← Back to search

io.github.CSOAI-ORG/agent-policy-enforcement-mcp

CSOAI-ORG streamable_http Scanned 24d ago

Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<100...

MCP Registry ↗
B
75.5 / 100

Versions

1.0.11latest
first seen Jun 30, 2026
1.0.2
first seen May 19, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 6

define_policy
annotations: none low

Define a policy rule. - from_agent / to_agent / operation: may use "*" wildcard - effect: "allow" or "deny" - condition: optional predicate "context.<key> <op> <value>" (see docs) - priority: higher wins (default 100). Denies tie-break over allows.

effect str api_key str priority int to_agent str condition str operation str tenant_id str from_agent str
evaluate_call
annotations: none low

Evaluate whether agent-to-agent call is permitted. Returns the full decision trace. Logs the decision for audit.

api_key str to_agent str operation str tenant_id str from_agent str context_json str
list_policies
annotations: none low

List all policies for a tenant.

api_key str tenant_id str
remove_policy
annotations: none low

Remove a policy. Pro/Enterprise only.

api_key str policy_id str tenant_id str
decision_log
annotations: none low

Recent policy decisions. Pro tier sees unbounded history (otherwise last 100 only).

limit int api_key str tenant_id str
sign_policy_attestation
annotations: none low

Emit a cryptographically signed attestation of policy enforcement over a window. Evidence for EU AI Act Art 14 + ISO 42001 Annex A.7 auditors.

email str api_key str denials int tenant_id str window_end_utc str window_start_utc str total_evaluations int

Permissions 3

network medium
Server uses network capabilities via: urllib
filesystem low
Server uses filesystem capabilities via: open(), os
env_vars low
Server uses env_vars capabilities via: os.environ

Scan Findings 31

low
Tool 'define_policy' has no annotations annotation_checker · 100%
low
Tool 'evaluate_call' has no annotations annotation_checker · 100%
low
Tool 'list_policies' has no annotations annotation_checker · 100%
low
Tool 'remove_policy' has no annotations annotation_checker · 100%
low
Tool 'decision_log' has no annotations annotation_checker · 100%
low
Tool 'sign_policy_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: define_policy manifest_parser · 90%
info
Tool: evaluate_call manifest_parser · 90%
info
Tool: list_policies manifest_parser · 90%
info
Tool: remove_policy manifest_parser · 90%
info
Tool: decision_log manifest_parser · 90%
info
Tool: sign_policy_attestation manifest_parser · 90%
info
Required env vars (7) 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 · 80%
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%