Aletheia Aegis Output Guard & Eval Harness

● Active

io.github.vikasny30/aletheia-aegis

Output guard that checks model replies before they reach the user; optional model judge

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "aletheia-aegis": {
      "command": "npx",
      "args": [
        "-y",
        "aletheia-aegis@0.3.0"
      ]
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add aletheia-aegis -- npx -y aletheia-aegis@0.3.0
OpenAI Codex CLI
codex mcp add aletheia-aegis -- npx -y aletheia-aegis@0.3.0
VS Code
code --add-mcp '{"name":"aletheia-aegis","type":"stdio","command":"npx","args":["-y","aletheia-aegis@0.3.0"]}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Other
Version
0.3.0
Registry
active
Published
11/21/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Aletheia Aegis Output Guard & Eval Harness is maintained, open source.

Maintained
Active
Last commit today (Nov 22, 2026), 3 open issues.
Official registry
Active
Published as io.github.vikasny30/aletheia-aegis in the official MCP registry, version 0.3.0.
Source
Open source, Apache-2.0
Public repository under the Apache-2.0 licence, 2 stars, 0 forks.
Runs
On your machine
A local npm package started by your client; it can reach whatever your user account can.
Credentials
None declared
The registry entry declares no required environment variables.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself.

On GitHub

read Nov 22, 2026
Stars
2
Forks
0
Last push
Nov 22, 2026
License
Apache-2.0

TypeScriptagentic-aiai-safetyeval-harnessguardrailsinference-safetyinference-time-safetyllm-safetymcpmcp-servermodel-context-protocoloutput-guardresponsible-ai

From the README

Aletheia Aegis: Inference-Time Output Enforcement for Autonomous Agents A deterministic, sub-millisecond inference-time guard for model outputs. Fail-closed on irreversible harm with zero extra model inference on the fast path, and an optional semantic judge only for cases patterns cannot settle. Aegis is the output plane of the Aletheia safety framework. It inspects generated text before it reaches a user, blocks credential leaks and life-safety failures outright, and flags everything else for audit or disclaimer. It runs offline by default, on CPU, with no response text retained. Ships as an MCP server, TypeScript SDK, and CLI. Version 0.3.0. Apache 2.0. TypeScript, Node.js 18/20/22. Why Aegis exists Built for platform, security, and AI infrastructure teams deploying tool-using agents into regulated or high-throughput production environments. Production agents need safety that does not break the product. The common approach, running a second LLM as judge on 100 percent of outbound traffic, fails on three counts at scale: 1. Latency. A 1,000 to 4,000 ms penalty per turn breaks streaming and multi-step agentic loops. 2. Cost. A secondary frontier model on every payload turns safety into a cost center, roughly $0.002 to $0.02 per evaluation, tens of thousands of dollars monthly at scale. 3. Reliability.…

Read the full README on GitHub →

Alternatives to Aletheia Aegis Output Guard & Eval Harness

All Aletheia Aegis Output Guard & Eval Harness alternatives →Best Other servers →

The most-starred Other servers in the index, with their live-check result.

ServerStarsLast pushLive check
Labelhead Artist Momentum114,594Nov 2026Working
World Monitor91,002Nov 2026Needs sign-in
Tldraw51,470Nov 2026Working
OpenSEO28,515Nov 2026Needs sign-in
Windows MCP11,833Nov 2026Local / not checked

Aletheia Aegis Output Guard & Eval Harness: questions people ask

Is Aletheia Aegis Output Guard & Eval Harness a remote or a local MCP server?
According to its entry in the official MCP registry, Aletheia Aegis Output Guard & Eval Harness ships as a local package (npm) that your client starts on your machine.
Is Aletheia Aegis Output Guard & Eval Harness safe to use?
Looks healthy: Aletheia Aegis Output Guard & Eval Harness is maintained, open source. In detail — maintained: Active; official registry: Active; source: Open source, Apache-2.0; runs: On your machine; credentials: None declared. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Aletheia Aegis Output Guard & Eval Harness still maintained?
Active: the repository's last commit today. Last push Nov 22, 2026, 2 GitHub stars, Apache-2.0 licence. Read from GitHub on Nov 22, 2026.
How do I add Aletheia Aegis Output Guard & Eval Harness to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
  1. Aletheia Runtime Safety & Scope Creep FilterDeterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls★ 12
Browse all Other →

Add the badge to your site

Show visitors that Aletheia Aegis Output Guard & Eval Harness is listed here — it’s also the link we check for a free listing.

Aletheia Aegis Output Guard & Eval Harness — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-vikasny30-aletheia-aegis?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Aletheia Aegis Output Guard & Eval Harness — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Aletheia Aegis Output Guard & Eval Harness — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-vikasny30-aletheia-aegis?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/io-github-vikasny30-aletheia-aegis) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/io-github-vikasny30-aletheia-aegis) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/io-github-vikasny30-aletheia-aegis)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/io-github-vikasny30-aletheia-aegis"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-vikasny30-aletheia-aegis"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-vikasny30-aletheia-aegis"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).