Field-by-field comparison
Compare the evidence before choosing an MCP.
Each signal stays separate, missing facts remain visible, and the column order follows your selection.
| Evidence field | Official MCP Rust SDKMCP100 Selected | Docker MCP GatewayMCP100 Selected |
|---|---|---|
| Task fit | ||
| Best for |
|
|
| Not ideal for |
|
|
| Avoid when |
|
|
| Provenance | ||
| Provenance details | First-party MCP Model Context Protocol project · Publisher source ↗ | First-party MCP Docker · Publisher source ↗ |
| Maintenance | ||
| Maintenance details | Repo: Not documented Package: Not documented | Repo: Aug 13, 2026 Package: Not documented |
| Popularity evidence | ||
| GitHub stars | Not documented | 1,529 GitHub stars · checked 2026-08-14T18:46:26.000Z |
| Client coverage | ||
| Client coverage details | Not documented | Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio |
| Client coverage note | Local stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server. | |
| Access and data | ||
| Authentication | The SDK provides protocol/client/server primitives; authentication is chosen by the application. Current SDK lines include support for MCP transport/auth mechanisms where applicable. | The gateway handles downstream server credentials and OAuth flows. The client connects locally over stdio by running `docker mcp gateway run`, optionally with a named profile. |
| Cost | Open-source SDK; runtime, hosting, APIs, and external services may have separate costs. | The open-source gateway documents no standalone usage fee. Docker Desktop licensing, Docker AI Governance invite-only features, container infrastructure, downstream MCP services, and AI-client charges may apply. |
| Permissions | The SDK itself does not grant external permissions. Applications decide which tools/resources are exposed and what credentials they use. | The gateway exposes the servers and tools included in the selected profile. It starts catalog servers in containers with restricted privileges, network access, and resource usage, injects configured secrets, and can support OAuth. Dynamic MCP can additionally expose tools that discover, add, configure, remove, and execute servers during a session. |
| Data handling | Data flow is application-defined: MCP messages, tool inputs/outputs, resources, prompts, and any downstream system data handled by the app. | Tool requests and results pass through the local gateway to downstream MCP containers or remote services. Docker documents built-in logging and call tracing. Credentials are managed and injected by the gateway; downstream servers can still receive data and reach networks allowed by their configuration. |
| Limitations | ||
| Tradeoffs |
|
|
| Risk context | Medium. Main risks are application misconfiguration, dependency/supply-chain issues, overly broad tools, exposed transports, and unsafe downstream actions. | Gateway safety is only as strong as the selected profile, catalog provenance, tool filters, network policy, and downstream credentials. Disable experimental Dynamic MCP unless required, use narrow profiles, verify signatures where available, inspect traces, and treat each downstream server as a separate trust decision. This review does not claim MCP100 execution testing. |
| Evidence date | ||
| Editorial review | 2026-09-11 | 2026-07-24 |
| Candidate evidence | 2026-09-11T00:00:00.000Z | 2026-08-14T18:46:26.000Z |
Popularity, maintenance, fit, permissions, and client support are independent evidence fields.
Read the evidence method →