Mmcp.market

MCP server

by prismnetwork-tech·io.github.prismnetwork-tech/mcp·v0.9.4

Rent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

1 stars70 downloads/wk

Reviews

Write one

Nobody has reviewed MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MCP tools (21, 7 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • prism_batch_result

    Read the output of a batch lease by lease_id, once its node has reported. Use it to recover a result after prism_batch_run timed out.

  • prism_batch_runwrite action

    Fund a lease that runs one command with no interactive access at all: the node executes it and reports the signed output. Matches only suppliers at trust class 'isolated' or above, so it can find no supplier when none is online; prefer prism_lease_and_run for broad availability. Output is capped at 64 KiB per stream.

  • prism_budget

    Show the spending limits this server enforces and what it has already spent in the last 24 hours, with the recent charges. Needs no wallet. Check this before a long job; a lease refused for budget says the same numbers.

  • prism_confidential_inferwrite action

    Buy one LLM generation that runs inside a GPU TEE, with the message contents encrypted end to end to a key the enclave's own attestation commits to, so Prism's relay in between carries ciphertext and cannot read the prompt or the answer. Costs a little more than prism_infer. Returns the answer, the cost, and a receipt id the workload signed over the exact bytes of the exchange; pass that id to pri

  • prism_end_lease

    Release a lease. Access closes and billing stops here: settlement charges the seconds the lease was open and returns the rest of the deposit. A lease nobody releases bills until its window ends.

  • prism_inferwrite action

    Buy one LLM generation from Prism's managed inference endpoint. Pays the quoted USDG price from this wallet (about 0.01 USDG), waits through a cold start when no box is warm (up to a few minutes), and returns the generation with token usage. Cheaper and simpler than leasing when all you need is a completion.

  • prism_infer_batchwrite action

    Buy many LLM generations from Prism's managed inference endpoint in one paid call. Every prompt runs whole on a rented GPU, spread across every GPU the endpoint holds, so a list of prompts finishes far sooner than the same prompts sent one at a time. Costs the single-generation price times the number of prompts. Returns every answer in order plus a Merkle receipt naming the leases that did the wor

  • prism_lease

    Lease a GPU and keep it running. Returns a lease_id and SSH access. Use prism_run to execute commands and prism_end_lease when done.

  • prism_lease_and_runwrite action

    Lease a GPU, run one shell command on it, and return the output. The lease stays alive (use prism_run for more commands, prism_end_lease to release). Prefer this for a single command; use prism_lease when you'll run several.

  • prism_leases

    List this wallet's leases on Prism Network with their current state.

  • prism_list_gpus

    List GPUs currently available to lease on Prism Network, with model, VRAM, price per second in USDG, and trust class. Trust class runs open < isolated < attested < confidential; on an 'open' supplier the host operator can read anything the workload touches. Keep secrets and credentials in prism_vault_store rather than on the box, and raise min_trust when the workload itself must not be readable.

  • prism_price_index

    Current GPU pricing on Prism Network by model: sourced low/median/high and settled mean, in USDG per hour. Needs no wallet. Use it to estimate what an analysis job will cost before leasing.

  • prism_receipts

    Recent settled lease receipts from the public proof feed: GPU model, runtime, what was charged and refunded, and the settlement transaction hash on Robinhood Chain. Needs no wallet. Every Prism lease ends in one of these.

  • prism_runwrite action

    Run a shell command on a GPU you already leased with prism_lease.

  • prism_vault_deletewrite action

    Permanently delete a vault item. The ciphertext is removed and the value cannot be recovered.

  • prism_vault_list

    List the agent's sealed vault items: item_id, label, version and trust floor. Values are not returned and are not readable by Prism.

  • prism_vault_read

    Decrypt and return one vault item, in this process, using the wallet-derived key. The plaintext exists only here; do not echo it into a leased workspace, a log, or a message.

  • prism_vault_release

    Authorize a vault item into a lease you hold and return its plaintext for use there. Refused when the lease's trust class is below the item's trust floor, which is what stops a secret reaching a host that can read it. Every allowed release is recorded against the account.

  • prism_vault_store

    Store private data (a card, an identity document, an API credential) encrypted under a key derived from this agent's wallet on this machine. Prism receives ciphertext only and cannot read it. Use this instead of writing a secret into a workspace or a file. Returns an item_id; the value is not recoverable without the wallet.

  • prism_verify_attestation

    Check a confidential generation against its signed receipt and the hardware behind it: the TDX quote verifies to Intel's root and commits to the key set that signed the receipt, the boot log replays to the measurement in that quote, the receipt covers the exact bytes of this call, the upstream that ran the model was itself verified, and the GPU is attested by NVIDIA. Returns every check with its r

  • prism_wallet

    Show the agent's wallet address and on-chain balances (USDG and ETH for gas) on Robinhood Chain. Check this before leasing to confirm the wallet can pay.

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • Live reliabilityno gateway calls yet and no remote to proben/a
  • Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the MCP repository's README, as published. We do not edit it. Read it on GitHub

Prism Network

Prism Network is open infrastructure for metered GPU compute. The current system implements account and wallet onboarding, GPU offer discovery, USDG escrow, workload provisioning, time-limited access, metering, settlement and public receipt generation.

Prism has two execution paths:

VM-backed containers with exclusive NVIDIA VFIO passthrough. Access uses short-lived SSH or Jupyter credentials through an outbound-only mTLS tunnel.

  • Independent nodes: Ubuntu 24.04 x86-64 hosts run public OCI images in Kata

exposes direct SSH. This path relies on provider-reported readiness and evidence; it does not provide Kata/VFIO isolation, the Prism gateway, or Jupyter access.

  • Vast broker: a bonded broker provisions disposable L40S instances and

Interactive raw GPU leases are what the network serves today. A lease can also carry a single command instead of a session, which runs on an independent node and reports back what it printed, but no independent node has completed the hardware canary yet, so nothing has run that path in production. Managed inference is not implemented.

Current state

Verified on 2026-07-20:

This is an unaudited pre-production system, so do not put production traffic or serious money on it yet.

What a supplier protects is stated per offer rather than as one blanket warning. Every offer, quote, lease and receipt carries a trust class (open, isolated, attested or confidential), and renters can require a minimum instead of trusting prose:

curl https://api.prismnetwork.tech/v1/offers?min_trust=isolated

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y @prismnetwork/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @prismnetwork/mcp
Add to Cursor

MCP: common questions

Is MCP server safe?
Mostly: it is graded B (82/100). Read the MCP safety report
How do I install MCP?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does MCP need an API key?
Yes. The registry entry asks for PRISM_AGENT_KEY.
Is MCP maintained?
The last commit was 5 days ago (2026-09-16). The latest release is v0.9.4.
What can I use instead of MCP?
Servers from other publishers that do the same job: Ausca MCP server, Maginary MCP server and BridgeNode MCP server. Compare all MCP alternatives.

Alternatives to MCP

Same job from other publishers: the closest match first, then the best rated.

All MCP alternatives →
  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    B
  • Maginary
    AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
    B
  • BridgeNode MCP
    BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
    A
  • NVIDIA Elements
    NVIDIA Elements UI design system and agent tools for AI/ML, robotics, and autonomous vehicles.
    A
  • Ask Codex
    Bridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions
    A

More from prismnetwork-tech