---
title: "agentic_security vs cve-mcp-server"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/msoedov-agentic-security-vs-mukul975-cve-mcp-server"
tools: ["msoedov-agentic-security", "mukul975-cve-mcp-server"]
---

# agentic_security vs cve-mcp-server

*GraphCanon updated Jul 28, 2026*

## Verdict

Pick agentic_security if agentic Security is an agent-based framework for scanning vulnerabilities in large language models with a Python-based toolkit for robust security assessments via fuzz testing; pick cve-mcp-server if cve-mcp-server offers production-grade integration of Claude with diverse cybersecurity APIs and tools.

[agentic_security](https://agentic-security.vercel.app) reports 1.9k GitHub stars, 270 forks, and 70 open issues, last pushed Jun 23, 2026. [cve-mcp-server](https://www.mahipal.engineer/CVE-MCP-Server/) has 1.1k stars, 179 forks, and 10 open issues, last pushed Jul 16, 2026. Figures are from public GitHub metadata via [agentic_security's repository](https://github.com/msoedov/agentic_security) and [cve-mcp-server's repository](https://github.com/mukul975/cve-mcp-server).

| | [agentic_security](/tools/msoedov-agentic-security.md) | [cve-mcp-server](/tools/mukul975-cve-mcp-server.md) |
| --- | --- | --- |
| Tagline | Agentic LLM Vulnerability Scanner / AI red teaming kit | Production-grade MCP server providing Claude access to multiple cybersecurity tools and APIs |
| Stars | 1,943 | 1,096 |
| Forks | 270 | 179 |
| Open issues | 70 | 10 |
| Language | Python | Python |
| Adopt for | Agentic Security is an agent-based framework for scanning vulnerabilities in large language models with a Python-based toolkit for robust security assessments via fuzz testing. | cve-mcp-server offers production-grade integration of Claude with diverse cybersecurity APIs and tools. |
| Persona | - | - |
| Runtime | - | - |
| License | Apache-2.0 - Permissive license encouraging free use and modification under the condition of preserving notices. | Apache-2.0 |
| Categories | Evaluation & Observability, LLM Frameworks | Data & Retrieval, Evaluation & Observability |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [agentic_security](/tools/msoedov-agentic-security.md) | [cve-mcp-server](/tools/mukul975-cve-mcp-server.md) |
| --- | --- | --- |
| Maintenance | Steady (60%) | Active (82%) |
| Days since push | 35d | 10d |
| Open issues (now) | 70 | 10 |
| Full report | [trust report](/tools/msoedov-agentic-security/trust.md) | [trust report](/tools/mukul975-cve-mcp-server/trust.md) |

## Shared compatibility

- **Python**: [agentic_security](/tools/msoedov-agentic-security.md) - Python runtime; [cve-mcp-server](/tools/mukul975-cve-mcp-server.md) - Python runtime

## Decision facts: agentic_security

- **Adopt for:** Agentic Security is an agent-based framework for scanning vulnerabilities in large language models with a Python-based toolkit for robust security assessments via fuzz testing.
- **License detail:** Apache-2.0 - Permissive license encouraging free use and modification under the condition of preserving notices.

## Decision facts: cve-mcp-server

- **Hosting:** self hosted - This tool needs to be hosted and run on your own infrastructure.
- **Requirements:** cve-mcp-server requires a Python environment.; Proper API keys for accessing various security tools and APIs are necessary.
- **Adopt for:** cve-mcp-server offers production-grade integration of Claude with diverse cybersecurity APIs and tools.
- **License detail:** Apache-2.0

## Choose when

### Choose agentic_security if…

- Tags unique to agentic_security: agent-framework, fuzzing, llm-evaluation, red-teaming.
- Also covers LLM Frameworks.
- Developers need to ensure their LLMs are secure from jailbreak attempts and vulnerabilities.

