Elenchus MCP Server

English | 한국어

Adversarial Code Verification System using Verifier↔Critic Debate Loop

Elenchus (ἔλεγχος): Socrates' method of refutation through systematic questioning - exposing contradictions to reach truth.

Table of Contents

• Overview
• Key Features
• Quick Start
• Installation
• Usage
• MCP Tools Reference
• MCP Resources
• MCP Prompts
• Verification Modes
• Automatic Verification
• Issue Lifecycle
• Convergence Detection
• Token Optimization
• Configuration
• Architecture
• Security
• Troubleshooting
• Development
• License

Overview

Elenchus is a Model Context Protocol (MCP) server that implements adversarial code verification. Unlike simple linting or static analysis, Elenchus orchestrates a debate between Verifier and Critic agents to systematically uncover issues through dialectical reasoning.

Why Adversarial Verification?

The Verifier↔Critic Loop

┌──────────────────────────────────────────────────────────────┐
│                    VERIFICATION LOOP                          │
├──────────────────────────────────────────────────────────────┤
│  Round 1: Verifier → Examines code, RAISES issues            │
│  Round 2: Critic   → Challenges issues (VALID/INVALID/PARTIAL)│
│  Round 3: Verifier → Defends, resolves, or finds new issues  │
│  Round 4: Critic   → Re-evaluates, checks coverage           │
│  ...continues until convergence...                            │
│  Final: Verdict (PASS / FAIL / CONDITIONAL)                  │
└──────────────────────────────────────────────────────────────┘

Key Features

🔄 Adversarial Debate System

• Verifier: Finds issues with evidence
• Critic: Challenges findings, validates claims
• Role Enforcement: Strict alternation with compliance scoring

📊 Intent-Based Convergence

• Semantic understanding instead of keyword matching
• 5 category coverage (Security, Correctness, Reliability, Maintainability, Performance)
• Edge case documentation requirements
• Negative assertions for clean code

🔍 Automatic Impact Analysis

• Dependency graph construction
• Ripple effect prediction
• Cascade depth calculation
• Risk level assessment

💾 Session Management

• Checkpoint/rollback support
• Global session storage
• Audit trail preservation

⚡ Token Optimization (Optional)

• Differential analysis (verify only changed code)
• Response caching
• Selective chunking
• Tiered verification pipeline

Quick Start

Add to your MCP client configuration:

{
  "mcpServers": {
    "elenchus": {
      "command": "npx",
      "args": ["-y", "@jhlee0409/elenchus-mcp"]
    }
  }
}

Then use naturally with your AI assistant:

"Please verify src/auth for security issues"

See Installation for client-specific setup instructions.

Installation

Supported Clients

VS Code (GitHub Copilot)

Add to .vscode/mcp.json:

{
  "mcp": {
    "servers": {
      "elenchus": {
        "command": "npx",
        "args": ["-y", "@jhlee0409/elenchus-mcp"]
      }
    }
  }
}

Cursor

Go to Settings > MCP > Add new global MCP Server:

{
  "mcpServers": {
    "elenchus": {
      "command": "npx",
      "args": ["-y", "@jhlee0409/elenchus-mcp"]
    }
  }
}

Usage

Simply describe what you want to verify:

"Verify src/auth for security vulnerabilities"
"Check the payment module for edge cases"
"Review src/api for correctness and reliability issues"

Your AI assistant will automatically use Elenchus tools.

For structured workflows, see MCP Prompts.

MCP Tools Reference

Session Lifecycle

elenchus_start_session

Initialize a new verification session.

Inputs:

• target (string, required): Target path to verify (file or directory)
• requirements (string, required): Verification requirements/focus areas
• workingDir (string, required): Working directory for relative paths
• maxRounds (number, optional): Maximum rounds before stopping (default: 10)
• verificationMode (object, optional): Mode configuration
  • mode: "standard" | "fast-track" | "single-pass"
  • skipCriticForCleanCode: boolean
• differentialConfig (object, optional): Verify only changed files
• cacheConfig (object, optional): Cache previous verifications
• chunkingConfig (object, optional): Split large files into chunks
• pipelineConfig (object, optional): Tiered verification

Returns: Session ID and initial context including files collected, dependency graph stats, and role configuration.

