ProvenPin is answering right now. Last checked 3 min ago. It exposes 3 tools. Last commit 16 Oct 2026.
Tested, version-pinned code recipes for AI coding agents, each with its last-passed receipt.
Today is the operative word: we check ProvenPin every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
claude mcp add provenpin --transport http https://mcp.provenpin.com/mcp
{
"mcpServers": {
"provenpin": {
"url": "https://mcp.provenpin.com/mcp"
}
}
}
[mcp_servers.provenpin]
url = "https://mcp.provenpin.com/mcp"
{
"mcpServers": {
"provenpin": {
"url": "https://mcp.provenpin.com/mcp"
}
}
}
{
"mcpServers": {
"provenpin": {
"url": "https://mcp.provenpin.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_recipe
search_recipes
list_stacks
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.provenpin.com/mcp | streamable-http | answering | 123 ms | 3 min ago |
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Research intelligence for AI coding agents. 2M+ CS papers with evidence and tradeoffs.
Multi-party decisions for agents: red lines rejected in code, max-min pick, SHA-256 receipt. Stdlib.
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
Keeps AI coding agents' plan and design markdown managed and versioned, for Claude Code and Codex.
AI personas with a lasting, encrypted memory per project, for Claude Code. Hosted in France.
Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.
Answers built from our own checks of this server.