### Choose cve-mcp-server if…

- This tool needs to be hosted and run on your own infrastructure.
- Requirements: cve-mcp-server requires a Python environment.; Proper API keys for accessing various security tools and APIs are necessary..
- Tags unique to cve-mcp-server: cisa-kev, claude-ai, cve, cybersecurity.
- Also covers Data & Retrieval.
- Use cve-mcp-server when you need to provide comprehensive threat intelligence and vulnerability management capabilities to the LLM 'Claude', leveraging 27 security intelligence tools.

## When NOT to use agentic_security

- Teams require solutions that do not involve agent frameworks for vulnerability scanning.
- Projects seek a no-fuzz-testing approach for evaluating LLM security.

## When NOT to use cve-mcp-server

- Avoid cve-mcp-server if your application does not require integration with the specific set of cybersecurity tools it provides or if a different LLM is preferred.
- Do not use this tool if you need to integrate only one or two security APIs; its strength lies in its extensive library of integrations, which might be overkill for smaller scale projects.

## Common questions

### What is the difference between agentic_security and cve-mcp-server?

agentic_security: Agentic LLM Vulnerability Scanner / AI red teaming kit. cve-mcp-server: Production-grade MCP server providing Claude access to multiple cybersecurity tools and APIs. See the comparison table for live GitHub stats and shared categories.

### When should I choose agentic_security over cve-mcp-server?

Choose agentic_security over cve-mcp-server when Tags unique to agentic_security: agent-framework, fuzzing, llm-evaluation, red-teaming; Also covers LLM Frameworks; Developers need to ensure their LLMs are secure from jailbreak attempts and vulnerabilities.

### When should I choose cve-mcp-server over agentic_security?

Choose cve-mcp-server over agentic_security when This tool needs to be hosted and run on your own infrastructure; Requirements: cve-mcp-server requires a Python environment.; Proper API keys for accessing various security tools and APIs are necessary.; Tags unique to cve-mcp-server: cisa-kev, claude-ai, cve, cybersecurity; Also covers Data & Retrieval; Use cve-mcp-server when you need to provide comprehensive threat intelligence and vulnerability management capabilities to the LLM 'Claude', leveraging 27 security intelligence tools.

### When should I avoid agentic_security?

Teams require solutions that do not involve agent frameworks for vulnerability scanning. Projects seek a no-fuzz-testing approach for evaluating LLM security.

### When should I avoid cve-mcp-server?

Avoid cve-mcp-server if your application does not require integration with the specific set of cybersecurity tools it provides or if a different LLM is preferred. Do not use this tool if you need to integrate only one or two security APIs; its strength lies in its extensive library of integrations, which might be overkill for smaller scale projects.

### Is agentic_security or cve-mcp-server more popular on GitHub?

agentic_security has more GitHub stars (1,943 vs 1,096). Stars measure visibility, not whether either tool fits your constraints.

### Are agentic_security and cve-mcp-server open source?

Yes - both are open-source projects on GitHub (agentic_security: Apache-2.0, cve-mcp-server: Apache-2.0).

### Where can I find alternatives to agentic_security or cve-mcp-server?

GraphCanon lists graph-backed alternatives at [agentic_security alternatives](/tools/msoedov-agentic-security/alternatives) and [cve-mcp-server alternatives](/tools/mukul975-cve-mcp-server/alternatives) ([agentic_security markdown twin](/tools/msoedov-agentic-security/alternatives.md), [cve-mcp-server markdown twin](/tools/mukul975-cve-mcp-server/alternatives.md)), ranked by typed relationship edges rather than popularity votes.

### Is there a machine-readable version of this comparison?

Yes. The markdown twin at [this comparison](/compare/msoedov-agentic-security-vs-mukul975-cve-mcp-server.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, agentic_security or cve-mcp-server?

agentic_security: Steady. cve-mcp-server: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.

### Where are the full trust reports for agentic_security and cve-mcp-server?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentic_security trust report](/tools/msoedov-agentic-security/trust); [cve-mcp-server trust report](/tools/mukul975-cve-mcp-server/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=msoedov-agentic-security`](/api/graphcanon/graph?tool=msoedov-agentic-security)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_