Skip to main content

Canonical taxonomy and cross-project adapters for the MCP security ecosystem

Project description

mcp-taxonomy

Canonical classification taxonomy for the MCP security ecosystem.

Provides shared enums, types, and cross-project adapters so findings from palisade-scanner, MCPGuard, MCPwn, and agentgate can be correlated, compared, and displayed in a unified view (MCPscop).

Quick Start

from mcp_taxonomy import (
    AttackCategory, Severity, Confidence, DetectionMethod,
    palisade_finding_to_taxonomy,
    mcpguard_event_to_taxonomy,
    mcpwn_finding_to_taxonomy,
    agentgate_signal_to_taxonomy,
)

# Normalize findings from any tool into a common TaxonomyEvent
event = palisade_finding_to_taxonomy({
    "category": "jailbreak",
    "detector": "injection_patterns",
    "severity": "high",
    "confidence": 0.9,
    "title": "Jailbreak detected",
})

print(event.attack_category)  # AttackCategory.JAILBREAK
print(event.severity)         # Severity.HIGH
print(event.source)           # "palisade-scanner"

Taxonomy

Attack Categories (20)

Category Default Severity
rce critical
command_injection critical
sql_injection critical
malware critical
exfiltration high
tool_poisoning high
ssrf high
jailbreak high
injection high
scareware high
policy_violation medium
impersonation medium
stego medium
resource_scan medium
unicode_attack medium
encoded_payload medium
anomaly medium
crawl low
homoglyph low
misconfiguration low

Severity (5 levels)

critical (25) > high (10) > medium (3) > low (1) > info (0)

Detection Methods (22)

Hidden text, injection patterns, metadata, exfiltration, unicode advanced, stego markers, entropy, image stego, instruction classifier (palisade-scanner), prompt injection, jailbreak patterns, tool poisoning, resource prompt, stego detector, anomaly detector (MCPGuard), injection tester, prompt fuzzer, tool analysis, tool poisoning fuzzer, SSRF tester, SQLi tester, RCE blind tester, A2A scanner (MCPwn), known/suspicious UA, rate/honeypot (agentgate).

Adapters

Function Input Source
palisade_finding_to_taxonomy() dict or Finding object palisade-scanner
mcpguard_event_to_taxonomy() dict or SecurityEvent MCPGuard
mcpwn_finding_to_taxonomy() dict or Finding object MCPwn
agentgate_signal_to_taxonomy() signal type + metadata agentgate

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_taxonomy-0.2.0.tar.gz (10.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_taxonomy-0.2.0-py3-none-any.whl (11.7 kB view details)

Uploaded Python 3

File details

Details for the file mcp_taxonomy-0.2.0.tar.gz.

File metadata

  • Download URL: mcp_taxonomy-0.2.0.tar.gz
  • Upload date:
  • Size: 10.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for mcp_taxonomy-0.2.0.tar.gz
Algorithm Hash digest
SHA256 dedd9f9d859a4d71b5c3072bef19c93755a61e70dacbe157ce11460b3330ee84
MD5 598f47a9e82dc7bfa6dd083b5f55b995
BLAKE2b-256 1bc82bb6da9d40579771f48a0ad8c895ca91d497b76b21f3ff28a219beb1809a

See more details on using hashes here.

File details

Details for the file mcp_taxonomy-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: mcp_taxonomy-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 11.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for mcp_taxonomy-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b521af786aebf1266912a5289165e851c1a6d7b4be2e2ba796b40665b66ffa9a
MD5 cd50934522cdeee31238889d17a417a5
BLAKE2b-256 cc40e4c7d5e04fc7c4a1ddf56b74021c9c365170501489e595296908fa56c4ad

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page