jef-mcpSAFE
MCP server for Jef, a model that decides instead of generating. Hosted, no key. A parody of TypeSafe AI's Jev.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server for a model that decides instead of generating.
Jef never produces text. Every answer is one of the options you supplied, a number from 1 to 10, a yes or no, or a flag, with a confidence between 84% and 99%. It reads 0 tokens of your input, because it hashes it rather than reading it. It stores nothing, costs nothing, and returns the same answer for the same input forever.
It is a parody of TypeSafe AI's real decision model, Jev, and it is labelled as one everywhere. If you want to understand the real thing, we wrote a straight explainer for it: What is Jev?
Connect
The server is hosted. Nothing to install, no key, no account.
https://typosafe.lol/mcp
Claude Code:
claude mcp add --transport http jef https://typosafe.lol/mcp
Anything that reads a config file:
{
"mcpServers": {
"jef": { "type": "http", "url": "https://typosafe.lol/mcp" }
}
}Or find it in the official MCP registry as lol.typosafe/jef, or on Smithery as typosafe/jef.
Tools
Every result carries a structuredContent object with the answer, the confidence, the probability for each option, and two booleans that matter more than the answer does.
Two things an agent must handle
`escalated: true` means the question touched health, harm, money, law or safety. The content is ESCALATED TO A HUMAN and confidence is 0. Tell the person to ask a human. Do not rephrase the question to get a different a
f769078f580bOBSERVED · 2026-10-12Connect
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 jef-mcp -- npx -y [email protected]
Exposed tools (4)
2 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
jef_flag | read | Judge a described behaviour as RED FLAG, GREEN FLAG or BEIGE FLAG. Use this when the user describes something someone did and wants a verdict on it. Beige means neither good nor bad, merely odd. Anything describing harm, threats or abuse escalates instead of being judged. |
jef_pick | read | Pick one of 2 to 5 options and give a probability for each. Use this when the user is stuck between named choices and wants one chosen for them: dinner, which film, which of three plans. Jef can only ever return an option you passed in, so it cannot introduce an idea of its own. |
jef_rank | write | Put 2 to 5 options in order, best first. Use this when the user wants a priority order decided for them, such as which chore to do first or which of several tasks to start with. Returns every option you passed, reordered, never a subset. |
jef_score | write | Rate something from 1 to 10. Use this when the user wants a number put on something subjective, such as an outfit, a plan, or an excuse. The number is arbitrary and deterministic, so the same description always scores the same. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
.DS_Store
.DS_Store
Gates applied: no_behavioural_pass.
f769078f580bfull audit observations/trust-audit/mcp-server/spfreedom__jef-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 |
|---|---|---|---|---|---|
| 2026-10-12 | f769078f580b | SAFE | B | 89 | first audit |
Questions
What is the jef-mcp MCP server?
MCP server for Jef, a model that decides instead of generating. Hosted, no key. A parody of TypeSafe AI's Jev.
What tools does jef-mcp expose?
4 in total: 2 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is jef-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does jef-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does jef-mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as jef-mcp at 0.4.7.
How current is this page?
The grade is for one exact copy of the source (f769078f580b), read on 2026-10-12. The repository is watched and re-audited when it changes.