catalog / DevOps & Infra / AWS MCP Servers

◇MCP serverDevOps & InfraFree

AWS MCP Servers

Name: AWS MCP Servers
Availability: InStock
Author: ai-supply

AWS Labs' suite of MCP servers for AWS docs, infrastructure, containers, databases, and cost analysis.

@ai-supply

Installationen43k

⟳ upstream 2026.08.20260813230114 · updated 6d ago

↗ Quell-Repository

← More DevOps & Infra DevOps & Infra leaderboard →How we grade security →Source ↗

! Grade B · 75/100 · ReviewSecurity assessment

✓No compromise signals48capabilities surfaced1known CVE5of 20 OWASP controls clear

Broad capability surfaceBroad capability surfacePrompt-injection phrasingPotentially unbounded loop

scanned 4d agoosv · gitleaks · opengrep · picklescan + heuristicsfull breakdown in the Security tab ↓

AWS MCP Servers

awslabs/mcp is an open-source suite of specialized Model Context Protocol servers maintained by AWS Labs, designed to help you get more out of AWS from any MCP client.

The monorepo ships many focused servers spanning real-time access to official AWS documentation, infrastructure and deployment (CDK, Terraform, CloudFormation), container platforms (ECS, EKS), serverless, databases, and cost analysis. Each server exposes AWS capabilities as MCP tools that coding agents can call directly.

It is intended for developers and cloud engineers building on AWS who want their AI assistant to reference AWS docs and interact with AWS services programmatically.

! Security: Review · 7575/100 · grade Bscanned 4d ago

✓ no compromise signals49 risk-surface · 10/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · high confidence (static)

Tools (1)

mcp_generate_image

⚑ filesystem⚑ shell⚑ network⚑ secrets

egress → sscce.org, docs.aws.amazon.com, feathericons.com, docs.github.com, pypi.org, gh.io, www.apache.org, gallery.ecr.aws +32

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications

⚠LLM03Supply Chaincritical

Vulnerable/compromised dependencies, models or archives in the artifact.

•Dependency manifest — 117 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/bandit-requirements.txtrisk surface

•Dependency manifest — 162 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/detect-secrets-requirements.txtrisk surface

•Dependency manifest — 81 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/pre-commit-requirements.txtrisk surface

•Dependency manifest — 479 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/semgrep-requirements.txtrisk surface

•Dependency manifest — 13 npm dependencies declared · awslabs-mcp-6d289e1/docusaurus/package.jsonrisk surface

•Dependency manifest — 20 pip requirements declared · awslabs-mcp-6d289e1/src/amazon-bedrock-agentcore-mcp-server/uv-requirements.txtrisk surface

•Vulnerable dependencies — 2205 known vulnerabilities in: ajv@8.17.1, http-proxy-middleware@2.0.9, image-size@2.0.2, joi@17.13.3, nanoid@3.3.17, path-to-regexp@0.1.12, picomatch@2.3.1, serialize-javascript@6.0.2 (CWE-1395)known CVE · -25 pts

⚠LLM01Prompt Injectionhigh

Adversarial instructions embedded in an artifact that hijack a downstream LLM.

•Prompt-injection phrasing — instruction-subversion language detected · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/aws-transform-mcp-server.md (CWE-77)risk surface

⚠LLM02Sensitive Information Disclosurehigh

Secrets, credentials or PII shipped inside the artifact.

•Embedded credentials — found: hardcoded credential · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/mssql-mcp-server.md (CWE-798)expected

•Embedded credentials — found: AWS access key id, AWS secret key · awslabs-mcp-6d289e1/src/amazon-translate-mcp-server/tests/test_aws_client.py (CWE-798)expected

•Embedded credentials — found: AWS access key id · awslabs-mcp-6d289e1/src/aws-location-mcp-server/tests/test_server.py (CWE-798)expected

•Low-confidence secret match — 1 possible: generic-api-key · awslabs-mcp-6d289e1/src/amazon-bedrock-agentcore-mcp-server/awslabs/amazon_bedrock_agentcore_mcp_server/tools/policy/guide.py (CWE-798)risk surface

⚠LLM05Improper Output Handlinghigh

Code that pipes model/user output into shell, eval, SQL or paths unsafely.

