The Reliability Layer for Your AI Agent Tools

Contract validation, self-healing failover, and BYOK encryption for every MCP tool call. Drop-in middleware, zero infrastructure changes.

npx correctover-mcp-server
View on GitHub → Enterprise →

6-Dimension Contract Validation

📋 Schema Validation

JSON Schema enforcement on every MCP tool input/output. Catches malformed payloads before they reach agent logic.

🔗 Deterministic Hash

Hash-based response verification. Detects corrupted or tampered outputs by comparing signatures.

📐 Similarity Check

Semantic vector comparison against expected output profiles. Flags looks-correct-but-wrong responses.

🔍 Entity Extraction

Named entity validation against allowed schemas. Prevents PII and credential leakage through tool responses.

🚫 Prohibited Patterns

Regex-based pattern blocking for code execution, path traversal, and SSRF attempts in tool arguments.

💬 Prompt Injection Guard

Detects prompt injection attempts embedded in tool call parameters before they reach the LLM.

Self-Healing Failover

When a provider returns errors, Correctover transparently retries across fallback providers, validates the replacement response, and continues streaming — all within the same tool call lifecycle.

Registries

📦 npm 🐙 GitHub ✨ Glama (Official) 🔧 Smithery

Client Configuration

Add to your mcpServers config. Set at least one provider API key (BYOK) so the server can route tool calls:

{
  "mcpServers": {
    "correctover": {
      "command": "npx",
      "args": ["correctover-mcp-server"],
      "env": {
        "OPENAI_API_KEY": "sk-...",
        "CORRECTOVER_LICENSE_KEY": "NB-PRO-... (optional, for Pro plan)"
      }
    }
  }
}

Server reads provider keys from env: OPENAI_API_KEY, ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, MOONSHOT_API_KEY, ZHIPU_API_KEY, DASHSCOPE_API_KEY.

Get your provider key from its dashboard (e.g. platform.openai.com/api-keys). Pro license key from rating/register.