MCP Scanner is a Python tool that examines Model Context Protocol servers and tools for security findings and potential threats. It can run as a command-line tool or REST API and uses YARA rules, LLM analysis, Cisco AI Defense, dependency checks, and other scans.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cisco-ai-defense/mcp-scannernpx agentmods add skills/cisco-ai-defense/mcp-scanner/security-scanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cisco-ai-defense/mcp-scanner/security-scan)<a href="https://agentmods.dev/skills/cisco-ai-defense/mcp-scanner/security-scan"><img src="https://agentmods.dev/badge/skills/cisco-ai-defense/mcp-scanner/security-scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cisco-ai-defense/mcp-scanner/security-scan"><img src="https://agentmods.dev/badge/skills/cisco-ai-defense/mcp-scanner/security-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 77 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.02422 |
| Opus 5.5 | $0.00026 | $0.00969 |
| Sonnet 5.5 | $0.00013 | $0.00484 |
| Haiku 4.5 | $0.00006 | $0.00242 |
Grade A, and why
mcp-security-scan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Security Scanning
When the user asks to scan MCP servers or check for security issues in MCP configurations, use the uv run mcp-scanner CLI tool. This tool detects prompt injection, tool poisoning, command injection, data exfiltration, and other MCP-specific threats.
Important: Always run mcp-scanner using uv run mcp-scanner to ensure proper dependency management.
Threat Types Detected
- Prompt Injection: Malicious instructions embedded in tool descriptions or prompts
- Tool Poisoning: Tools that claim to do one thing but actually perform malicious actions
- Command Injection: Tools that execute arbitrary system commands
- Data Exfiltration: Tools that leak sensitive data to external endpoints
- Privilege Escalation: Tools that request excessive permissions
- Cross-Origin Attacks: Tools that access unauthorized resources
- Behavioral Mismatches: Discrepancies between documented and actual tool behavior
Analyzers
| Analyzer | Description | Requirements | Best For |
|---|---|---|---|
yara |
Fast pattern-based detection using YARA rules | None | Quick scans, CI/CD pipelines |
llm |
LLM-powered semantic analysis | MCP_SCANNER_LLM_API_KEY |
Deep analysis, prompt injection detection |
api |
Cisco AI Defense API | MCP_SCANNER_API_KEY |
Enterprise-grade threat detection |
Combine analyzers: --analyzers yara,llm,api for comprehensive scanning.
Scanning Modes
1. Remote MCP Server
Scan tools on a remote SSE or streamable HTTP MCP server:
# Basic scan
uv run mcp-scanner --analyzers yara remote --server-url https://mcp.example.com/mcp
# With authentication
uv run mcp-scanner --analyzers yara remote --server-url https://mcp.example.com/mcp --bearer-token "$TOKEN"
# With custom headers (e.g., MCP Gateway dual-token auth)
uv run mcp-scanner --analyzers yara remote --server-url https://gateway.example.com/mcp \
--header "Authorization: Bearer ingress-token" \
--header "X-Egress-Auth: Bearer egress-token"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 257 lines · 64 tokens per session scan A 1bff3fc17180
mcp-security-scan is a skill published in the GitHub repository cisco-ai-defense/mcp-scanner (1,094 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 2,422 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".