Site is a remote MCP server that gives an AI agent 7 tools, among them dataset_columns, dataset_compare, dataset_provenance. It answers at https://biobricks.org/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.
BioBricks: the site's own MCP server — dataset, enquiry (enquiry = a human handoff, not a...
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
dataset_columns | The columns, which of them are numeric, the row count and the provenance banner of the BioBricks dataset. Call this first to learn the schema. |
dataset_compare | The rows of the BioBricks dataset whose column is any of the given values, in the order given — for "X vs Y" questions. Inputs: column, values |
dataset_provenance | The source, the date it was computed, the licence and the citation for the BioBricks dataset. Read this to attribute a figure correctly. |
dataset_row | The rows of the BioBricks dataset where a column equals a value exactly (case-insensitive). Inputs: column, value |
dataset_search | Rows of the BioBricks dataset whose cells contain the query (case-insensitive), up to 50. Inputs: query, limit |
dataset_stats | count, min, max, mean, median and sum of a numeric column of the BioBricks dataset (grouping commas and currency are handled; non-numeric rows are excluded and counted). Inputs: column |
dataset_top | The highest (or lowest) rows of the BioBricks dataset by a numeric column — "which is the most/least X". Inputs: column, limit, ascending |
Every block below points at https://biobricks.org/mcp. Pick your client and copy.
claude mcp add --transport http site https://biobricks.org/mcp
{
"mcpServers": {
"site": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://biobricks.org/mcp"]
}
}
}{
"mcpServers": {
"site": {
"url": "https://biobricks.org/mcp"
}
}
}{
"servers": {
"site": {
"type": "http",
"url": "https://biobricks.org/mcp"
}
}
}{
"context_servers": {
"site": {
"url": "https://biobricks.org/mcp"
}
}
}{
"mcpServers": {
"site": {
"serverUrl": "https://biobricks.org/mcp"
}
}
}{
"mcpServers": {
"site": {
"url": "https://biobricks.org/mcp"
}
}
}name: Site
version: 0.0.1
schema: v1
mcpServers:
- name: Site
type: streamable-http
url: https://biobricks.org/mcp{
"mcpServers": {
"site": {
"httpUrl": "https://biobricks.org/mcp"
}
}
}{
"mcpServers": {
"site": {
"type": "http",
"url": "https://biobricks.org/mcp"
}
}
}{
"mcpServers": {
"site": {
"url": "https://biobricks.org/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fbiobricks.org%2Fmcp&type=streamable_http&id=site&name=Site
It answered our last check on 24 October 2026 in 474 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by biobricks.org and served from biobricks.org, the vendor's own domain: https://biobricks.org/mcp.
7, as returned by the server's own tools/list on 23 September 2026: dataset_columns, dataset_compare, dataset_provenance, dataset_row, dataset_search, dataset_stats, dataset_top.
It answered our last check on 24 October 2026 in 474 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://biobricks.org/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: org.biobricks. Endpoint host: biobricks.org. ARD identifier: urn:air:org.biobricks:mcp:site.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.