agiscorecard-web3-compute

io.github.f-tiger/agiscorecard-web3-computeVersion 1.7.0

Compare GPU workload costs per accepted output, including setup, storage, egress and failed work.

Status

Responds251 msNov 14, 2026, 14:51 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:51 UTC
Latency: 251 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://compute.agiscorecard.com/mcpResponds251 msNov 14, 2026, 14:51 UTC

No sign-in

Claude Code

claude mcp add --transport http agiscorecard-web3-compute https://compute.agiscorecard.com/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: agiscorecard-web3-compute
Remote MCP server URL: https://compute.agiscorecard.com/mcp

Cursor

{
  "mcpServers": {
    "agiscorecard-web3-compute": {
      "url": "https://compute.agiscorecard.com/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"agiscorecard-web3-compute","type":"http","url":"https://compute.agiscorecard.com/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

3 tools

Tools of agiscorecard-web3-compute
	Description		Read-only	Idempotent	Open world
`compare_compute_costs`Compute Lens compares measured workload runs using total entered compute, setup, storage and egress costs per accepted output. It filters mismatched workload labels, currencies, quality and memory limits. All examples are fictional; no live GPU quotes are supplied. No live GPU inventory, automatic benchmarking, reservation, infrastructure management or verified savings. Retrieve compute with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.	Compute Lens compares measured workload runs using total entered compute, setup, storage and egress costs per accepted output. It filters mismatched workload labels, currencies, quality and memory limits. All examples are fictional; no live GPU quotes are supplied. No live GPU inventory, automatic benchmarking, reservation, infrastructure management or verified savings. Retrieve compute with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.	No	Yes	Yes	No
`fetch`Retrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.	Retrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.	No	Yes	Yes	No
`search`Search this server’s public AI/Web3 tools and citation pages. English and Chinese names supported. Empty query lists the available worksheets.	Search this server’s public AI/Web3 tools and citation pages. English and Chinese names supported. Empty query lists the available worksheets.	No	Yes	Yes	No

Details

Registry status: Active
Published: Oct 10, 2026
Updated: Oct 10, 2026
Website: https://compute.agiscorecard.com/⁠ (opens in a new tab)
Repository: https://github.com/f-tiger/agi-site⁠ (opens in a new tab)
Categories (suggested): Files and storageSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing