LLMVerify runs on your own machine — the client starts it, so there is no endpoint to ping. 3 729 installs a week from npm. Last commit 9 Oct 2026.
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
We read the source, 7 d ago · rules ccca72095570
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.
<li>Select text in the editor</li>
<li>Press <code>Ctrl+Shift+V</code> (or <code>Cmd+Shift+V</code> on Mac)</li>
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 llmverify -- npx -y llmverify
{
"mcpServers": {
"llmverify": {
"args": [
"-y",
"llmverify"
],
"command": "npx"
}
}
}
[mcp_servers.llmverify]
command = "npx"
args = ["-y", "llmverify"]
{
"mcpServers": {
"llmverify": {
"args": [
"-y",
"llmverify"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"llmverify": {
"args": [
"-y",
"llmverify"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
LLMVERIFY_MCP_MAX_INPUT_CHARS (Max characters accepted in a content/input argument), LLMVERIFY_MCP_TIMEOUT_MS (Per-tool wall-clock timeout in milliseconds), LLMVERIFY_MCP_MAX_OUTPUT_ITEMS (Cap on any single output array), LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS (Cap on any single text field in output), LLMVERIFY_HOME (Base directory for engine local state), LLMVERIFY_AUDIT_DIR (Audit JSONL directory), LLMVERIFY_LOG_DIR (Operational log directory), LLMVERIFY_BASELINE_DIR (Drift baseline directory), LLMVERIFY_USAGE_FILE (Usage counter file), LLMVERIFY_AUDIT_HASH_KEY (Enables keyed hmac-sha256 content hashes in audit records), LLMVERIFY_AUDIT_NO_CONTENT_HASH (Set to 1 to disable content hashes in audit records).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Verus on-chain data retrieval, decryption, signing, and verification
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
Local security layer for coding agents: secret redaction, prompt-injection checks and MCP proxy.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Zotero MCP server: local-first search, library checks, and preview-first writes for AI agents.
Local-first MCP server for PlantUML and Mermaid diagrams with drift detection.
Zero-cost MCP server for local code inspection and best-practice recommendations
Crypto market intelligence, token rug-checks, and wallet verification in one MCP server.
Answers built from our own checks of this server.