Arkheiaai runs on your own machine — the client starts it, so there is no endpoint to ping. 46 installs a week from npm. Last commit 4 Aug 2026.
Detect fabrication and hallucination in any LLM output. 30+ models supported.
We read the source, 23 min 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.
postinstall: node scripts/setup.js
const version = execFileSync(resolved, ["--version"], {
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
proc = subprocess.run(
env = dict(os.environ)
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 mcp-server -- npx -y @arkheia/mcp-server
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@arkheia/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@arkheia/mcp-server"]
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@arkheia/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@arkheia/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ARKHEIA_API_KEY (Your Arkheia API key (get one free at https://arkheia.ai)).
The author declared them in the registry entry; get the values from the project itself.
Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
Translate text or HTML, detect languages, and list supported languages with Langbly.
Hallucination validator and factual grounding checker for LLM outputs.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.
Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.
Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated.
Answers built from our own checks of this server.