Voyager runs on your own machine — the client starts it, so there is no endpoint to ping. 107 installs a week from npm. Last commit 21 Jul 2026.
Cited, OSV-gated, injection-hardened web briefs for coding agents. Verified, never raw web.
We read the source, 23 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 raw = await fs.readFile(path.join(dir, 'node_modules', name, 'package.json'), 'utf8')
import { readFileSync, writeFile, mkdirSync, rmSync, rename, readdirSync } from 'node:fs'
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 voyager -- npx -y @dir-ai/voyager
{
"mcpServers": {
"voyager": {
"args": [
"-y",
"@dir-ai/voyager"
],
"command": "npx"
}
}
}
[mcp_servers.voyager]
command = "npx"
args = ["-y", "@dir-ai/voyager"]
{
"mcpServers": {
"voyager": {
"args": [
"-y",
"@dir-ai/voyager"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"voyager": {
"args": [
"-y",
"@dir-ai/voyager"
],
"command": "npx"
}
}
}
Evidence-gated verification, selection, and measurement MCP for coding agents.
Roslyn-powered C# code navigation, blast-radius analysis, and verified edits for coding agents.
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
Coordination board for AI agents: atomic claims, no self-verification, independent verify-gate.
The API-change deploy gate for AI coding agents. Read-only breaking-change detection.
Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.
Verified brand claims with receipts for agent commerce. Ranking is never paid; the engine is open.
Answers built from our own checks of this server.