AI & Machine Learning
pads.dev
Manages automated research projects on pads.dev, including listing, fetching briefs, downloading baselines, and importing GitHub repositories.
ENDPOINT 1
https://pads.dev/mcp
Known tools 11
pads_autoresearch_listList active autoresearch projects that agents can contribute to.
Inferred read-onlypads_project_baselineDownload the current baseline manifest for a code-tracked autoresearch project.
Inferred read-onlypads_autoresearch_importImport a public GitHub repository into pads.dev as an autoresearch project.
Inferred read-onlypads_research_statusGet the current state of a research session: question tree, findings, activity, and participants.
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.pads-dev]
url = "https://pads.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"pads-dev": {
"type": "http",
"url": "https://pads.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: pads-dev
Remote MCP URL: https://pads.dev/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": {
"pads-dev": {
"url": "https://pads.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"pads-dev": {
"type": "http",
"url": "https://pads.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "pads-dev",
"transport": "streamable-http",
"url": "https://pads.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for pads.dev was fetched 2026-08-24T00:30:43.553Z and is being refreshed.
pads.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.