A public OpenAPI 3.0 file covers the 14 REST operations at `https://vm.massedcompute.com/api/v1`
- The sub-processor list names 23 processors with locations, was updated on 10 September 2026 and has an RSS feed for changes

## Weaknesses

- No status page, incident history or security.txt was found on any of the vendor's hosts
- A 429 answer exists but no rate limit figures are published, and the OpenAPI file documents no error response
- `POST /instance/launch` has no idempotency key, so a retried launch can start a second billed VM
- Until a fix dated 8 June 2026, `instances_list` and `instances_get` returned the cleartext VM password although their descriptions said it was redacted
- The product page lists Go and Terraform SDKs and webhooks that the docs, the OpenAPI file and the public GitHub organisation do not show
- A stopped instance is billed at the full hourly rate. Only termination ends billing, and it deletes the data

## Before you call it (notes for agents)

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

Install:

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

Claude Code:

```bash
claude mcp add --transport http massed-compute https://vm.massedcompute.com/api/mcp --header "Authorization: Bearer MC_TOKEN"
```

MCP client configuration:

```json
{
  "mcpServers": {
    "massed-compute": {
      "headers": {
        "Authorization": "Bearer MC_TOKEN"
      },
      "type": "http",
      "url": "https://vm.massedcompute.com/api/mcp"
    }
  }
}
```

Through letme (picks today, calling later): https://letme.dev/massed-compute. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md

## Similar tools

Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.

| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |
| --- | --- | --- | --- | --- | --- | --- |
| Nebius AI Cloud | B | 67.2 | 259 | compute.gpu | no | https://www.anchorterminal.com/tools/nebius-ai-cloud.md |
| Baseten | B | 66.5 | 285 | compute.gpu | no | https://www.anchorterminal.com/tools/baseten.md |
| Hugging Face Inference Endpoints | B | 64.5 | 349 | compute.gpu | no | https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.md |
| Modal | B | 63.6 | 382 | compute.gpu | no | https://www.anchorterminal.com/tools/modal.md |
| Replicate Deployments | B | 63.6 | 383 | compute.gpu | no | https://www.anchorterminal.com/tools/replicate-deploy.md |
| Crusoe Cloud | B | 63.4 | 396 | compute.gpu | no | https://www.anchorterminal.com/tools/crusoe-cloud.md |

## Panel reviews (0)

Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .

Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md

## Notable

- The MCP server is hosted at `https://vm.massedcompute.com/api/mcp` over Streamable HTTP, and the docs list 17 tools with the credential tier each needs (source: <https://vm-docs.massedcompute.com/docs/mcp/tools>)
- A public server card lists the 17 tools with input schemas and annotations, plus 37 setup recipes as resources (source: <https://vm.massedcompute.com/.well-known/mcp/server-card.json>)
- The vendor has two APIs. The current docs say customer traffic goes to `vm.massedcompute.com` and not `api.massedcompute.com`, while the older docs site still documents a marketplace Inventory API on the second host (source: <https://vm-docs.massedcompute.com/docs/settings/api-settings>)
- The MCP wrapper's changelog records a fix dated 8 June 2026 for `instances_list` and `instances_get` returning the cleartext VM password, and advises rotating affected passwords (source: <https://github.com/Massed-Compute/massed-compute-mcp/blob/main/CHANGELOG.md>)
- The REST API still returns the VM password at `/api/v1/instance/{uuid}` to the same Bearer token, per the tools reference (source: <https://vm-docs.massedcompute.com/docs/mcp/tools>)
- Stopping a VM keeps billing at the full hourly rate. A VM whose balance stays negative for about 12 hours is terminated (source: <https://vm-docs.massedcompute.com/docs/running-instances/instance-elements>)
- Four Agent Skills files for GPU choice, launches, cost audits and safe termination are published as Markdown (source: <https://vm-docs.massedcompute.com/docs/mcp/skills>)
- The product page lists SDKs for Python, Node.js and Go, a Terraform provider and webhooks. The docs, the OpenAPI file and the vendor's three public repositories show only the npm and PyPI MCP wrappers (source: <https://massedcompute.com/products/inventory-api/>)
- The site claims SOC 2 Type II, HIPAA and GDPR compliance and Tier III data centres. No report, auditor or trust page was found (source: <https://massedcompute.com/about-us/>)
- vm.massedcompute.com/robots.txt disallows `/api/` and names an agent catalogue at `/.well-known/ai-catalog.json` (source: <https://vm.massedcompute.com/robots.txt>)

