Is Agentseal safe to use?

Agentseal has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install Agentseal?

Agentseal supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with Agentseal?

Agentseal is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is Agentseal actively maintained?

Agentseal is recently maintained — last commit was 30 days ago. It has 279 GitHub stars.

Agentseal

Name: Agentseal
Author: AgentSeal

agentseal · by AgentSeal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

279 0 tools GitHub PyPI

No known CVEs

No license

Maintained

Last commit 30d ago

Works with most clients

Transport: stdio, sse, http

0 tools

Grade F

Edit this pageView history

Security AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agentseal": {
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/agentseal)](https://mcppedia.org/s/agentseal)

Read me

What Agentseal does

pip install agentseal # or: npm install agentseal agentseal guard # scan your machine - no API key needed

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

58/100across 5 weighted dimensions

How we score →

0255075100

−42

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked agentseal against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Agentseal safe to use?: Agentseal has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install Agentseal?: Agentseal supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Agentseal?: Agentseal is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Agentseal actively maintained?: Agentseal is recently maintained — last commit was 30 days ago. It has 279 GitHub stars.

Similar servers

Others in security / ai-ml

View all →

Memory MCP Server98

Persistent memory using a knowledge graph

86.4k 5

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

86.4k 1

Antigravity Workspace Template96

Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.

1.2k 2

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

16.0k 6

MCP Security Weekly

Get CVE alerts and security updates for Agentseal and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

Security AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agentseal": {
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/agentseal)](https://mcppedia.org/s/agentseal)

Read me

What Agentseal does

pip install agentseal # or: npm install agentseal agentseal guard # scan your machine - no API key needed

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

README

Security toolkit for AI agents. Red-team prompts, detect MCP poisoning,
scan skill files, trace toxic data flows. 225+ tests across 28 agents.

Docs · MCP Registry · Dashboard · Blog

Quick Start

pip install agentseal    # or: npm install agentseal
agentseal guard          # scan your machine - no API key needed

That's it. AgentSeal finds dangerous skill files, poisoned MCP server configs, and data exfiltration paths across every AI agent on your machine.

Want to test a system prompt against adversarial attacks?

agentseal scan --prompt "You are a helpful assistant..." --model ollama/llama3.1:8b  # free, local
agentseal scan --prompt "You are a helpful assistant..." --model gpt-4o              # cloud

What does each command do?

Command	What it does	Needs an LLM?
`guard`	Scans skill files, MCP configs, toxic data flows, and supply chain changes on your machine	No
`scan`	Tests a system prompt against 225+ adversarial attack probes	Yes*
`scan-mcp`	Connects to a live MCP server and audits its tool descriptions for poisoning	No
`shield`	Watches agent config files in real time, alerts on threats, quarantines payloads	No

*Free with Ollama. Cloud providers (OpenAI, Anthropic, etc.) require an API key.

Guard

Scans all AI agent configurations on your machine. No API key, no network calls - everything runs locally.

Supported agents: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Gemini CLI, Codex CLI, Cline, Roo Code, Kilo Code, Copilot CLI, Aider, Continue, Zed, Amp, Amazon Q, Junie, Goose, Kiro, OpenCode, OpenClaw, Crush, Qwen Code, Grok CLI, Visual Studio, Kimi CLI, Trae, MaxClaw.

agentseal guard

Guard runs a six-stage detection pipeline on every file it finds:

Pattern signatures - known malicious patterns (credential access, exfiltration URLs, shell commands)
Deobfuscation - decodes Unicode tags, Base64, BiDi overrides, zero-width characters, TR39 confusables
Semantic analysis - embedding similarity (MiniLM-L6-v2) catches rephrased attacks that bypass patterns
Baseline tracking - SHA-256 hashes detect config changes since your last scan (rug-pull detection)
Registry enrichment - live trust scores from the MCP Security Registry (6,600+ servers)
Custom rules - YAML rules to enforce org-specific policies

agentseal guard init             # generate .agentseal.yaml project policy
agentseal guard --output sarif   # SARIF for GitHub Security tab
agentseal guard --output json    # machine-readable output
agentseal guard --no-diff        # skip baseline delta section
agentseal guard test            

... [View full README on GitHub](https://github.com/AgentSeal/agentseal#readme)

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

58/100across 5 weighted dimensions

How we score →

0255075100

−42

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked agentseal against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Agentseal safe to use?: Agentseal has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install Agentseal?: Agentseal supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Agentseal?: Agentseal is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Agentseal actively maintained?: Agentseal is recently maintained — last commit was 30 days ago. It has 279 GitHub stars.

Similar servers

Others in security / ai-ml

View all →

Memory MCP Server98

Persistent memory using a knowledge graph

86.4k 5

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

86.4k 1

Antigravity Workspace Template96

Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.

1.2k 2

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

16.0k 6

MCP Security Weekly

Get CVE alerts and security updates for Agentseal and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Agentseal

Install in your client

What Agentseal does

Test This Server

Why this score

58/100across 5 weighted dimensions

Security

Reviews

Frequently Asked Questions

Similar servers

Discussion

Agentseal

Install in your client

What Agentseal does

Test This Server

Security toolkit for AI agents. Red-team prompts, detect MCP poisoning,scan skill files, trace toxic data flows. 225+ tests across 28 agents.

Quick Start

What does each command do?

Guard

Why this score

58/100across 5 weighted dimensions

Security

Reviews

Frequently Asked Questions

Similar servers

Discussion

Security toolkit for AI agents. Red-team prompts, detect MCP poisoning,scan skill files, trace toxic data flows. 225+ tests across 28 agents.

Quick Start

What does each command do?

Guard

Security toolkit for AI agents. Red-team prompts, detect MCP poisoning,
scan skill files, trace toxic data flows. 225+ tests across 28 agents.

Security toolkit for AI agents. Red-team prompts, detect MCP poisoning,
scan skill files, trace toxic data flows. 225+ tests across 28 agents.