Tersign Evidence runs on your own machine — the client starts it, so there is no endpoint to ping. 181 installs a week from npm. Last commit 30 Aug 2026.
Counter-signed evidence records for agent commerce: receipts, verification, dispute envelopes.
We read the source, 20 h ago · rules 3dff92dd89df
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.
const child = spawn(opts.command, [...opts.args], { stdio: ['pipe', 'pipe', opts.stderr] });
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 evidence -- npx -y tersign
{
"mcpServers": {
"evidence": {
"args": [
"-y",
"tersign"
],
"command": "npx"
}
}
}
[mcp_servers.evidence]
command = "npx"
args = ["-y", "tersign"]
{
"mcpServers": {
"evidence": {
"args": [
"-y",
"tersign"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"evidence": {
"args": [
"-y",
"tersign"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
TERSIGN_SELLER_KEY (0x-prefixed private key the seller signs receipts with), TERSIGN_ISSUER_NAME (Seller/issuer display name), TERSIGN_ISSUER_JURISDICTION (Seller jurisdiction (e.g. HK)), TERSIGN_ISSUER_TAX_ID (Seller tax/business-registration id (optional)), TERSIGN_LEDGER_URL (Hosted ledger base URL for counter-signing (optional; SDK works standalone)), TERSIGN_LEDGER_API_KEY (Ledger seller API key (required only if counter-signing)), TERSIGN_LEDGER_SELLER_ID (Ledger seller id (required only if counter-signing)).
The author declared them in the registry entry; get the values from the project itself.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records.
Independent effect verification and signed receipts for consequential AI agent actions.
Runtime verification for agent tool calls: Ed25519 signed receipts, fail-closed RCE/SSRF checks.
Agent leases, signed receipts, watchdogs, and optional paid source-verification evidence.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Read-only agent-commerce audit for UCP, x402, remediation and verification evidence.
Read-only discovery for exact-commit Agent Skill validation, x402 payment, and signed receipts.
Answers built from our own checks of this server.