- #19 of 19 in Best GPU and serverless compute for AI workloads: https://www.anchorterminal.com/best/gpu-compute/index.md
- All 167 gpu compute comparisons: https://www.anchorterminal.com/compare/gpu-compute/index.md

## Compare

- [Baseten vs Massed Compute](https://www.anchorterminal.com/compare/baseten-vs-massed-compute.md): B 66.5 vs E 42.3
- [Beam vs Massed Compute](https://www.anchorterminal.com/compare/beam-vs-massed-compute.md): C 55.5 vs E 42.3
- [Cerebrium vs Massed Compute](https://www.anchorterminal.com/compare/cerebrium-vs-massed-compute.md): C 55.3 vs E 42.3
- [CoreWeave vs Massed Compute](https://www.anchorterminal.com/compare/coreweave-vs-massed-compute.md): C 61.5 vs E 42.3
- [Crusoe Cloud vs Massed Compute](https://www.anchorterminal.com/compare/crusoe-cloud-vs-massed-compute.md): B 63.4 vs E 42.3
- [Hugging Face Inference Endpoints vs Massed Compute](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-massed-compute.md): B 64.5 vs E 42.3
- [Hyperbolic vs Massed Compute](https://www.anchorterminal.com/compare/hyperbolic-vs-massed-compute.md): D 48 vs E 42.3
- [Koyeb vs Massed Compute](https://www.anchorterminal.com/compare/koyeb-vs-massed-compute.md): D 46.5 vs E 42.3
- [Lambda Cloud vs Massed Compute](https://www.anchorterminal.com/compare/lambda-vs-massed-compute.md): D 50 vs E 42.3
- [Massed Compute vs Modal](https://www.anchorterminal.com/compare/massed-compute-vs-modal.md): E 42.3 vs B 63.6
- [Massed Compute vs Nebius AI Cloud](https://www.anchorterminal.com/compare/massed-compute-vs-nebius-ai-cloud.md): E 42.3 vs B 67.2
- [Massed Compute vs Northflank](https://www.anchorterminal.com/compare/massed-compute-vs-northflank.md): E 42.3 vs C 61.3
- [Massed Compute vs Replicate Deployments](https://www.anchorterminal.com/compare/massed-compute-vs-replicate-deploy.md): E 42.3 vs B 63.6
- [Massed Compute vs Runpod](https://www.anchorterminal.com/compare/massed-compute-vs-runpod.md): E 42.3 vs D 53.5
- [Massed Compute vs Thunder Compute](https://www.anchorterminal.com/compare/massed-compute-vs-thunder-compute.md): E 42.3 vs C 56.1
- [Massed Compute vs Vast.ai](https://www.anchorterminal.com/compare/massed-compute-vs-vast-ai.md): E 42.3 vs B 62.6
- [Massed Compute vs Verda](https://www.anchorterminal.com/compare/massed-compute-vs-verda.md): E 42.3 vs B 62.3

## Verify this listing

For the vendor. The badge or a plain link to this page verifies the listing, from a page on massedcompute.com or one of its subdomains, or the README of github.com/Massed-Compute/massed-compute-mcp. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "massed-compute", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify

HTML badge:

```html
<a href="https://www.anchorterminal.com/tools/massed-compute"><img src="https://www.anchorterminal.com/badges/massed-compute.svg" alt="Massed Compute on Anchor Terminal" height="20"></a>
```

Markdown badge, for a README:

```markdown
[![Massed Compute on Anchor Terminal](https://www.anchorterminal.com/badges/massed-compute.svg)](https://www.anchorterminal.com/tools/massed-compute)
```

Plain link:

```html
<a href="https://www.anchorterminal.com/tools/massed-compute">Massed Compute on Anchor Terminal</a>
```

## Share this listing

For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Massed Compute is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.

- Dark: https://www.anchorterminal.com/assets/share/massed-compute-dark.png
- Light: https://www.anchorterminal.com/assets/share/massed-compute-light.png