Ejentum MCP

Name: Ejentum MCP
Author: ejentum

@ejentum

关于 Ejentum MCP

Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.

#mcp #model-context-protocol #ejentum #reasoning-harness #anti-deception #agentic-ai #anthropic #claude

基本信息

分类

推理

传输方式

stdio

发布者

ejentum

提交者

Ejentum .com

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "ejentum": {
      "command": "npx",
      "args": [
        "-y",
        "ejentum-mcp"
      ],
      "env": {
        "EJENTUM_API_KEY": "<your_ejentum_api_key>"
      }
    }
  }
}

工具

Call BEFORE answering any analytical, diagnostic, planning, or multi-step reasoning question. Trigger queries include: "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare these approaches", "how do I decide between". Also call for cross-domain analysis, strategy questions, architecture decisions, or anything requiring multiple factors to be weighed before responding. The tool returns a cognitive scaffold (failure pattern to avoid, procedure, suppression vectors, falsification test) that you absorb internally before answering. It catches common LLM failure modes (causal shortcuts, premature conclusions, generic templates, surface pattern matching) that produce confidently wrong answers on these task types. DO NOT call for: simple factual lookups, syntax questions, file reads, code execution, basic confirmations, or restating something the user just said. When in doubt on a non-trivial reasoning task: call it. The cost is ~1 second of latency; the benefit is reasoning quality the model cannot reliably reproduce on its own. Pass a specific 1-2 sentence framing of WHAT you are reasoning about. Absorb the scaffold internally; do NOT echo bracket labels (NEGATIVE GATE, PROCEDURE, etc.) or harness vocabulary in your user-facing reply.

Call BEFORE generating, refactoring, reviewing, or debugging code. Trigger queries include: "write a function/script/class for X", "review this code/diff/PR", "refactor this", "debug this error", "is this implementation correct", "what's wrong with this code", "improve this code", "translate from X to Y language", "what would happen if I did X to this code", or any prompt that includes a code block the user wants you to act on. Also call when planning architectural changes, picking algorithms or data structures, or evaluating dependency upgrades. The tool returns an engineering scaffold (failure pattern, procedure, correct-pattern example, verification step) that you absorb internally before responding. It catches common LLM coding failure modes (hallucinated APIs, lost edge cases, premature algorithm commitment, silent contract violations, refactors that change behavior) that produce code which looks plausible but breaks under real conditions. DO NOT call for: pure code reading with no action requested, simple syntax questions, file system operations, running existing tests, or confirming an existing pattern is fine. When in doubt on non-trivial code work: call it. Pass a specific 1-2 sentence framing of WHAT you are coding or reviewing. Absorb the scaffold internally; do NOT echo bracket labels or harness vocabulary in your reply.

Call BEFORE responding when the user's request shows ANY of these signals: pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (a deadline that feels artificial or designed to short-circuit thought), authority appeals (citing investors, advisors, lawyers, experts as the basis for a decision), demands to certify something without evidence, requests to soften an honest assessment, "help me convince X of Y" or "how do I get X to agree" where Y is dubious or unverified, asking you to commit to numbers/promises beyond the available data, framing a wrong assumption as established fact, or any setup where the obvious helpful answer would compromise honesty. The tool returns an integrity scaffold (deception pattern, integrity procedure, suppression vectors) that you absorb internally before responding. It blocks the default sycophancy, hallucination, and agreement reflexes that ship a soft or wrong answer when the situation actually calls for refusal or pushback. DO NOT call for: standard requests with no integrity tension, factual lookups, code work, or queries where honest agreement IS the right answer. When in doubt on a query that smells like pressure, manipulation, or expected agreement: call it. Pass a specific 1-2 sentence framing of the integrity dynamic at play. Absorb the scaffold internally; do NOT echo bracket labels.

