Pulse MCP Server

Open compute-pricing MCP server — daily GPU and inference-token medians, free under CC-BY 4.0.

Remote serverstreamable-http

What is the Pulse MCP MCP server?

Open compute-pricing MCP server — daily GPU and inference-token medians, free under CC-BY 4.0. Exposed over MCP by the pulse mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • list_indices — List every published Pulse compute-pricing index with its current value, freshness, methodology version, and status
  • get_series — Fetch the full payload for one Pulse index: metadata, gated daily headline series, per-provider observations, contributing-provider list. Optional
  • latest_value — Quick lookup: the latest published value for one index, with minimal payload and a ready-to-paste cite_as string
  • get_status — Pipeline freshness and per-provider collection health
  • compare_indices — Compare current values across multiple Pulse indices (e.g. hyperscaler vs neocloud for the same GPU)
  • Cursor — Add to ~/.cursor/mcp.json (or use the in-app MCP settings). Same JSON as above; full file in examples/cursor_mcp.json

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pulse MCP's toolset — list_indices, get_series, latest_value and 3 more — is a fair guide to whether it matches your workflow. It is maintained by pulsebenchmarks; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pulse MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the pulse mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
list_indicesList every published Pulse compute-pricing index with its current value, freshness, methodology version, and status.
get_seriesFetch the full payload for one Pulse index: metadata, gated daily headline series, per-provider observations, contributing-provider list. Optional range filter (30d / 90d / 1y / all).
latest_valueQuick lookup: the latest published value for one index, with minimal payload and a ready-to-paste cite_as string.
get_statusPipeline freshness and per-provider collection health.
compare_indicesCompare current values across multiple Pulse indices (e.g. hyperscaler vs neocloud for the same GPU).
CursorAdd to ~/.cursor/mcp.json (or use the in-app MCP settings). Same JSON as above; full file in [examples/cursor_mcp.json](examples/cursor_mcp.json).

How to install the Pulse MCP MCP server

{
  "mcpServers": {
    "pulse": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://pulsebenchmarks.com/mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Pulse MCP to list indices.
  • Use Pulse MCP to get series.
  • Use Pulse MCP to latest value.

Frequently asked questions

It connects Pulse MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (list_indices, get_series, latest_value, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pulse MCP directly.