Correctover MCP Server
OfficialThe Correctover MCP Server acts as an intelligent intermediary that validates LLM responses in real-time across six dimensions and automatically self-heals through retries or failover to ensure reliable AI outputs.
Core Validation (6 Dimensions): Structure (JSON/YAML well-formedness, required fields), Schema (type correctness, enum compliance), Latency (SLA thresholds), Cost (token usage/budget), Identity (model/provider match), and Integrity (content tampering, hash verification).
Tools:
chat— Send messages to LLMs with automatic 6-dimension validation and failover. Supports specifying provider, model, temperature, max tokens, and system prompts; returns a detailed validation report.health— Check availability and status of all configured LLM providers before use.providers— View supported providers (OpenAI, Anthropic, DeepSeek, Groq, Alibaba Qwen, Zhipu/GLM, SiliconFlow, Together, Moonshot/Kimi, etc.) with default models, base URLs, and configuration status.stats— Review session metrics: total API calls, validation pass rate, failover count, active providers, and server version.validation_history— Paginate through up to 500 recent validation records (newest first), each showing provider, model, latency, pass/fail status, score, and failure reasons.
Prompts: Pre-built prompts for verifying AI output (verify-output), comparing providers (compare-providers), and running reliability audits (reliability-audit).
BYOK (Bring Your Own Key): API keys stay on your machine — no proxying or data collection.
Provides integration with OpenAI's API for chat completion with automatic verification and self-healing.
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., "@Correctover MCP Server verify the AI output for correctness and completeness"
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.
Correctover — MCP Runtime Security
The runtime security layer for the MCP ecosystem.
We build the runtime security layer for AI agent ecosystems. Correctover enforces security conformance on every MCP tool call — validating LLM outputs, blocking injection attacks, preventing credential hijacking, and auto-recovering from failures at 22μs P50 latency.
What We Do
Layer | What | Where |
Runtime Verification | 6-dimension output validation (structure, schema, latency, cost, identity, integrity) + auto-failover |
|
Agent Governance SDK | Synchronous interceptor-based governance — fail-closed by design |
|
Security Audits | MCP protocol vulnerability research — CVE-class findings across 50+ implementations | |
Conformance Standard | CCS v1.0 — formal standard for agentic runtime verification | |
Fault Taxonomy | 215 fault types, 19 CVEs, 561 fault variants cataloged | Internal knowledge base |
Related MCP server: Kluster.ai Verify MCP
Real Data — Not Benchmarks
We don't simulate. We collect real API responses from production MCP servers and verify them.
20,000 Verified API Traces
Dataset | Records | Size | Format |
CCS 20K Verification Subset | 20,000 | 18 MB | JSONL (download) |
Collection methodology:
43.6 minutes of continuous collection at 13.7 API calls/second
68.88% conformance rate (13,776 conformant / 6,224 non-conformant)
30% fault injection rate for stress testing
Every record includes: request, response, latency, validation result, fault classification
Third-party independent verification: 120,426 conformance re-calculations by @babyblueviper1 — full consistency confirmed.
The complete 20K dataset is in ./data/ — download, verify, fork, do whatever you want. No gatekeeping.
Research & Publications
CCS v1.0 — Runtime Security Conformance Standard
The first formal conformance standard defining how agent runtimes should validate tool execution results at runtime.
Key findings from 20K real traces:
P50 validation latency: 22μs
Self-heal rate: 97.4% (engine auto-retries/fails over on failed validation, then re-validates)
Rule coverage: 88 detection rules (64 high-confidence)
561 distinct fault variants cataloged across all major LLM providers
Fault Taxonomy
We maintain a living fault taxonomy derived from real-world MCP server failures:
215 distinct fault types classified across 7 severity levels
19 CVE-class vulnerabilities identified across MCP implementations
Categories: RCE, SSRF, cloud credential hijacking, path traversal, output injection, privilege escalation
Upstream PR Contributions
We don't just report — we fix. Our contributions go directly into major agent frameworks:
PR | Framework | Status | What |
Ferro Labs | OPEN | Runtime validation integration | |
CrewAI | 10 commits | GuardrailProvider — runtime governance protocol | |
CrewAI | Discussion | Defining runtime verification authority | |
Microsoft | Under review | Runtime threat scanner — recursive nested-arg scanning, SSRF gaps, credential redaction, path boundary fixes |
Community Validation
Real researchers using our work in production:
Researcher | Framework | Contribution |
@pshkv (AutoGen maintainer) | AutoGen | Adopted Required(τ)⊆Supported(τ) framework for tool governance |
CrewAI | Testing two-layer governance structure | |
CrewAI | Implemented GuardrailProvider based on our design (10 commits) | |
Independent | 120,426 independent conformance re-calculations | |
PHI-OMEGA | ICLR paper collaboration on runtime verification | |
CrewAI | Idempotency analysis and interaction |
MCP Server — Product
The runtime verification engine packaged as an MCP server for your AI tools.
Quick Start
npm install -g correctover-mcp-serverAdd to your mcp.json (Cursor, Claude Desktop, Windsurf):
{
"mcpServers": {
"correctover": {
"command": "correctover-mcp-server",
"env": {
"OPENAI_API_KEY": "sk-...",
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
}
}BYOK — your keys stay on your machine. No proxy, no data collection.