Example:

elenchus_start_session({
  target: "src/auth",
  requirements: "Security audit for authentication",
  workingDir: "/path/to/project",
  verificationMode: { mode: "fast-track" }
})

elenchus_get_context

Get current session context including files, issues, and proactive guidance.

Inputs:

• sessionId (string, required): The session ID

Returns: Files, issues summary, focus areas, unreviewed files, recommendations.

elenchus_submit_round

Submit a Verifier or Critic round.

Inputs:

• sessionId (string, required): The session ID
• role ("verifier" | "critic", required): Role for this round
• output (string, required): Full agent analysis output
• issuesRaised (Issue[], optional): New issues (Verifier role)
• issuesResolved (string[], optional): Resolved issue IDs (Critic role)

Issue Schema:

{
  id: string,
  category: "SECURITY" | "CORRECTNESS" | "RELIABILITY" | "MAINTAINABILITY" | "PERFORMANCE",
  severity: "CRITICAL" | "HIGH" | "MEDIUM" | "LOW",
  summary: string,
  location: string,        // "file:line" format
  description: string,
  evidence: string         // Code snippet or proof
}

Returns: Round number, convergence status, mediator interventions, role compliance score.

elenchus_end_session

End session with final verdict.

Inputs:

• sessionId (string, required): The session ID
• verdict ("PASS" | "FAIL" | "CONDITIONAL", required): Final verdict

Returns: Session summary including total rounds, issues by category and severity.

elenchus_get_issues

Query issues with optional filtering.

Inputs:

• sessionId (string, required): The session ID
• status ("all" | "unresolved" | "critical", optional): Filter by status

Returns: Array of issues matching the filter.

State Management

elenchus_checkpoint

Create a checkpoint for potential rollback.

Inputs:

• sessionId (string, required): The session ID

Returns: Success status and round number.

elenchus_rollback

Rollback to a previous checkpoint.

Inputs:

• sessionId (string, required): The session ID
• toRound (number, required): Round number to rollback to

Returns: Success status and restored round number.

Analysis Tools

elenchus_ripple_effect

Analyze impact of changing a file.

Inputs:

• sessionId (string, required): The session ID
• changedFile (string, required): File that will be changed
• changedFunction (string, optional): Specific function within the file

Returns: Affected files, dependency paths, cascade depth, and recommendations.

Example:

elenchus_ripple_effect({
  sessionId: "...",
  changedFile: "src/auth/login.ts",
  changedFunction: "validateToken"
})
// Returns: { affectedFiles: [...], cascadeDepth: 2, totalAffected: 8 }

elenchus_mediator_summary

Get mediator analysis summary.

Inputs:

• sessionId (string, required): The session ID

Returns: Dependency graph stats, coverage metrics, intervention history.

Role Enforcement

elenchus_get_role_prompt

Get role-specific guidelines.

Inputs:

• role ("verifier" | "critic", required): Role to get prompt for

Returns: System prompt, output template, checklist, mustDo/mustNotDo rules, focus areas.

elenchus_role_summary

Get role compliance summary for a session.

Inputs:

• sessionId (string, required): The session ID

Returns: Compliance history, average scores, violations, current expected role.

elenchus_update_role_config

Update role enforcement settings.

Inputs:

• sessionId (string, required): The session ID
• strictMode (boolean, optional): Reject non-compliant rounds
• minComplianceScore (number, optional): Minimum score (0-100)
• requireAlternation (boolean, optional): Require role alternation

Returns: Updated configuration.

Re-verification

elenchus_start_reverification

Start re-verification of resolved issues from a previous session.

Inputs:

• previousSessionId (string, required): Original session ID
• workingDir (string, required): Working directory
• targetIssueIds (string[], optional): Specific issues to re-verify
• maxRounds (number, optional): Maximum rounds (default: 6)

Returns: New session ID with focused context on target issues.

