← Back to search

io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp

CSOAI-ORG streamable_http Scanned 20d ago

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

MCP Registry ↗
B
76.6 / 100

Versions

1.0.10latest
first seen Jun 30, 2026
1.0.2
first seen May 19, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 5

scan_prompt
annotations: none low

Scan a piece of text for prompt injection. Returns full decision trace. - context: where this text came from (user-prompt | rag-document | tool-arg | a2a-payload) Returns `safe`, `risk_level` (none|low|medium|high|critical), `patterns_matched` (list of rule hits), and `recommended_action` (allow | log | escalate | block).

text str api_key str context str tenant_id str
define_custom_rule
annotations: none low

Define a tenant-specific detection rule. Pro+ only. - pattern: regex (case-insensitive) - action: block | escalate | log

action str api_key str pattern str rule_name str tenant_id str
list_rules
annotations: none low

List built-in + custom rules (if tenant_id provided).

api_key str tenant_id str
scan_log
annotations: none low

Recent scan log. Pro tier: unbounded. Free tier: last 100.

limit int api_key str tenant_id str risk_filter str
sign_firewall_attestation
annotations: none low

Emit a signed attestation of firewall enforcement. Evidence for OWASP LLM01 + EU AI Act Art 15 (cybersecurity) + ISO 42001 Annex A.5 (security).

email str blocks int api_key str tenant_id str escalations int total_scans int window_end_utc str window_start_utc str

Permissions 3

network medium
Server uses network capabilities via: urllib
filesystem low
Server uses filesystem capabilities via: os
env_vars low
Server uses env_vars capabilities via: os.environ

Scan Findings 29

low
Tool 'scan_prompt' has no annotations annotation_checker · 100%
low
Tool 'define_custom_rule' has no annotations annotation_checker · 100%
low
Tool 'list_rules' has no annotations annotation_checker · 100%
low
Tool 'scan_log' has no annotations annotation_checker · 100%
low
Tool 'sign_firewall_attestation' has no annotations annotation_checker · 100%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-3qhf-m339-9g5v) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-9h52-p55h-vw2f) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-j975-95f5-7wqh) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-jpw9-pfvf-9f58) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-vj7q-gjh5-988w) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1616) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1617) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1618) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-3482) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-3483) dependency_analyzer · 95%
info
pyproject.toml metadata manifest_parser · 100%
info
Tool: scan_prompt manifest_parser · 90%
info
Tool: define_custom_rule manifest_parser · 90%
info
Tool: list_rules manifest_parser · 90%
info
Tool: scan_log manifest_parser · 90%
info
Tool: sign_firewall_attestation manifest_parser · 90%
info
Required env vars (2) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 80%
low
Permission: filesystem access detected permission_analyzer · 70%
low
Permission: env_vars access detected permission_analyzer · 90%
info
No dependency files found for SBOM generation sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%