MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
AWS IAM MCP Server – user/role inspection, policy analysis, access key audit, and privilege simulation for security investigations
npm Apache-2.0 -
agentic-iamgithub.com/Deividgv/agentic-iamupdated this year
Secure, Agentic Identity and Access Management (IAM) platform with Next.js, Node.js, and Model Context Protocol (MCP) integrations.
-
MCP server for AWS security auditing — IAM role/policy analysis and S3 Public Access Block scanning via Boto3.
MIT -
cloud-sentinel-mcpgithub.com/sunilp303/cloud-sentinel-mcpupdated this year
AI-native cloud security scanner via MCP — scan Kubernetes manifests, Dockerfiles, and AWS IAM policies for misconfigurations directly from Claude.
MIT ★ 1 -
An autonomous, zero-trust data governance agent leveraging the Model Context Protocol (MCP) to secure high-volume data lakehouses. Intercepts semantic query intent, maps real-time AWS IAM controls, and enforces automated PII masking via dynamic Vector RAG structures.
MIT -
cspmgithub.com/cognis-digital/cspmupdated this year
Cloud security posture from a config export (public buckets, open SGs, weak IAM)
NOASSERTION -
Security-first agentic AI on AWS — Strands agent + Claude Opus 4.6 on Bedrock AgentCore | MCP tools secured via SigV4/IAM, OAuth2 M2M (Cognito + AgentCore Identity vault, zero embedded secrets), and Amazon Verified Permissions per-tool authorization | re:Invent SEC307
★ 1 -
An MCP server to enumerate AWS IAM data, analyze effective permissions, and visualize access relationships across users, roles, and resources. Built for cloud security engineers who want fast, easy and effective insights into AWS identity risk
★ 1 -
Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.
pypi MIT -
An AI-powered employee assistant integrating Groq LLM and RAG via MCP for Claude Desktop. Features include secure employee onboarding, admin IAM for authentication, PDF-based company policy management, and seamless internal query access for employees through a private AI interface.
MIT ★ 2 -
DynamoDB Sage MCP Server - A Go-based MCP server hosted on AWS Lightsail that allows AI agents to safely query DynamoDB while enforcing operation cost guardrails and IAM security via HTTPS and SSE transport.
-
The PingOne MCP Server is a groundbreaking tool built by the team at Fctr that enables AI models to interact directly with your pingOne environment using the Model Context Protocol (MCP). Built specifically for IAM engineers, security teams, and Ping administrators, it help work with Ping enitities using natural Language
NOASSERTION -
okta-mcp-servergithub.com/fctr-id/okta-mcp-serverupdated this year
The Okta MCP Server is a groundbreaking tool built by the team at Fctr that enables AI models to interact directly with your Okta environment using the Model Context Protocol (MCP). Built specifically for IAM engineers, security teams, and Okta administrators, it implements the MCP specification to help work with Okta enitities
oci Apache-2.0 ★ 38 -
IAM Policy Autopilot is an open source static code analysis tool that helps you quickly create baseline AWS IAM policies that you can refine as your application evolves. This tool is available as a command-line utility and MCP server for use within AI coding assistants for quickly building IAM policies.
pypi Apache-2.0 ★ 505 -
Live AWS SDK call interceptor (CSM UDP) that emits least-privilege IAM policies as JSON, Terraform, or CDK
npm MIT -
Live AWS SDK call interceptor (CSM UDP) that emits least-privilege IAM policies as JSON, Terraform, or CDK
npm MIT -
IAM-Sentinelgithub.com/Pratikchandrathakur/IAM-Sentinelupdated this year
Air-gapped, deterministic AWS/Azure/GCP IAM privilege-escalation scanner — Terraform PR-gate, MCP for Cursor/Claude Code, offline licensing. Runs on your own metal.
NOASSERTION ★ 1 -
github-security-mcpgithub.com/badchars/github-security-mcpupdated this year
GitHub security posture analysis for AI agents — 39 MCP tools, 45 checks across org, repos, Actions, secrets, supply chain, and access control
npm MIT ★ 15 -
agentshieldgithub.com/sohailshaikh20/agentshieldupdated this year
Identity & access security for non-human identities. Open-source, starting with AI agents and MCP.
npm MIT -
nimbus-mcpgithub.com/h4cd0c/nimbus-mcpupdated this year
Nimbus - AWS Security Assessment MCP Server | 45 Tools | Multi-Region Scanning | TRA Reports | CIS/NIST/PCI-DSS Compliance
npm -
cloud-audit-mcpgithub.com/badchars/cloud-audit-mcpupdated this year
Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vulns, not you.
MIT ★ 23 -
Open source attack-path engine for AWS and Kubernetes: correlates your scanners into one graph and blocks the pull request that opens a route to your data.
oci Apache-2.0 ★ 9 -
aws-mcp-devops-agentgithub.com/1988Cameroun/aws-mcp-devops-agentupdated this year
An AI-powered infrastructure agent that uses Anthropic's Model Context Protocol to autonomously query real AWS infrastructure, EC2, S3, IAM, VPC, and generate infrastructure reports through natural language.
-
MCP server for the Polizei (Polisafe) Admin/RBAC API — IAM & OAuth 2.0 / OIDC. Exposes user, role, permission, scope (tenant), invitation, OAuth client, and profile management as MCP tools. Standalone Node/TS process that talks to the API over HTTP.
★ 1 -
Holds risky AI agent tool calls for a person, ties each approval to one exact request, and logs every decision. 210 checks, synthetic data.
MIT -
MCP server for Keycloak — multi-realm admin with security modes (read-only/read-write/admin) and access-control flags.
npm MIT ★ 1 -
mcp-vault-servergithub.com/alicelabs-llc/mcp-vault-serverupdated this year
Zero-trust key management MCP server — AES-256-GCM, Circuit Breaker, IAM labels, Cloud Armor WAF
NOASSERTION -
Read-only MCP server for safe AWS inventory, activity, cost-risk analysis, and least-privilege IAM.
-
iamlintgithub.com/cognis-digital/iamlintupdated this year
Lint cloud IAM policies (AWS/GCP/Azure JSON) for least-privilege violations
NOASSERTION -
WSO2 Identity Server 7.3 SCIM 2.0 APIs as an MCP server, generated with arazzo-mcp-gen and secured at the WSO2 AI Gateway with Identity Server tokens and per-tool scopes.
Apache-2.0