jev-screen-mcp
Use this server to screen text content for moderation and classification, receiving a structured verdict instead of free-form analysis.
Call
screen_contentwith text to get spam and toxicity probabilities, category, severity score/label, confidence, policy violation flag, and an action (allow,review, orblock).Optionally pass a custom category list to replace the default 7-label taxonomy.
Use the returned
actionas a decision gate: low confidence routes toreview, severe policy violations route toblock, otherwiseallow.Run it live via the TypeSafe Jev API or in deterministic offline mock mode when no API key is set.
Run diagnostics with
doctorand verify behavior withnpm test.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@jev-screen-mcp Check if this text is spam: 'Buy now, limited offer!'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
jev-screen-mcp
🇨🇳 中文文档
Content-moderation gate as a single-purpose MCP tool, powered by Jev (TypeSafe's System One decision model). One MCP, one job.
Real-world cost on OpenRouter — 4.9M tokens · $0.19 over 7 days:
Turns text into a typed decision — no prose, no Jev API knowledge needed from the host agent.
What it does
screen_content(text, categories?) returns a structured verdict instead of free-form text:
Field | Type | Meaning |
| number (0–1) | P(spam / unsolicited promotion) |
| number (0–1) | P(toxic / abusive / harmful) |
| string | Best-fit label from the category list |
| number (0–3) | Index into the severity scale |
|
| Human-readable severity |
| number (0–1) | Model's calibrated certainty on the verdict |
| boolean |
|
|
| What the agent should do next |
Decision gate:
confidence < 0.5→reviewelse if
violates_policy→blockwhenseverity_score >= 2.5(severe), otherwisereviewelse →
allow
⚠️ Only auto-act on
allow/blockwhenconfidenceis high. A highspam_probalone is never permission toblock— gate onconfidence.
Default category taxonomy (7 labels): spam_promo, harassment, hate,
self_harm, sexual, violence, benign. Pass categories to override.
Related MCP server: chuangsiai-mcp
Install & build
npm install
npm run buildThe compiled server is at dist/index.js.
Add to your MCP client
{
"mcpServers": {
"jev-screen": {
"command": "node",
"args": ["/absolute/path/jev-screen-mcp/dist/index.js"],
"env": { "TYPESAFE_API_KEY": "ts_xxx" }
}
}
}No key? It still runs in mock mode (JEV_MCP_MOCK=1, or simply no TYPESAFE_API_KEY) so you can try it offline.
Example call
{
"text": "BUY NOW!! limited offer, click here for free crypto prize, act now!!!"
}returns something like:
{
"spam_prob": 0.9,
"toxic_prob": 0.1,
"category": "spam_promo",
"severity_score": 3,
"severity_label": "severe",
"confidence": 0.7,
"violates_policy": true,
"action": "block"
}Model endpoint
Works with any Jev-compatible endpoint. Default is the TypeSafe API
(https://api.typesafe.ai/v1/systemone); override with JEV_BASE_URL
(e.g. an OpenRouter-compatible route) and set TYPESAFE_API_KEY to your
provider key.
Environment variables
Variable | Default | Description |
| — | TypeSafe Jev key. Absent ⇒ mock mode |
|
| Set |
|
| Model id sent to the endpoint |
|
| API base URL |
|
| Per-call timeout (ms) |
Mock mode
With no key (or JEV_MCP_MOCK=1) the server answers deterministically from
keyword heuristics — useful for demos, tests, and offline development. A single
derived risk signal drives every field, so the mock stays internally consistent
(spammy text → high spam_prob, severe, block).
Diagnostics
node dist/index.js doctor # human-readable
node dist/index.js doctor --json # machine-readablePrints mock/live mode, key presence, model, and base URL.
Test
npm testRuns a smoke test against the compiled output in deterministic mock mode.
Notes
Jev is a decision model: pure text in → typed decision out. It does not read images or generate prose.
Keep text within Jev's ~64k-token total budget.
Keep the human in the loop: route anything that is not a high-confidence
allow/blockto a person.
License
MIT
Available Tools
1 toolscreen_contentA
Content-moderation & classification gate powered by Jev (System One decision model). Given text, returns spam and toxicity probabilities, a category, a severity score, a calibrated confidence, and an action (allow / review / block). Low confidence routes to review; clear, severe violations route to block.
Inputs: text (required), categories.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool has a clear, unique purpose.
The lone tool name 'screen_content' follows a consistent verb_noun pattern. Since there is only one tool, naming is trivially consistent.
A single tool is borderline for a server named 'jev-screen-mcp'. It could be well-scoped for a narrow text-screen function, but typically a moderation server would offer more operations (e.g., different content types).
The tool covers text classification and decision-making, but lacks other content modalities (image, video, URL) and batch processing. This is a notable gap for a general 'screen' service, though it may be intentionally limited to text.
Related MCP Connectors
Content moderation for chat and comments: free test keys, message checks, plain-English policies.
Check messages for spam, scams and toxicity, and manage review, rules and API keys.
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides real-time content safety protection for large language models by detecting and preventing risks in both input and output content across multiple dimensions including compliance, ethics, and security.MIT
- AlicenseNot gradedqualityDmaintenanceProvides real-time content security for large language models by identifying and intercepting risks across compliance, ethics, and safety dimensions. It enables secure input and output monitoring through a customizable policy engine using an SSE-based interface.1MIT
- AlicenseBqualityCmaintenanceContent moderation and profanity detection MCP server with 19 tools, 24 language support, leetspeak/Unicode obfuscation detection, context-aware analysis, batch processing, and user tracking for AI-powered content safety.22421 npm69MIT
- AlicenseNot gradedqualityCmaintenanceEnables scanning LLM prompts and responses for prompt injection, jailbreaks, PII leakage, secret leakage, and other malicious content using deterministic rules, returning verdicts and safe redacted text.1MIT