Lexicon runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 25 Oct 2026.
Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.
We read the source, 1 h 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.
(home as NSString).appendingPathComponent("Library/LaunchAgents/\(label).plist")
let process = Process()
Process.Start(new ProcessStartInfo(path) { UseShellExecute = true });
execFileSync(file, [...args], { encoding: 'utf8', timeout: 15000, stdio: ['ignore', 'pipe', 'ignore'] })) as ImportExec,
return path.join(xdgConfigHome(ctx.env, home), 'Claude', 'claude_desktop_config.json');
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 lexicon -- npx -y @ashlr/lexicon
{
"mcpServers": {
"lexicon": {
"command": "npx",
"args": [
"-y",
"@ashlr/lexicon"
]
}
}
}
[mcp_servers.lexicon]
command = "npx"
args = ["-y", "@ashlr/lexicon"]
{
"mcpServers": {
"lexicon": {
"command": "npx",
"args": [
"-y",
"@ashlr/lexicon"
]
}
}
}
{
"servers": {
"lexicon": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ashlr/lexicon"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
LEXICON_PATH (Path to the global lexicon YAML. Defaults to $XDG_CONFIG_HOME/lexicon/lexicon.yaml, else ~/.config/lexicon/lexicon.yaml), LEXICON_CWD (Directory used to locate the project .lexicon.yaml. Defaults to the server process working directory).
The oracle for agents. Verify trades, tokens and messages before your agent acts.
The oracle for agents. Verify trades, tokens and messages before your agent acts.
Private on-device speech to text: transcribe audio files and search your Yap dictations. No upload.
Puts Approve/Deny on your phone before an agent acts, and waits for your fingerprint.
Give your AI agents the ability to listen. Microphone capture and speech-to-text.
Give your AI agents the ability to listen. Microphone capture and speech-to-text.
Your agent asks before it acts, so the same real-world action is attempted at most once.
Read a project's prompts, logs and agents, and send new work to the agent on your own machines.
Answers built from our own checks of this server.