General Tools
buildspace.tv
Provides general-purpose tools through the Model Context Protocol.
ENDPOINT 1
https://www.buildspace.tv/api/mcp
MCP server metadata
- Name
- physical-ai-sprint
- Version
- 1.0.0
Data for The Physical AI Sprint, a one-day Physical AI hackathon on 2026-08-17 in San Francisco alongside Actuate SF, hosted by Nebius with NVIDIA, Antioch and Toloka. Use these tools to answer questions about the event itself (date, schedule, hosts, robots available, judging criteria), about which teams are attending and which still have room for members, and about what projects teams built. Everything here is read-only. You cannot register a person, create a team, or submit a project through this server: registration is on Luma and both forms are GitHub issue forms that need a signed-in human. Give the user the link instead of attempting it.
Known tools 5
list_teamsList the teams taking part in The Physical AI Sprint, with each team's roster, the skills they already have, and the skills they are still looking for.
Inferred read-onlyget_teamGet a single hackathon team by its slug, including the full roster with GitHub handles, the pitch describing what they want to build, and the URL of the GitHub thread where people ask to join.
Inferred read-onlylist_projectsList the projects submitted to the showcase, with the track each ran in (simulation only, hardware only, or both), the robots used, demo media, and the team that built it.
Inferred read-onlyget_event_detailsGet the details of The Physical AI Sprint: the date, start and end times, hosting organizations, the three project tracks, the robot hardware available, the judging criteria, the submission deadline, and how to register.
Inferred read-onlysearch_hackathonSearch across everything at once: team names and pitches, the skills teams are seeking, project titles and descriptions, the robots used, and people by name or GitHub handle.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.physical-ai-sprint]
url = "https://www.buildspace.tv/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"physical-ai-sprint": {
"type": "http",
"url": "https://www.buildspace.tv/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: physical-ai-sprint
Remote MCP URL: https://www.buildspace.tv/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"physical-ai-sprint": {
"url": "https://www.buildspace.tv/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"physical-ai-sprint": {
"type": "http",
"url": "https://www.buildspace.tv/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "physical-ai-sprint",
"transport": "streamable-http",
"url": "https://www.buildspace.tv/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.