# cisco-ai-defense/mcp-scanner

Scan MCP servers for potential threats & security findings.

Repository: https://github.com/cisco-ai-defense/mcp-scanner
Canonical: https://ross.abutalabs.com/products/mcp-scanner
Homepage: https://blogs.cisco.com/ai/securing-the-ai-agent-supply-chain-with-ciscos-open-source-mcp-scanner
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, ai, mcp, security
Last push: 2026-08-25T22:43:39+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 24
- inputs: {"age_days": 344, "days_push": 8, "days_rel": 26, "gap_med": 2.0, "n_releases_24m": 45}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1051, forks 132 (observed 2026-08-28T04:03:23.082165+00:00)

## What it is
MCP Scanner is a Python tool and SDK from Cisco AI Defense that scans Model Context Protocol (MCP) servers, tools, prompts, and resources for security threats. It combines YARA rules, LLM-based analysis, and the Cisco AI Defense inspect API, and can run as a CLI or REST API server.

## Use cases
- scan mcp servers for malicious tools before connecting agents
- audit ai agent supply chain for security threats
- detect tool poisoning in model context protocol servers
- scan pypi packages used by mcp servers for malware
- run mcp security scans in ci/cd pipelines
- check mcp server code for behavioral threats

## When to choose
- you deploy or consume MCP servers and need to vet them for security findings
- you want multi-engine scanning (YARA, LLM, Cisco AI Defense) of MCP tools, prompts, and resources
- you need offline/static scanning of MCP server metadata for air-gapped or CI environments

## When to avoid
- you need general-purpose vulnerability scanning of non-MCP software
- you require a fully self-contained scanner with no reliance on external APIs like Cisco AI Defense or VirusTotal
- you need runtime protection of agents rather than pre-deployment scanning

## Facets
- artifact type: cli-tool
- maturity: active
- function: security, vulnerability-scanning, mcp, cli, developer-tools
- domain: security, developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: mcp-security, supply-chain-security, yara-rules, llm-analysis, ai-agent-supply-chain, pypi-package-scanning, virus-total, ai-agents, docker

## Member repositories
- cisco-ai-defense/mcp-scanner (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.082165+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:02.892015+00:00, confidence not recorded.
  - readme: https://github.com/cisco-ai-defense/mcp-scanner (fetched 2026-08-28T04:03:23.082165+00:00, sha 277cb0e362ee)
  - homepage: https://blogs.cisco.com/ai/securing-the-ai-agent-supply-chain-with-ciscos-open-source-mcp-scanner (fetched 2026-08-29T13:01:47.739663+00:00, sha 638466d2f4d7)
- Data as of 2026-08-30T08:39:29.467469+00:00.