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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/cisco-ai-defense/mcp-scannerWrote 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/commands/cisco-ai-defense/mcp-scanner/scan-prompts)<a href="https://agentmods.dev/commands/cisco-ai-defense/mcp-scanner/scan-prompts"><img src="https://agentmods.dev/badge/commands/cisco-ai-defense/mcp-scanner/scan-prompts/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/commands/cisco-ai-defense/mcp-scanner/scan-prompts"><img src="https://agentmods.dev/badge/commands/cisco-ai-defense/mcp-scanner/scan-prompts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00010 | $0.00125 |
| Opus 5 | $0.00005 | $0.00063 |
| Sonnet 5 | $0.00002 | $0.00025 |
| Haiku 4.5 | $0.00001 | $0.00013 |
Grade A, and why
scan-prompts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Scan MCP Server Prompts
Scan all prompts on the MCP server at "$ARGUMENTS" for security threats including prompt injection.
Run the following command:
mcp-scanner --analyzers llm --format detailed prompts --server-url "$ARGUMENTS"
If the URL is not provided, ask the user for the MCP server URL.
Note: This scan requires the LLM analyzer. Ensure MCP_SCANNER_LLM_API_KEY is set.
After scanning, summarize any prompt injection risks or other security concerns found.
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.
- 11d ago First seen · 19 lines · 10 tokens per session scan A 5102bfa10096
scan-prompts is a command published in the GitHub repository cisco-ai-defense/mcp-scanner (1,070 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10 tokens to every session and 125 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
template
Manage issue templates for streamlined issue creation.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
discover
Search the Everruns(Dev) API catalog for available operations.
fix
Universal debugging and fix application with semantic code analysis.
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.