•Suspicious code patterns — pipe-to-shell install · awslabs-mcp-6d289e1/.github/workflows/trivy.yml (CWE-494)expected

•Suspicious code patterns — dynamic code execution · awslabs-mcp-6d289e1/DESIGN_GUIDELINES.md (CWE-95)expected

•Suspicious code patterns — OS command execution · awslabs-mcp-6d289e1/src/aws-healthomics-mcp-server/awslabs/aws_healthomics_mcp_server/tools/workflow_linting.py (CWE-78)expected

⚠LLM06Excessive Agencyhigh

Over-broad tool/permission surface or unrestricted egress.

•External endpoints declared — 1 distinct host(s) · awslabs-mcp-6d289e1/.github/CODEOWNERSexpected

•External endpoints declared — 2 distinct host(s) · awslabs-mcp-6d289e1/.github/ISSUE_TEMPLATE/bug_report.ymlexpected

•Egress to a private/loopback host — feathericons.com · awslabs-mcp-6d289e1/.github/actions/build-and-push-container-image/action.yml (CWE-918)expected

•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · awslabs-mcp-6d289e1/.github/workflows/python.yml (CWE-272)risk surface

•External endpoints declared — 3 distinct host(s) · awslabs-mcp-6d289e1/.github/workflows/release.ymlexpected

•External endpoints declared — 11 distinct host(s) · awslabs-mcp-6d289e1/.gitignoreexpected

•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · awslabs-mcp-6d289e1/DESIGN_GUIDELINES.md (CWE-272)risk surface

•External endpoints declared — 4 distinct host(s) · awslabs-mcp-6d289e1/DESIGN_GUIDELINES.mdexpected

•Egress to a private/loopback host — 127.0.0.1 · awslabs-mcp-6d289e1/DEVELOPER_GUIDE.md (CWE-918)expected

•External endpoints declared — 12 distinct host(s) · awslabs-mcp-6d289e1/DEVELOPER_GUIDE.mdexpected

•External endpoints declared — 21 distinct host(s) · awslabs-mcp-6d289e1/README.mdexpected

•External endpoints declared — 6 distinct host(s) · awslabs-mcp-6d289e1/VIBE_CODING_TIPS_TRICKS.mdexpected

•External endpoints declared — 7 distinct host(s) · awslabs-mcp-6d289e1/docusaurus/docs/installation.mdexpected

•External endpoints declared — 5 distinct host(s) · awslabs-mcp-6d289e1/docusaurus/docusaurus.config.tsexpected

•External endpoints declared — 8 distinct host(s) · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/amazon-kendra-index-mcp-server.mdexpected

•External endpoints declared — 9 distinct host(s) · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/aurora-dsql-mcp-server.mdexpected

•External endpoints declared — 14 distinct host(s) · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/aws-api-mcp-server.mdexpected

•External endpoints declared — 10 distinct host(s) · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/aws-dataprocessing-mcp-server.mdexpected

•Egress to a private/loopback host — 10.0.0.5 · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/openapi-mcp-server.md (CWE-918)expected

•Egress to a private/loopback host — 192.168.1.1 · awslabs-mcp-6d289e1/src/aws-api-mcp-server/tests/middleware/test_http_header_validation_middleware.py (CWE-918)expected

•Egress to a private/loopback host — 127.0.0.1, [::1], 192.168.1.1 · awslabs-mcp-6d289e1/src/aws-api-mcp-server/tests/parser/test_parser.py (CWE-918)expected

•Egress to a private/loopback host — 127.0.0.1, 127.0.0.2, 127.255.255.255, 10.0.0.1, 192.168.1.1, 172.16.0.1, 172.31.255.255, 169.254.169.254, 169.254.0.1, 0.0.0.0, [::1], [fe80::1], [fc00::1], 0.0.0.127, 0.0.0.1 · awslabs-mcp-6d289e1/src/aws-appsync-mcp-server/tests/test_create_datasource.py (CWE-918)expected

•External endpoints declared — 20 distinct host(s) · awslabs-mcp-6d289e1/src/aws-appsync-mcp-server/tests/test_create_datasource.pyexpected

•Egress to a private/loopback host — 169.254.169.254 · awslabs-mcp-6d289e1/src/aws-documentation-mcp-server/tests/test_server_aws_cn.py (CWE-918)expected

⚠LLM07System Prompt Leakagehigh

Secrets, internal hosts or proprietary logic exposed in shipped prompts.