MCP Resources

Access session data via URI-based resources:

Usage:

Read elenchus://sessions/
Read elenchus://sessions/2026-01-17_src-auth_abc123

MCP Prompts (Slash Commands)

Invocation format varies by client. Check your MCP client's documentation.

Verification Modes

Three modes for different use cases:

Example:

elenchus_start_session({
  target: "src/",
  requirements: "Security audit",
  workingDir: "/project",
  verificationMode: {
    mode: "fast-track",
    skipCriticForCleanCode: true
  }
})

Automatic Verification (MCP Sampling)

Elenchus supports fully automatic verification using MCP Sampling capability. The server autonomously orchestrates the Verifier↔Critic debate loop without manual intervention.

How It Works

┌─────────────────────────────────────────────────────────────┐
│                   AUTOMATIC VERIFICATION                     │
├─────────────────────────────────────────────────────────────┤
│  1. Client calls elenchus_auto_verify                       │
│  2. Server creates session and context                      │
│  3. Server requests Verifier completion via MCP Sampling    │
│  4. Server parses response, extracts issues                 │
│  5. Server requests Critic completion via MCP Sampling      │
│  6. Server parses response, updates issue statuses          │
│  7. Repeat until convergence or max rounds                  │
│  8. Return final result with all issues and fix plan        │
└─────────────────────────────────────────────────────────────┘

Client Requirements

Client Support:

• MCP Sampling capability required
• Check your client's documentation for support

Tool: elenchus_auto_verify

Inputs:

• target (string, required): Target path to verify
• requirements (string, required): Verification requirements
• workingDir (string, required): Working directory
• config (object, optional):
  • maxRounds: Maximum rounds (default: 10)
  • maxTokens: Max tokens per request (default: 4000)
  • stopOnCritical: Stop on CRITICAL issue (default: false)
  • minRounds: Min rounds before convergence (default: 2)
  • enableProgress: Stream progress updates (default: true)
  • modelHint: "fast" | "balanced" | "thorough"
  • includePreAnalysis: Include static analysis (default: true)
  • autoConsolidate: Generate fix plan (default: true)

Returns: Session ID, final status, all issues, and optional consolidated fix plan.

Example:

elenchus_auto_verify({
  target: "src/auth",
  requirements: "Security audit for authentication module",
  workingDir: "/path/to/project",
  config: {
    maxRounds: 10,
    modelHint: "thorough",
    autoConsolidate: true
  }
})

Tool: elenchus_get_auto_loop_status

Inputs:

• sessionId (string, required): Session ID to query

Returns: Current round, status, issues found so far, convergence info.

Comparison: Manual vs Automatic

Issue Lifecycle

Issues transition through states:

RAISED → CHALLENGED → RESOLVED
           ↓
        DISMISSED (false positive)
           ↓
        MERGED (combined)
           ↓
        SPLIT (divided)

Issue States

Critic Verdicts

Convergence Detection

A session converges when ALL criteria are met:

• No CRITICAL or HIGH severity unresolved issues
• Stable for 2+ rounds (no new issues)
• Minimum rounds completed (varies by mode)
• All 5 categories examined
• No recent issue state transitions
• Edge cases documented
• Clean areas explicitly stated (negative assertions)
• High-risk impacted files reviewed

Category Coverage

All 5 categories must be examined:

1. SECURITY - Authentication, authorization, injection
2. CORRECTNESS - Logic errors, type mismatches
3. RELIABILITY - Error handling, resource management
4. MAINTAINABILITY - Code structure, documentation
5. PERFORMANCE - Efficiency, resource usage

Token Optimization

{
  differentialConfig: {
    enabled: true,
    baseRef: "main"  // Compare against main branch
  }
}

{
  cacheConfig: {
    enabled: true,
    ttlSeconds: 3600  // Cache for 1 hour
  }
}

{
  chunkingConfig: {
    enabled: true,
    maxChunkSize: 500  // Lines per chunk
  }
}

{
  pipelineConfig: {
    enabled: true,
    startTier: "quick"  // quick → standard → deep
  }
}

Configuration

Environment Variables

Storage Location

Sessions and data are stored in a client-agnostic location:

