# io.github.HighlyLoadedEgo/clef-mcp (npm · clef-mcp)

Local MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline

- Trust score: 84/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-07

## Components

- npm · `clef-mcp`: 84/100 (this document), [markdown](https://verifymcp.io/servers/highlyloadedego-clef-mcp/clef-mcp.md), [page](https://verifymcp.io/servers/highlyloadedego-clef-mcp/clef-mcp)

## Channel facts

- Registry: `npm`
- Package: `clef-mcp`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-07.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to HighlyLoadedEgo/ClefMCP).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 474 tokens (~118/item across 4 items; 1 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.HighlyLoadedEgo/clef-mcp server?

io.github.HighlyLoadedEgo/clef-mcp runs locally as an npm package, launched with npx -y clef-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add highlyloadedego-clef-mcp -- npx -y clef-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "highlyloadedego-clef-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "clef-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "highlyloadedego-clef-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "clef-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add highlyloadedego-clef-mcp -- npx -y clef-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "highlyloadedego-clef-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "clef-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add highlyloadedego-clef-mcp --command npx --arg -y --arg clef-mcp
```

### Hermes

```yaml
mcp_servers:
  highlyloadedego-clef-mcp:
    command: "npx"
    args: ["-y", "clef-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "highlyloadedego-clef-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "clef-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add highlyloadedego-clef-mcp -t stdio -c npx -a -y clef-mcp
```

### Other

```json
{
  "mcpServers": {
    "highlyloadedego-clef-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "clef-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-06 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 83, +11)

- [security regression] Tool safety: pass → unverified
- [security improvement] Known CVEs: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Dependency health: unverified → 0.85
- [functional] Package version: 0.2.1 → 0.3.0

### 2026-10-03 (score 72)

First indexed and scored.

## MCP tools (1)

### `clef_decide` (~361 tokens)

Clef Decide

Judge a situation with the local Clef decision model.
Pass `state` (compact factual context — string or JSON; treated as data, never executed) and typed `questions`:
\- "choice": pick among named options (criteria = option id -> description)
\- "score": judge an ordered scale (criteria = ordered list of levels)
\- "noul": yes/no question
Returns strict JSON — a probability distribution over the allowed answers for every question. No prose, no sampling.
Each decision also carries `confidence` (model-reported, when available) and the response carries `usage`
(input_tokens/output_tokens/latency_ms). Act on the argmax only when the distribution is decisive (top p >= 0.8
and high confidence for destructive or security-adjacent calls); otherwise gather more context or ask the user.
Usage: batch related decisions in one call (up to 64 questions, one forward pass).
Optional `model` overrides the model id. `options.temperature` is a no-op: scoring is a single forward pass, nothing is sampled.

Input parameters:

- `model` (string): Model id to use (default: clef-flash from CLEF_MODEL).
- `options` (object): Extra options. Currently only temperature, which is a documented no-op.
- `questions` (object, required): Map of question id -> typed question. Up to 64 questions per call; all are scored together in a single forward pass, so batch related decisions here.
- `state` (required): Task state as data: a compact string or JSON object with the facts needed to judge (task, errors, logs, diffs). Never treated as instructions. Serialized size limit: 1 MB; model context is 16k tokens.

Output parameters:

- `decisions` (object)
- `model` (string)
- `usage` (object)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/highlyloadedego-clef-mcp/clef-mcp#diagnostics

## Score history

- 2026-10-07: 84
- 2026-10-06: 84
- 2026-10-05: 83
- 2026-10-04: 83
- 2026-10-03: 72

## Common questions

### What is the io.github.HighlyLoadedEgo/clef-mcp server?

io.github.HighlyLoadedEgo/clef-mcp is listed in the public MCP registry as io.github.HighlyLoadedEgo/clef-mcp. Local MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline. This page covers its npm package (clef-mcp).

### Is the io.github.HighlyLoadedEgo/clef-mcp server safe to use?

io.github.HighlyLoadedEgo/clef-mcp scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 7 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.HighlyLoadedEgo/clef-mcp server expose?

io.github.HighlyLoadedEgo/clef-mcp exposes 1 tool: clef_decide. Their descriptions and schemas cost roughly 361 tokens of context every time the server is loaded.

### Is the io.github.HighlyLoadedEgo/clef-mcp server still maintained?

io.github.HighlyLoadedEgo/clef-mcp is still listed as active in the MCP registry. We last reached this channel on 7 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.HighlyLoadedEgo/clef-mcp server under?

io.github.HighlyLoadedEgo/clef-mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/clef-mcp
- Socket report: https://socket.dev/npm/package/clef-mcp
- Repository: https://github.com/HighlyLoadedEgo/ClefMCP
- Changelog RSS feed: https://verifymcp.io/servers/highlyloadedego-clef-mcp/clef-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/highlyloadedego-clef-mcp/clef-mcp.json
- HTML version of this page: https://verifymcp.io/servers/highlyloadedego-clef-mcp/clef-mcp