Add hyperscaler discovery MCP servers and Well-Architected guidance
Some checks failed
check agents / check (push) Failing after 12s

azure-discovery, aws-discovery and gcp-discovery collect read-only metadata
on servers, workloads, Kubernetes clusters, networks, data stores, policies
and provider recommendations. Credentials arrive per call from the vault.
Replies are paged, scrubbed of secrets and anonymised, and throttled calls
back off. cloud-knowledge searches each provider's Well-Architected guidance
from fixed lists only, so no customer detail can leave the platform.

Adds shared skills, the render and test tooling, a public Python Dockerfile
until the hardened base image is reachable, the customer access guide, the
implementation plan and the Vault Service platform issue.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-30 20:11:57 +00:00
parent 416c66ced4
commit c14a94f33b
91 changed files with 13296 additions and 1 deletions

View File

@@ -0,0 +1,159 @@
# aws-discovery: every read assumes the customer's read-only role, inside the accounts and regions of the connection.
import asyncio
import boto3
from botocore.config import Config as BotoConfig
AWS_SESSIONS = {}
# kind -> (service, operation, result key, token parameter, token in the reply, fixed arguments)
AWS_SERVERS = {
"instances": ("ec2", "describe_instances", "Reservations", "NextToken", "NextToken", {}),
"auto_scaling_groups": ("autoscaling", "describe_auto_scaling_groups", "AutoScalingGroups", "NextToken", "NextToken", {}),
"volumes": ("ec2", "describe_volumes", "Volumes", "NextToken", "NextToken", {}),
}
AWS_WORKLOADS = {
"lambda_functions": ("lambda", "list_functions", "Functions", "Marker", "NextMarker", {}),
"ecs_clusters": ("ecs", "list_clusters", "clusterArns", "nextToken", "nextToken", {}),
"app_runner_services": ("apprunner", "list_services", "ServiceSummaryList", "NextToken", "NextToken", {}),
"elastic_beanstalk_environments": ("elasticbeanstalk", "describe_environments", "Environments", "NextToken", "NextToken", {}),
}
AWS_NETWORK = {
"vpcs": ("ec2", "describe_vpcs", "Vpcs", "NextToken", "NextToken", {}),
"subnets": ("ec2", "describe_subnets", "Subnets", "NextToken", "NextToken", {}),
"route_tables": ("ec2", "describe_route_tables", "RouteTables", "NextToken", "NextToken", {}),
"security_groups": ("ec2", "describe_security_groups", "SecurityGroups", "NextToken", "NextToken", {}),
"nat_gateways": ("ec2", "describe_nat_gateways", "NatGateways", "NextToken", "NextToken", {}),
"internet_gateways": ("ec2", "describe_internet_gateways", "InternetGateways", "NextToken", "NextToken", {}),
"transit_gateways": ("ec2", "describe_transit_gateways", "TransitGateways", "NextToken", "NextToken", {}),
"vpc_peering": ("ec2", "describe_vpc_peering_connections", "VpcPeeringConnections", "NextToken", "NextToken", {}),
"vpc_endpoints": ("ec2", "describe_vpc_endpoints", "VpcEndpoints", "NextToken", "NextToken", {}),
"load_balancers": ("elbv2", "describe_load_balancers", "LoadBalancers", "Marker", "NextMarker", {}),
}
AWS_DATA = {
"rds_instances": ("rds", "describe_db_instances", "DBInstances", "Marker", "Marker", {}),
"dynamodb_tables": ("dynamodb", "list_tables", "TableNames", "ExclusiveStartTableName", "LastEvaluatedTableName", {}),
"s3_buckets": ("s3", "list_buckets", "Buckets", "ContinuationToken", "ContinuationToken", {}),
}
AWS_ORG_POLICY_TYPES = {"service_control_policies": "SERVICE_CONTROL_POLICY", "resource_control_policies": "RESOURCE_CONTROL_POLICY",
"tag_policies": "TAG_POLICY", "backup_policies": "BACKUP_POLICY"}
AWS_PILLARS = {"cost_optimizing": "cost", "security": "security", "fault_tolerance": "reliability",
"performance": "performance", "operational_excellence": "operations", "service_limits": "reliability"}
def _aws_csv(connection: Dict[str, Any], field: str) -> List[str]:
return [v.strip() for v in str(connection.get(field) or "").split(",") if v.strip()]
def _aws_session(connection: Dict[str, Any], account_id: Optional[str]):
"""A session on the customer's read-only role, or on the member account's when one is named."""
key = hashlib.sha256(json.dumps([connection, account_id], sort_keys=True).encode()).hexdigest()
cached = AWS_SESSIONS.get(key)
now = time.time()
if cached and cached[1] > now + 60:
return cached[0]
def assume(session, role_arn, external_id=None):
region = _aws_csv(connection, "regions")[0]
request = {"RoleArn": role_arn, "RoleSessionName": "kab-discovery", "DurationSeconds": 3600}
if external_id:
request["ExternalId"] = external_id
