Pulse
About
Open compute-pricing reference — daily GPU and inference-token medians, free under CC-BY 4.0.
Details
- Author
- pulsebenchmarks
- Categories
- Cloud Service, Infrastructure, AI, Other
Jump to
Setup
Install Pulse in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/pulsebenchmarks/pulse-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
MCP server forPulse— the open compute-pricing reference. Daily GPU and inference-token medians, free under CC-BY 4.0.
The server is hosted athttps://pulsebenchmarks.com/mcp. This repository is a public mirror of the production handler, kept here so MCP registries and end users have a stable source URL.
Install the server in Claude Desktop, Cursor, Cline, or any MCP-aware client. You get five tools that wrap the public Pulse API and return JSON with pre-formatted citations:
- list_indices— every published index with current value, freshness, and methodology version
- get_series— full payload for one index: history, per-provider observations, contributing-provider list
- latest_value— quick lookup for one index, withcite_asstring ready to paste
- get_status— pipeline freshness and per-provider collection health
- compare_indices— current values across multiple indices side-by-side
The data covers four GPU series (H100 SXM and A100 80GB, hyperscaler vs neocloud), four additional neocloud series (B200, H200 141GB, H100 PCIe, A100 80GB spot), and an inference-token basket anchored on Llama 3.3 70B FP8.
The server is hosted, so the install is the same on every client: pointmcp-remoteat the public endpoint.
Add to~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or the equivalent on Windows/Linux:
{ "mcpServers": { "pulse": { "command": "npx", "args": ["-y", "mcp-remote", "https://pulsebenchmarks.com/mcp"] } } }
Restart Claude Desktop. You should seepulsein the tools menu.
Add to~/.cursor/mcp.json(or use the in-app MCP settings). Same JSON as above; full file inexamples/cursor_mcp.json.
Any MCP client that speaksmcp-remoteover HTTP works the same way. The endpoint ishttps://pulsebenchmarks.com/mcp; transport is JSON-RPC 2.0 over POST; no auth.
Full input schemas and tool implementations are infunctions/mcp.js.
The MCP server is a thin wrapper over Pulse's public HTTP endpoints. The same data is available without an MCP client:
- Methodology:https://pulsebenchmarks.com/methodology/
- Public API:GET https://pulsebenchmarks.com/api/indices,GET https://pulsebenchmarks.com/api/indices/{slug},GET https://pulsebenchmarks.com/api/status
- Bulk export (CC-BY 4.0):https://pulsebenchmarks.com/data/data_export.json
- Reproducibility script:https://pulsebenchmarks.com/methodology/#reproducibility
- Agent guide:https://pulsebenchmarks.com/llms.txt
Methodology v1.0 covers four headline GPU series (H100 SXM and A100 80GB, hyperscaler vs neocloud) plus a Llama 3.3 70B FP8 inference-token basket. Series additions and methodology changes are versioned and documented in themethodology changelog.
For most users we recommend the hosted server. Self-hosting is mainly useful if you want to add caching, vendor it into a private network, or extend the tool set against the same public endpoints.
- Server code (this repository):Apache License 2.0
- Pricing data returned by the server:Creative Commons Attribution 4.0 International(CC-BY 4.0)
When citing a value, prefer thecite_asstring returned bylatest_value. It already includes the index name, methodology version, year, and canonical URL.
- Email:methodology@pulsebenchmarks.com
- Issues:https://github.com/pulsebenchmarks/pulse-mcp/issues
The production handler lives in the main Pulse codebase; changes there flow into this repository on a release cadence. PRs are reviewed as time allows; for fast turnaround on data or tool-shape changes, open an issue first so we can align before you write code.
Manage research data and compute with Globus.
Free oncology data (research, clinical trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions, exposed as MCP tools.
Integrate with the Dataloop AI platform for data management and annotation using a Docker-based stdio interface.
Access the Hugging Face Dataset Viewer API to query, explore, search, and analyze machine learning datasets from the Hugging Face Hub.
Interact with Qlik Cloud applications and extract data from visualizations using the Qlik Cloud API.
Create computer vision projects, train models, and deploy them with Roboflow MCP server
A server for Snowflake providing tools for its Cortex AI features, including Search, Analyst, and Complete.
Administer Tableau Cloud with AI-powered tools. This server offers complete API coverage, enterprise-grade logging, and a production-ready architecture.
Get access to Kaggle's datasets, models, competitions, notebook and benchmarks.
An AI-powered gateway for managing over 40 data sources like Alibaba Cloud and mainstream databases, featuring NL2SQL, code generation, and data migration.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