•Embedded credentials — found: hardcoded credential · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/mssql-mcp-server.md (CWE-798)expected

•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/openapi-mcp-server.md (CWE-200)expected

•Embedded credentials — found: AWS access key id, AWS secret key · awslabs-mcp-6d289e1/src/amazon-translate-mcp-server/tests/test_aws_client.py (CWE-798)expected

•Embedded credentials — found: AWS access key id · awslabs-mcp-6d289e1/src/aws-location-mcp-server/tests/test_server.py (CWE-798)expected

⚠LLM10Unbounded Consumptionmedium

Unbounded loops/recursion causing DoS or runaway cost.

Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.

•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · awslabs-mcp-6d289e1/src/amazon-bedrock-agentcore-mcp-server/awslabs/amazon_bedrock_agentcore_mcp_server/tools/browser/__init__.py (CWE-835)risk surface

§LLM09MisinformationGovernance

Artifacts designed to produce false/deceptive output.

Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.

✓LLM04Data and Model PoisoningPassed

Backdoors/poisoning in training data or serialized models.

Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.

✓LLM08Vector and Embedding WeaknessesPassed

PII or plaintext source leakage in embedding/vector exports.

Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.

OWASP Machine Learning Security Top 10

⚠ML06AI Supply Chaincritical

Compromised PyPI/npm packages, typosquats, unsafe serialized models.

•Dependency manifest — 117 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/bandit-requirements.txtrisk surface

•Dependency manifest — 162 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/detect-secrets-requirements.txtrisk surface

•Dependency manifest — 81 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/pre-commit-requirements.txtrisk surface

•Dependency manifest — 479 pip requirements declared · awslabs-mcp-6d289e1/.github/workflows/semgrep-requirements.txtrisk surface

•Dependency manifest — 13 npm dependencies declared · awslabs-mcp-6d289e1/docusaurus/package.jsonrisk surface

•Dependency manifest — 20 pip requirements declared · awslabs-mcp-6d289e1/src/amazon-bedrock-agentcore-mcp-server/uv-requirements.txtrisk surface

⚠ML02Data Poisoninghigh

Poisoned training datasets with triggers or anomalous distributions.

Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.

⚠ML09Output Integrityhigh

Middleware tampering with model outputs in transit.

Gateway enforces TLS + response integrity; static check flags output-rewriting code.

•Suspicious code patterns — pipe-to-shell install · awslabs-mcp-6d289e1/.github/workflows/trivy.yml (CWE-494)expected

•Suspicious code patterns — dynamic code execution · awslabs-mcp-6d289e1/DESIGN_GUIDELINES.md (CWE-95)expected

•Suspicious code patterns — OS command execution · awslabs-mcp-6d289e1/src/aws-healthomics-mcp-server/awslabs/aws_healthomics_mcp_server/tools/workflow_linting.py (CWE-78)expected

§ML01Input Manipulation (Adversarial)Governance

Models vulnerable to adversarial perturbations.

Requires runtime robustness evaluation; addressed via publisher robustness attestation.

§ML03Model InversionGovernance

Training data reconstructable from a model's outputs.

Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.

§ML04Membership InferenceGovernance

Determining whether a record was in the training set.

Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.

§ML08Model SkewingGovernance

Models trained on skewed data producing biased output.

Requires fairness evaluation; addressed via model-card bias/limitations disclosure.

✓ML05Model TheftPassed

Unlicensed re-distribution / license-incompatible derivatives.

Static check verifies license declaration; extraction throttling is runtime.

✓ML07Transfer Learning AttackPassed

Backdoored base models / LoRA adapters propagating to derivatives.

Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.

✓ML10Model Poisoning (Weights)Passed

Tampered model weight files; integrity must be verifiable.

Static check enforces safe formats + records a content hash for downstream verification.

