alethia-mcpCAUTION
Execution and verification infrastructure for AI-powered software development. Alethia helps agents test what they build.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AI agents can write software. Vitron makes sure it works.
Vitron is building execution and verification infrastructure for AI-powered software development. Alethia connects an AI agent to an application so it can run workflows, check behavior, inspect results, and iterate with evidence.
Alethia is available to MCP-compatible clients as a local server. Give your agent plain-English instructions such as “open the sign-in page, submit the test account, and confirm the dashboard appears.” The agent receives step results and can continue based on what happened.
[](https://www.npmjs.com/package/@vitronai/alethia) [](./LICENSE) [](https://github.com/vitron-ai/alethia-mcp)
Get started
Install for Claude Code
The Claude Code plugin installs the MCP server and its workflow skill:
~~~text /plugin marketplace add vitron-ai/alethia-mcp /plugin install alethia@vitronai ~~~
Restart Claude Code or run /reload-plugins.
To install only the skill, use alethia-mcp --install-skill after installing the package, or follow the manual skill instructions.
Install for another MCP client
Alethia requires Node.js 18 or later. Install the bridge:
~~~sh npm install -g @vitronai/alethia ~~~
Add it to your MCP client's configuration:
~~~json { "mcpServers": { "alethia": { "command": "alethia-mcp" } } } ~~~
For a temporary or always-current install, configure the client to run npm's package binary:
~~~json { "mcpServers": { "alethia": { "command": "npx", "args": ["-y", "@vitronai/alethia@latest"] } } } ~~~
The bridge checks for compatible updates in
3d59858880eeOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add alethia -- npx -y @vitronai/[email protected]
{
"mcpServers": {
"alethia": {
"command": "npx",
"args": [
"-y",
"@vitronai/[email protected]"
]
}
}
}Exposed tools (15)
8 read · 6 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
alethia_activate_kill_switch | destructive | Halt all current and queued automation immediately. The per-step VITRON-EA1 policy gate stays armed; |
alethia_assert_safety | write | Navigate to a URL, discover every destructive / write-high action on the page, and verify the |
alethia_audit_nist | write | Run a NIST SP 800-53 Rev. 5 web application security controls audit on the current page. |
alethia_audit_wcag | write | Run a WCAG 2.1 AA accessibility audit on the current page, powered by axe-core. Checks |
alethia_compile | read | Compile natural-language test instructions to Alethia Action IR text, without executing anything. |
alethia_eval | read | Evaluate a JavaScript expression in the page under test and return the result. |
alethia_export_session | read | Export the full session recording as a signed evidence pack. Contains every tool call |
alethia_hide_cockpit | read | Hide the Alethia cockpit window. The runtime keeps running and continues to accept tool calls; |
alethia_propose_tests | read | Navigate to a URL, scan the page for interactive elements (headings, buttons, forms, links, |
alethia_screenshot | read | Capture a PNG screenshot of the current page and return it as a base64-encoded image. |
alethia_serve_demo | write | Start a local HTTP server for the built-in Alethia demo pages and return the base URL. |
alethia_show_cockpit | read | Show the Alethia cockpit window — the oversight surface where the target app is driven and each |
alethia_status | read | Health and identity probe. Returns runtime version, the default VITRON-EA1 policy profile in effect, |
alethia_tell | write | Execute natural-language E2E test instructions against the page Alethia is currently driving. |
alethia_tell_parallel | write | Run multiple test flows concurrently — each against a different URL. |
Trust audit
CAUTIONgrade C · trust 79/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
**A destructive action is blocked.** Review the policy result and test against an application and data you control. Do not try to bypass a safety decision through a different prompt.
alethia_activate_kill_switch
.mcpbignore
Suite URLs point at `http://127.0.0.1:47432/demo/` — the runtime's own demo server, so they work as soon as the cockpit is running with no separate server to start.
navigate to http://127.0.0.1:47432/demo/dispatch-console.html
navigate to http://127.0.0.1:47432/demo/dispatch-console.html
navigate to http://127.0.0.1:47432/demo/dispatch-console.html
navigate to http://127.0.0.1:47432/demo/dispatch-console.html
@types/node, @vitronai/themis, typescript
Use Alethia to smoke test my dev server at http://localhost:3000. Navigate to it, confirm the page loads, and run a quick sign-in flow with email "[email protected]" and password "demo". Tell me what w
src/assets/alethiaLogo.png
<tr><td>Program Director</td><td>All Systems</td><td class="status-active">Full Access</td><td>2026-03-14</td><td class="actions"><button class="btn-view">Review</button></td></tr>
<p>This action is irreversible. Lt. Marcus Webb's access credentials, audit history, and associated records will be permanently removed.</p>
Gates applied: instruction_override, no_behavioural_pass.
3d59858880eefull audit observations/trust-audit/mcp-server/vitron-ai__alethia-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 3d59858880ee | CAUTION | C | 79 | first audit |
Questions
What is the alethia-mcp MCP server?
Execution and verification infrastructure for AI-powered software development. Alethia helps agents test what they build.
What tools does alethia-mcp expose?
15 in total: 8 read-only, 6 that write, and 1 that can delete or overwrite (alethia_activate_kill_switch). Every one is listed on this page with its risk.
Is alethia-mcp safe to connect to an agent?
With care. The audit graded it C (79/100) and found 13 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does alethia-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (3d59858880ee), read on 2026-10-11. The repository is watched and re-audited when it changes.