found = session.client("sts", region_name=region).assume_role(**request)["Credentials"]
return boto3.Session(aws_access_key_id=found["AccessKeyId"], aws_secret_access_key=found["SecretAccessKey"],
aws_session_token=found["SessionToken"])
base = boto3.Session(aws_access_key_id=connection["access_key_id"], aws_secret_access_key=connection["secret_access_key"])
session = assume(base, connection["role_arn"], connection.get("external_id"))
if account_id:
partition = str(connection["role_arn"]).split(":")[1]
session = assume(session, f"arn:{partition}:iam::{account_id}:role/{connection['member_role_name']}")
AWS_SESSIONS[key] = (session, now + 3000)
return session
def _aws_target(arguments: Dict[str, Any]):
"""(account, region) or a refusal. Nothing outside the connection's accounts and regions is ever reached."""
connection = get_connection()
regions = _aws_csv(connection, "regions")
region = arguments.get("region") or regions[0]
if region not in regions:
return None, None, _refuse("outside_scope", "region isn't in this connection's regions")
account = arguments.get("account_id")
if account and (account not in _aws_csv(connection, "account_ids") or not connection.get("member_role_name")):
return None, None, _refuse("outside_scope", "account_id isn't in this connection's accounts")
return account, region, None
async def _aws_call(arguments: Dict[str, Any], service: str, operation: str, region: Optional[str] = None, **request):
connection = get_connection()
account = arguments.get("account_id")
where = region or arguments.get("region") or _aws_csv(connection, "regions")[0]
def run():
# Adaptive mode slows the client down when AWS throttles it, on top of retrying.
retries = BotoConfig(retries={"max_attempts": 6, "mode": "adaptive"}, read_timeout=60, connect_timeout=10)
client = _aws_session(connection, account).client(service, region_name=where, config=retries)
return getattr(client, operation)(**request)
return await asyncio.to_thread(run)
async def _aws_kind(tool: str, arguments: Dict[str, Any], kinds: Dict[str, tuple], default: str) -> Dict[str, Any]:
kind = arguments.get("kind") or default
if kind not in kinds:
return _refuse("unknown_kind", "kind must be one of: " + ", ".join(kinds))
account, region, refused = _aws_target(arguments)
if refused:
return refused
service, operation, result_key, token_in, token_out, fixed = kinds[kind]
try:
upstream, skip = _read_page(arguments)
except (ValueError, KeyError, TypeError):
return _refuse("invalid_page_token", "page_token isn't one this server issued")
request = dict(fixed)
if upstream:
request[token_in] = upstream
try:
body = await _aws_call(arguments, service, operation, region, **request)
except Exception as error:
return _upstream_failed("aws", error)
extra = {"account_id": account, "region": region, "kind": kind}
return _page_result("aws", tool, arguments, body.get(result_key, []), upstream, body.get(token_out), skip, extra)
async def _aws_each(tool: str, arguments: Dict[str, Any], list_kind: tuple, read) -> Dict[str, Any]:
"""List one page of things, then read a detail for each. A detail that's absent or refused is reported."""
account, region, refused = _aws_target(arguments)
if refused:
return refused
service, operation, result_key, token_in, token_out, fixed = list_kind
try:
upstream, skip = _read_page(arguments)
except (ValueError, KeyError, TypeError):
return _refuse("invalid_page_token", "page_token isn't one this server issued")
request = dict(fixed)
if upstream:
request[token_in] = upstream
try:
body = await _aws_call(arguments, service, operation, region, **request)
except Exception as error:
return _upstream_failed("aws", error)
items = []
for entry in body.get(result_key, [])[skip:skip + _page_size(arguments)]:
try:
items.append(await read(entry, region))
except Exception as error:
items.append({"resource": entry, "unread": type(error).__name__})
consumed = skip + len(items)
more = consumed < len(body.get(result_key, []))
next_upstream = upstream if more else body.get(token_out)
result = _page_result("aws", tool, arguments, items, None, None, 0, {"account_id": account, "region": region})
if more or next_upstream:
result["data"]["next_page_token"] = _write_page(next_upstream, consumed if more else 0)
return result
def _aws_document(text: Any) -> Any:
"""A policy document, parsed when it arrives as a JSON string, so its principals can be scrubbed."""
try:
return json.loads(text) if isinstance(text, str) else text
except ValueError:
return text