~/.elenchus/
├── sessions/          # Verification sessions
├── baselines/         # Differential analysis baselines
├── cache/             # Response cache
└── safeguards/        # Quality safeguards data

Priority Order:

1. $ELENCHUS_DATA_DIR - Explicit override
2. $XDG_DATA_HOME/elenchus - XDG spec
3. %LOCALAPPDATA%\elenchus - Windows
4. ~/.elenchus - Default fallback

Custom Storage

# Set custom location
export ELENCHUS_DATA_DIR=/path/to/custom/storage

# Or use XDG spec
export XDG_DATA_HOME=~/.local/share

Session Cleanup

Sessions are preserved as audit records. Manual cleanup:

rm -rf ~/.elenchus/sessions/*
# Or for specific sessions
rm -rf ~/.elenchus/sessions/2026-01-17_*

Architecture

┌─────────────────────────────────────────────────────────────────────┐
│                       ELENCHUS MCP SERVER                            │
├─────────────────────────────────────────────────────────────────────┤
│                                                                      │
│  ┌──────────────────────────────────────────────────────────────┐  │
│  │                     MCP PROTOCOL LAYER                        │  │
│  │  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────────┐ │  │
│  │  │  Tools   │  │Resources │  │ Prompts  │  │ Notifications│ │  │
│  │  │  (18)    │  │  (URI)   │  │   (6)    │  │  (optional)  │ │  │
│  │  └────┬─────┘  └────┬─────┘  └────┬─────┘  └──────────────┘ │  │
│  └───────┼─────────────┼─────────────┼──────────────────────────┘  │
│          │             │             │                              │
│  ┌───────┴─────────────┴─────────────┴──────────────────────────┐  │
│  │                       CORE MODULES                            │  │
│  │  Session Manager │ Context Manager │ Mediator System          │  │
│  │  Role Enforcement │ Issue Lifecycle │ Pipeline (Tiered)       │  │
│  └───────────────────────────────────────────────────────────────┘  │
│                              │                                       │
│                              ▼                                       │
│                    ┌──────────────────┐                             │
│                    │     STORAGE      │                             │
│                    │ ~/.elenchus/     │                             │
│                    └──────────────────┘                             │
└─────────────────────────────────────────────────────────────────────┘

Module Responsibilities

Security

Security Model

Elenchus operates with the following security considerations:

• No Code Execution: Elenchus does NOT execute the code it verifies. It performs static analysis only.
• Local Storage: All session data is stored locally in ~/.elenchus/. No data is sent to external servers.
• Path Validation: All file paths are validated to prevent path traversal attacks.
• No Secrets in Output: Tool outputs are sanitized to avoid exposing sensitive data.

Permissions

Elenchus requires:

• Read access to target files for verification
• Write access to ~/.elenchus/ for session storage

Reporting Security Issues

Please report security vulnerabilities via GitHub Security Advisories.

Troubleshooting

Common Issues

Debugging

Use MCP Inspector for debugging:

npm run inspector
# or
npx @modelcontextprotocol/inspector node dist/index.js

Getting Help

• Issues: GitHub Issues
• Discussions: GitHub Discussions

Development

Build Commands

npm run build      # Compile TypeScript to dist/
npm run dev        # Watch mode with auto-rebuild
npm run start      # Run the compiled server
npm run inspector  # Launch MCP Inspector for debugging

Project Structure

elenchus-mcp/
├── src/
│   ├── index.ts           # Entry point, MCP server setup
│   ├── tools/             # Tool definitions and handlers
│   ├── resources/         # Resource definitions
│   ├── prompts/           # Prompt templates
│   ├── types/             # TypeScript interfaces
│   ├── state/             # Session and context management
│   ├── mediator/          # Dependency analysis
│   ├── roles/             # Role enforcement
│   ├── config/            # Configuration constants
│   ├── cache/             # Response caching
│   ├── chunking/          # Code chunking
│   ├── diff/              # Differential analysis
│   ├── pipeline/          # Tiered verification
│   └── safeguards/        # Quality safeguards
├── dist/                  # Compiled output
├── package.json
├── tsconfig.json
└── README.md

Contributing

Contributions welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Submit a pull request

License

MIT