awslabs.aws-api-mcp-server@1.6.1
VERIFIED· install onlyPublisher claims: "Model Context Protocol (MCP) server for interacting with AWS" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 24 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
AUTH_AUDIENCEAUTH_CLIENT_IDAUTH_ISSUERAUTH_JWKS_URIAUTH_TYPEConfiguration, not credentials: AWS_API_MCP_AGENT_SCRIPTS_DIR, AWS_API_MCP_ALLOWED_HOSTS, AWS_API_MCP_ALLOWED_ORIGINS, AWS_API_MCP_HOST, AWS_API_MCP_PORT, AWS_API_MCP_PROFILE_NAME, AWS_API_MCP_TRANSPORT, AWS_MAX_ATTEMPTS, AWS_REGION, ENDPOINT_SUGGEST_AWS_COMMANDS, FASTMCP_LOG_LEVEL, XDG_RUNTIME_DIR- Where it talks to
- no vendor host named in the codeAlso amazonaws.com, amazon.com, api.aws — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names amazonaws.com, amazon.com, api.aws as well as its own vendor. The guard injects AUTH_AUDIENCE, AUTH_CLIENT_ID, AUTH_ISSUER, AUTH_JWKS_URI, AUTH_TYPE only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 1.6.0
vet-skills diff awslabs.aws-api-mcp-server 1.6.0 1.6.1In the sandbox, this version reached for nothing 1.6.0 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-17 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
@patch('awslabs.aws_api_mcp_server.middleware.http_header_validation_middleware.get_http_headers')Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.- Invalid or missing AWS profile → check ~/.aws/credentials and ~/.aws/configFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from awslabs.aws_api_mcp_server.middleware.http_header_validation_middleware import (Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.- Invalid or missing AWS profile → check ~/.aws/credentials and ~/.aws/configFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.chmod o+x /rootFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.@patch('awslabs.aws_api_mcp_server.middleware.http_header_validation_middleware.get_http_headers')Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.'awslabs.aws_api_mcp_server.middleware.http_header_validation_middleware.ALLOWED_ORIGINS',Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.'awslabs.aws_api_mcp_server.middleware.http_header_validation_middleware.ALLOWED_ORIGINS',Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.@patch('awslabs.aws_api_mcp_server.server.TRANSPORT', 'streamable-http')Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.'aws ec2 create-tags --resources i-1234567890abcdef0 --tags Key=test,Value@=file:///etc/passwd',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.@patch('awslabs.aws_api_mcp_server.server.ALLOWED_ORIGINS', 'https://my-mcp-server.example.com')Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.'aws ec2 create-tags --resources i-1234567890abcdef0 --tags Key=yayme,Value@=fileb:///etc/passwd',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f'aws s3api upload-part --bucket bucket --key file.txt --body {WORKING_DIRECTORY}/part.bin --part-number 1 --upload-id x',Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.@patch('awslabs.aws_api_mcp_server.server.STATELESS_HTTP', True)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.('http://192.168.1.1:8080', 'Local endpoint was not a loopback address'),Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.- Example: `aws s3api upload-part --bucket bucket --key file.txt --body /path/to/part.bin --part-number 1 --upload-id x`Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.@patch('awslabs.aws_api_mcp_server.server.TRANSPORT', 'streamable-http')Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.@patch('awslabs.aws_api_mcp_server.server.STATELESS_HTTP', True)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.('http://192.168.1.1:8000', 'http://192.168.1.1'),Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.