How It Works
Your AI Tool (Cursor / Claude Desktop / Windsurf)
│
▼
┌─────────────────────────────┐
│ Correctover MCP Server │
│ ┌───────────────────────┐ │
│ │ 6-Dim Validator │ │
│ │ ├─ Structure │ │
│ │ ├─ Schema │ │
│ │ ├─ Latency │ │
│ │ ├─ Cost │ │
│ │ ├─ Identity │ │
│ │ └─ Integrity │ │
│ └───────────────────────┘ │
│ │ │
│ ┌──────▼──────┐ │
│ │ Failover │ │
│ │ Engine │ │
│ └──────┬──────┘ │
└──────────┼──────────────────┘
│
┌──────┼──────┬──────────┐
▼ ▼ ▼ ▼
OpenAI Anthropic DeepSeek Qwen ...Supported Providers
Provider | Models | Env Variable |
OpenAI | GPT-4o, GPT-4o-mini, o1 |
|
Anthropic | Claude 3.5 Sonnet, Haiku, Opus |
|
DeepSeek | DeepSeek-V3, DeepSeek-R1 |
|
Moonshot/Kimi | Moonshot-v1 |
|
Alibaba Qwen | Qwen-Max, Qwen-Plus |
|
Groq | Llama, Mixtral |
|
Together | Llama, Mistral |
|
Tools
Tool | Description |
| Verified chat — 6-dim validation + auto-failover |
| Check provider status |
| Detailed provider configuration |
| Session metrics: calls, pass rate, failover count |
| Query recent validation results (ring buffer, 500 records) |
Ecosystem Adoption
Real download numbers from public package registries (last 30 days):
Package | Registry | Monthly Downloads |
correctover-mcp-server | npm | 1,564 |
correctover | npm | 1,034 |
correctover-ccs | npm | 400 |
correctover | PyPI | 1,436 |
Total | 4,434/month |
All organic growth — no paid promotion. CCS standard package seeing highest growth rate (tens of thousands percent increase from baseline).
CCS SDK — Agent Governance
Python SDK for embedding governance into agent frameworks. Fail-closed by design.
pip install correctover-ccsfrom ccs import govern
@govern(policy="default")
def my_tool(args: dict) -> str:
return "result"
# Governance evaluates BEFORE function runs
# If denied → PermissionError, function never executesSupported frameworks: CrewAI, AutoGen, LangGraph/LangChain
Observer hooks (default): governance_crash → tool EXECUTES ❌
CCS decorators (ours): governance_crash → tool BLOCKED ✅Security Audit Reports
We publish detailed security audits of MCP server implementations:
Methodology: Source code analysis → fault injection → runtime verification → CVE classification
Findings to date: 506 security findings across 3 major repositories, 5 vulnerability types confirmed cross-repo.
Ecosystem & Links
Resource | Link |
CCS Standard (paper) | |
CCS Standard (GitHub) | |
MCP Server (npm) | |
CCS SDK (PyPI) | |
Security Audits | |
Agent Governance | Correctover/agent-governance-toolkit (fork with PRs) |
Glama | |
Protocol Spec | |
Website |
Contact
Security reports: wangguigui@correctover.com
BD / Enterprise: wangguigui@correctover.com
GitHub: @Correctover
License
Apache 2.0 © Correctover
Available Tools
5 toolschatARead-only
Send a chat message to an LLM with automatic output verification. Routes through the best available provider, validates the response across 6 dimensions (structure, schema, latency, cost, identity, integrity), and auto-heals on failure by retrying or failing over to another provider. Returns the response text plus a validation report showing which dimensions passed or failed.
Inputs: messages (required), model, provider, max_tokens, +2 more.
healthARead-onlyIdempotent
Check health and availability of all configured LLM providers. Returns a list of active providers with their default models and session statistics. Call this first to verify your configuration before using the chat tool.
providersARead-onlyIdempotent
List all supported LLM providers with their configuration details, default models, base URLs, and current status. Use this to see which providers are available, what model each uses by default, and whether custom base URLs are configured for proxy or mirror setups.
statsARead-onlyIdempotent
Show Correctover session statistics including total API calls, validation pass rate, failover count, active providers, and server version. Use this after a working session to review reliability metrics and see how many self-healing events occurred.
validation_historyARead-onlyIdempotent
Query recent validation results with pagination. Returns the most recent LLM call validation records, newest first. Each record includes provider, model, latency, pass/fail status, validation score, and failure reasons. Use limit and offset to paginate through results. Default returns the 20 most recent records. Maximum 100 per page. The buffer holds up to 500 records; older entries are automatically overwritten.
Inputs: limit, offset.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: chat for sending validated messages, health for checking provider availability, providers for listing all supported providers, stats for session statistics, and validation_history for reviewing past validation results. There is no overlap in functionality.
All tool names follow a consistent pattern: single words or compound words with underscores (e.g., validation_history). They are all lowercase and descriptive of their function, making them easy to understand and predict.
With 5 tools, the server is well-scoped for its purpose of managing LLM chat with validation and monitoring. Each tool covers a core aspect without being overly specialized or too sparse.
The tool surface covers the full lifecycle of interacting with LLM providers: checking configuration (health, providers), sending messages (chat), reviewing performance (stats), and auditing (validation_history). No obvious gaps are present for the stated purpose.
Maintenance
Related MCP Connectors
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.
Real-time fact-check, citation verification, and source-freshness for AI agents.
Related MCP Servers
- AlicenseBqualityFmaintenanceA lightweight bridge that wraps OpenAI's built-in tools (like web search and code interpreter) as Model Context Protocol servers, enabling their use with Claude and other MCP-compatible models.412MIT

Kluster.ai Verify MCPofficial
AlicenseNot gradedqualityNot gradedmaintenanceEnables fact-checking of AI responses against reliable sources and validation of responses against document content to ensure accuracy and reliability.-- 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

Arkheia Hallucinationofficial
AlicenseNot gradedqualityCmaintenanceDetect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.MIT