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.
-
databricks-mcp-agentgatewaygithub.com/christian-posta/databricks-mcp-agentgatewayupdated this year
—
-
mcp-hack26-tia-connect-agentgatewaygithub.com/feelautom/mcp-hack26-tia-connect-agentgatewayupdated this year
MCP_HACK//26 — Industrial Zero-Trust AI: T-IA Connect + AgentGateway for Siemens TIA Portal
★ 10 -
Reference implementation: one MCP agent shared by many tenants, where every tool call gets a 30-second PostgreSQL credential, handed over as a single-use OpenBao wrapping token and limited to one tenant by row-level security. Keycloak, SPIRE, Agentgateway, OPA, OpenBao and kagent on a local kind cluster.
-
—
Apache-2.0 -
Multi-tenant memory for AI agents as an MCP server: Postgres + pgvector, markdown or pure-vector modes, tenant enforced by the gateway and row-level security
Apache-2.0 -
shieldnet-mcpgithub.com/hhhashexe/shieldnet-mcpupdated this year
ShieldNet Security Scanner — MCP Server for AI Agent Security Governance. Scans URLs for XSS, SQLi, SSTI, CORS misconfig, missing headers, info disclosure, and more. Returns ALLOW/WARN/BLOCK governance decisions.
npm MIT