SPM is answering right now. Last checked 10 min ago.
Agent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.
Over the last week it answered 99.6% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add spm --transport http https://api.spmos.ai/mcp
{
"mcpServers": {
"spm": {
"url": "https://api.spmos.ai/mcp"
}
}
}
[mcp_servers.spm]
url = "https://api.spmos.ai/mcp"
{
"mcpServers": {
"spm": {
"url": "https://api.spmos.ai/mcp"
}
}
}
{
"mcpServers": {
"spm": {
"url": "https://api.spmos.ai/mcp"
}
}
}
This endpoint answered with an authorization challenge — the server is running, but you need an API key or OAuth to use it.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.spmos.ai/mcp | streamable-http | needs key | 1490 ms | 10 min ago |
Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records.
Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
Tamper-evident record of what your AI agent did, plus local-first verifiable memory.
Evidence-gated verification, selection, and measurement MCP for coding agents.
Agent memory where every fact carries a receipt, and deletion is provable.
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
Verifiable fact-checking: verdict, confidence, sources, and a tamper-evident certificate.
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Answers built from our own checks of this server.