Other findings (24) · hygiene / uncategorized

•Unrecognized file type — '.?' is not on the allowlist · awslabs-mcp-6d289e1/.github/CODEOWNERSrisk surface

•Unrecognized file type — '.gitignore' is not on the allowlist · awslabs-mcp-6d289e1/.gitignorerisk surface

•Unrecognized file type — '.python-version' is not on the allowlist · awslabs-mcp-6d289e1/.python-versionrisk surface

•Unrecognized file type — '.baseline' is not on the allowlist · awslabs-mcp-6d289e1/.secrets.baselinerisk surface

•Suspicious network references — raw IP URL (18 URLs) · awslabs-mcp-6d289e1/DEVELOPER_GUIDE.mdexpected

•Unrecognized file type — '.mdx' is not on the allowlist · awslabs-mcp-6d289e1/docusaurus/docs/servers/amazon-translate-mcp-server.mdxrisk surface

•Suspicious network references — raw IP URL (28 URLs) · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/aws-api-mcp-server.mdexpected

•Suspicious network references — raw IP URL (59 URLs) · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/openapi-mcp-server.mdexpected

•Malicious base64-encoded payload — decoded content matched: DB connection string with credentials · awslabs-mcp-6d289e1/docusaurus/i18n/ja/docusaurus-plugin-content-docs/current/servers/postgres-mcp-server.md (CWE-506)expected

•Unrecognized file type — '.tmx' is not on the allowlist · awslabs-mcp-6d289e1/src/amazon-translate-mcp-server/tests/fixtures/sample_terminology.tmxrisk surface

•Unrecognized file type — '.dockerignore' is not on the allowlist · awslabs-mcp-6d289e1/src/aurora-dsql-mcp-server/.dockerignorerisk surface

•Unrecognized file type — '.gitattributes' is not on the allowlist · awslabs-mcp-6d289e1/src/aws-api-mcp-server/.gitattributesrisk surface

•Suspicious network references — raw IP URL (31 URLs) · awslabs-mcp-6d289e1/src/aws-api-mcp-server/README.mdexpected

•Unrecognized file type — '.typed' is not on the allowlist · awslabs-mcp-6d289e1/src/aws-api-mcp-server/awslabs/aws_api_mcp_server/core/common/py.typedrisk surface

•Suspicious network references — raw IP URL (33 URLs) · awslabs-mcp-6d289e1/src/aws-api-mcp-server/tests/middleware/test_http_header_validation_middleware.pyexpected

•Suspicious network references — raw IP URL (10 URLs) · awslabs-mcp-6d289e1/src/aws-api-mcp-server/tests/parser/test_parser.pyexpected

•Suspicious network references — raw IP URL (25 URLs) · awslabs-mcp-6d289e1/src/aws-appsync-mcp-server/tests/test_create_datasource.pyexpected

•Suspicious network references — suspicious TLD (6 URLs) · awslabs-mcp-6d289e1/src/aws-documentation-mcp-server/awslabs/aws_documentation_mcp_server/server_aws_cn.pyexpected

•Suspicious network references — suspicious TLD (2 URLs) · awslabs-mcp-6d289e1/src/aws-documentation-mcp-server/tests/test_aws_cn_get_available_services_live.pyexpected

•Suspicious network references — suspicious TLD (3 URLs) · awslabs-mcp-6d289e1/src/aws-documentation-mcp-server/tests/test_aws_cn_read_documentation_live.pyexpected

•Suspicious network references — raw IP URL, suspicious TLD (14 URLs) · awslabs-mcp-6d289e1/src/aws-documentation-mcp-server/tests/test_server_aws_cn.pyexpected

•Suspicious network references — raw IP URL (83 URLs) · awslabs-mcp-6d289e1/src/aws-documentation-mcp-server/tests/test_util.pyexpected

•Suspicious network references — suspicious TLD (7 URLs) · awslabs-mcp-6d289e1/src/aws-healthomics-mcp-server/tests/test_workflow_management.pyexpected

•Unrecognized file type — '.guard' is not on the allowlist · awslabs-mcp-6d289e1/src/aws-iac-mcp-server/awslabs/aws_iac_mcp_server/data/default_guard_rules.guardrisk surface

✔ verified source · pinned awslabs-mcp-6d289e1

Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/aws-mcp-servers/check). Click a policy:

Consume AWS MCP Servers programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/aws-mcp-servers

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/aws-mcp-servers/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add aws-mcp-servers

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/aws-mcp-servers/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "aws-mcp-servers" })

OpenAPI spec →