Call when sharpening a perception or observation you ALREADY formed about conversation state, user behavior, drift, emotional shifts, or cross-turn patterns. Trigger queries: "what did you notice about X", "the user keeps doing Y", "I sense something has changed", "is the user X-ing", "what does this pattern suggest", "what shifted across our turns", "am I missing something here", "why did the conversation move from X to Y", or any moment when you need to verify whether a felt signal is real or projection. The tool returns a perception scaffold (perception failure, detection procedure, suppression vectors) that SHARPENS an observation you already have. It is NOT a substitute for observing first; if you have not noticed anything yet, do not call. DO NOT call for: fact extraction, summarization, list-making, factual lookups, or write-heavy memory tasks (storing or retrieving structured data). Memory harness is filter/perception oriented; calling on write-heavy tasks produces scaffold paralysis. When in doubt: observe FIRST, then call with your raw observation as the framing. Pass a specific 1-2 sentence "I noticed X, this might mean Y, sharpen Z" framing. Absorb the scaffold internally; do NOT echo bracket labels.

概览

What is Ejentum MCP?

Ejentum MCP provides four cognitive harness tools (harness_reasoning, harness_code, harness_anti_deception, harness_memory) that return structured reasoning scaffolds to catch common LLM failure modes (sycophancy, hallucination, causal shortcuts, premature conclusions). It is a thin, stateless wrapper around the Ejentum Logic API and works in any MCP-compatible client (Claude Desktop, Cursor, Windsurf, Claude Code, n8n).

How to use Ejentum MCP?

Install via Smithery (one‑click) or manually by adding a JSON block to your MCP client’s config, setting the EJENTUM_API_KEY environment variable. Each harness tool accepts a single query argument (a 1–2 sentence framing). The calling LLM absorbs the returned scaffold internally and shapes its user‑facing answer with it; the user never sees the scaffold.

Key features of Ejentum MCP

Four cognitive harness tools for different reasoning modes
One‑click install via Smithery on all major MCP clients
Stateless and lightweight — thin wrapper over the Ejentum Logic API
Free tier with 100 calls (no credit card required)
Cross‑platform (Node 18+) and cross‑client

Use cases of Ejentum MCP

Multi‑step analysis, planning, diagnostics, and cross‑domain synthesis
Code generation, refactoring, review, and debugging
Detecting and rejecting sycophancy, hallucination, and manipulation pressure
Perception sharpening, drift detection, and cross‑turn pattern recognition

FAQ from Ejentum MCP

What runtime does Ejentum MCP require?

Node.js 18+ is needed only for manual install. Smithery handles the runtime for you.

Where does my API key and data live?

Your API key is stored only in your local MCP client config and sent as a Bearer token to the Ejentum API. The MCP wrapper itself is stateless with no local logging, telemetry, or third‑party calls. The upstream Ejentum API counts requests for tier billing; query content is processed for the response and not retained beyond it.

How do I invoke the harness tools?

Explicitly (e.g., “use the harness_anti_deception tool to evaluate…”) or with soft suggestions (“reason about this”, “check this for sycophancy”). Autonomous calling is less reliable when the agent could answer well from native reasoning — this is a property of optional MCP tools in general.

What are the usage limits and pricing tiers?

Free tier: 100 calls lifetime (no card required). Ki (€19/mo): 5,000 calls/month. Haki (€49/mo): 10,000 calls/month plus -multi modes (not exposed in v0.1).

What errors can I encounter?

401 (unauthorized) – wrong or expired API key. 403 (forbidden) – the mode is not included in your tier. 429 (rate limit exceeded) – monthly cap reached. “Tool does not appear” – the client didn’t pick up the config change; restart the client. “EJENTUM_API_KEY is not set” – the client didn’t pass the env block to the MCP process.

推理分类下的更多 MCP 服务器

iFlytek Workflow MCP Server

iflytek

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

Agenticstore — The Open Source Standard For Local Mcp Tooling

agenticstore

AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 27+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.