Mandare runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 3 Oct 2026.
Verify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first.
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
cached = execFileSync(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 mandare -e 'MANDARE_LEDGER_DB=<MANDARE_LEDGER_DB>' -- npx -y @mandarelabs/mcp-server
{
"mcpServers": {
"mandare": {
"command": "npx",
"args": [
"-y",
"@mandarelabs/mcp-server"
],
"env": {
"MANDARE_LEDGER_DB": "<MANDARE_LEDGER_DB>"
}
}
}
}
[mcp_servers.mandare]
command = "npx"
args = ["-y", "@mandarelabs/mcp-server"]
env = { MANDARE_LEDGER_DB = "<MANDARE_LEDGER_DB>" }
{
"mcpServers": {
"mandare": {
"command": "npx",
"args": [
"-y",
"@mandarelabs/mcp-server"
],
"env": {
"MANDARE_LEDGER_DB": "<MANDARE_LEDGER_DB>"
}
}
}
}
{
"servers": {
"mandare": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mandarelabs/mcp-server"
],
"env": {
"MANDARE_LEDGER_DB": "<MANDARE_LEDGER_DB>"
}
}
}
}
Put your own value in place of
<MANDARE_LEDGER_DB> (Path to the Mandare ledger database this MCP server verifies and kills against).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
MANDARE_MCP_HOME (Directory where issued artifacts (mandates, credentials, token grant files) are written (default ~/.mandare/mcp)), MANDARE_WITNESS_URL (Witness server URL — enables truncation/rewrite checks and certificate export), MANDARE_WITNESS_PUBLIC_KEY (The witness's Ed25519 public key (64 hex chars), obtained out-of-band), MANDARE_GATEWAY_URL (Running gateway base URL — enables the gateway health tool), MANDARE_MCP_ALLOW_REINSTATE (Set to 1 to expose the reinstate tool (off by default; kills only close doors)).
Tamper-evident record of what your AI agent did, plus local-first verifiable memory.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
Read, verify and export a tamper-evident log of what an AI agent did. Read-only.
Evidence-first entity and knowledge graph MCP server for AI agents to verify claims.
Local-first memory for AI agents: markdown source of truth, budget-aware recall, write gate.
Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles.
List, check and package a SKILL.md skill for every agent-skill store.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Answers built from our own checks of this server.