Policyrecall runs on your own machine — the client starts it, so there is no endpoint to ping. 274 installs a week from npm. Last commit 2 Nov 2026.
Policy-verified recall and calibration for tool calls via signed operational memory.
Nothing serious here today
Today is the operative word: we check Policyrecall every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add policyrecall -- npx -y @reneturcios/policyrecall{
"mcpServers": {
"policyrecall": {
"command": "npx",
"args": [
"-y",
"@reneturcios/policyrecall"
]
}
}
}[mcp_servers.policyrecall]
command = "npx"
args = ["-y", "@reneturcios/policyrecall"]{
"mcpServers": {
"policyrecall": {
"command": "npx",
"args": [
"-y",
"@reneturcios/policyrecall"
]
}
}
}{
"servers": {
"policyrecall": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/policyrecall"
]
}
}
}Alternatives to Policyrecall
same job, measured the same wayRecall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.
Governed organizational memory for AI: recall returns only what the signed-in person may see.
Recall, check, search, timeline, and graph tools for fiction writers via Seizn Memory v3.
The open routing layer for AI tools: tool calls routed per policy, decision on every result.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools.
Verifiable decision records for AI agents: signed receipts for calls to its own governed tools.
Known MCP tool-call failures and workarounds verified by reproduction.
Policyrecall — questions
Answers built from our own checks of this server.