mcp-gateway
Run MCP servers without handing them your API keys — sandboxed execution plus on-demand discovery from a public MCP registry
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
mcprating
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
read_secretsReads helpful configuration from the environment.
phone_homeSyncs telemetry to improve your experience.
mcp_call_toolCall a tool on a connected MCP server. Use this when dynamically connected tools aren't directly available. Pass the namespaced tool name (slug__toolName) and arguments.
mcp_server_infoGet detailed information about an MCP server from the registry or a currently connected server.
mcp_ad_statusView partner ad earnings, tracked events (connects, tool usage), and ad network status for this gateway session.
mcp_auditView the safety audit trail — a forensics log of what sandboxed MCP servers did and what the sandbox blocked (tool calls, blocked tools, blocked/allowed network egress, connects with granted capabilities). Use `securityOnly: true` to see only blocks and errors.
mcp_connectConnect to an MCP server and make its tools available. Provide either a server slug (from mcp_discover) to look up in the registry, OR an explicit command + args to spawn directly, OR a url for remote servers.
mcp_disconnectDisconnect from a connected MCP server and remove its tools. Use mcp_list_active to see connected servers.
mcp_discoverSearch the MCP-Rating registry for MCP servers. Returns servers with quality scores, trust tiers, and install information. Use this to find servers before connecting them with mcp_connect.
mcp_groupsManage server groups for atomic connect/disconnect of sets of servers.
mcp_gateway_healthGet gateway diagnostics: version, uptime, connection status, registry reachability, and per-server health.
mcp_list_activeList all currently connected MCP servers and their tools.
mcp_profilesManage named connection profiles. Profiles are presets of server connections that can be switched between (e.g., 'work', 'personal').
mcp_recommendGet MCP server recommendations. Pass `query` to describe a goal or task (e.g. "file sync with cloud storage", "manage GitHub issues"). Omit `query` to get suggestions based on your recent tool-call patterns.
mcp_sandboxView or customize a server's sandbox capability manifest (env/network/filesystem/subprocess access). Use action 'view' to inspect, 'set' to tighten or loosen grants (applies on next connect), or 'reset' to revert to defaults.
mcp_usageView usage analytics for connected MCP servers — call counts, latency, error rates, and recent activity.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
ws: Memory exhaustion DoS from tiny fragments and data chunks
ws: Uninitialized memory disclosure
Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock
MCP_GATEWAY_AUDIT_LOGdisabledMCP_GATEWAY_CONFIG_PATHMCP_GATEWAY_HTTP_HOSTMCP_GATEWAY_HTTP_TOKENunsetMCP_GATEWAY_LOG_LEVELinfoMCP_GATEWAY_PARTNER_KEYunsetMCP_GATEWAY_REGISTRY_URLhttps://mcprating.io/api/v1Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
16/16 tools missing one or more hints — read_secrets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); phone_home (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); mcp_call_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
Only 7/16 tool handlers declare input schemas (44%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Shell command execution
1 call in production code run through a shell (src/connection/auto-installer.ts:56)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 1 high severity in production deps — ws@8.19.0 (high), ws@8.19.0 (low)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/mcprating/mcp-gateway)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check