# io.mcprating/gateway (npm · @mcp-rating/gateway)

Discover, judge and safely run any MCP server: 57k+ scored servers, sandboxed.

- Trust score: 91/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- npm · `@mcp-rating/gateway`: 91/100 (this document), [markdown](https://verifymcp.io/servers/io-mcprating-gateway/mcp-rating-gateway.md), [page](https://verifymcp.io/servers/io-mcprating-gateway/mcp-rating-gateway)

## Channel facts

- Registry: `npm`
- Package: `@mcp-rating/gateway`
- Version: `0.2.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 97 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to mcprating/mcp-gateway).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1903 tokens (~146/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.mcprating/gateway MCP server?

io.mcprating/gateway runs locally as an npm package, launched with npx -y @mcp-rating/gateway. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add io-mcprating-gateway -- npx -y @mcp-rating/gateway
```

### Cursor

```json
{
  "mcpServers": {
    "io-mcprating-gateway": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp-rating/gateway"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-mcprating-gateway": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp-rating/gateway"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add io-mcprating-gateway -- npx -y @mcp-rating/gateway
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-mcprating-gateway": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@mcp-rating/gateway"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-mcprating-gateway --command npx --arg -y --arg @mcp-rating/gateway
```

### Hermes

```yaml
mcp_servers:
  io-mcprating-gateway:
    command: "npx"
    args: ["-y", "@mcp-rating/gateway"]
```

### Netclaw

```json
{
  "McpServers": {
    "io-mcprating-gateway": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@mcp-rating/gateway"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-mcprating-gateway -t stdio -c npx -a -y @mcp-rating/gateway
```

### Other

```json
{
  "mcpServers": {
    "io-mcprating-gateway": {
      "command": "npx",
      "args": [
        "-y",
        "@mcp-rating/gateway"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `mcp_discover` (~100 tokens)

Search 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.

Input parameters:

- `category` (string): Filter by category slug (e.g., 'developer-tools', 'data-databases')
- `limit` (number): Max results (default 10)
- `query` (string, required): Search query (server name, description, or capability)

### `mcp_connect` (~265 tokens)

Connect 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.

Input parameters:

- `args` (array): Command arguments (e.g., ['-y', '@modelcontextprotocol/server-everything'])
- `command` (string): Explicit command to spawn (e.g., 'npx'). Use when server is not in registry.
- `confirmed` (boolean): Set to true to confirm connection to community/unknown trust tier servers. Required when the initial connect returns a confirmation warning.
- `env` (object): Additional environment variables for the server process
- `saveProfile` (boolean): Set to true to save this connection as an auto-connect profile. The server will auto-reconnect on gateway restart.
- `slug` (string): Server slug from MCP-Rating registry (e.g., '@modelcontextprotocol/inspector')
- `transportType` (string): Transport type. Defaults to 'stdio' for command-based, auto-detected from URL scheme if url is provided.
- `url` (string): URL for remote transports (SSE, WebSocket, Streamable HTTP). Use instead of command for remote servers.

### `mcp_disconnect` (~45 tokens)

Disconnect from a connected MCP server and remove its tools. Use mcp_list_active to see connected servers.

Input parameters:

- `slug` (string, required): Server slug of the connected server to disconnect

### `mcp_list_active` (~20 tokens)

List all currently connected MCP servers and their tools.

### `mcp_server_info` (~41 tokens)

Get detailed information about an MCP server from the registry or a currently connected server.

Input parameters:

- `slug` (string, required): Server slug (from registry or connected server)

### `mcp_call_tool` (~89 tokens)

Call 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.

Input parameters:

- `arguments` (object): Tool arguments as a JSON object
- `name` (string, required): Namespaced tool name: "server-slug__tool-name" (as shown by mcp_connect or mcp_list_active)

### `mcp_gateway_health` (~30 tokens)

Get gateway diagnostics: version, uptime, connection status, registry reachability, and per-server health.

### `mcp_sandbox` (~271 tokens)

View 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.

Input parameters:

- `action` (string, required): view = inspect manifest; set = override grants; reset = revert to defaults
- `enforcement` (string): [set] Isolation level. l2-container requires Docker/Podman.
- `envAllow` (array): [set] Environment variable NAMES the server may receive, e.g. ['GITHUB_TOKEN']
- `fsRead` (array): [set] Absolute paths the server may read
- `fsWrite` (array): [set] Absolute paths the server may write
- `network` (string): [set] Network mode. 'none' = no network, 'allowlist' = only listed hosts, 'all' = unrestricted
- `networkAllow` (array): [set] Allowed host:port patterns for allowlist mode, e.g. ['api.github.com:443', '*.example.com']
- `slug` (string, required): Server slug (as shown by mcp_list_active or mcp_discover)
- `subprocess` (boolean): [set] Whether the server may spawn subprocesses

### `mcp_audit` (~129 tokens)

View 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.

Input parameters:

- `event` (string): Filter to a single event type
- `limit` (number): Max events to return (default 50, newest first)
- `securityOnly` (boolean): Show only security-relevant events (blocks + errored calls)
- `slug` (string): Filter to a single server slug

### `mcp_profiles` (~201 tokens)

Manage named connection profiles. Profiles are presets of server connections that can be switched between (e.g., 'work', 'personal').

Input parameters:

- `action` (string, required): Action: list (all profiles), create (new profile), delete, add_server (add a server to profile), remove_server, switch (activate profile), show (details of a profile)
- `args` (array): Command arguments (for add_server with stdio)
- `command` (string): Explicit command for the server (for add_server with stdio)
- `description` (string): Profile description (optional, for create)
- `name` (string): Profile name (required for create, delete, add_server, remove_server, switch, show)
- `slug` (string): Server slug to add/remove from a profile
- `transportType` (string): Transport type (for add_server)
- `url` (string): Server URL (for add_server with SSE/WS/HTTP)

### `mcp_groups` (~171 tokens)

Manage server groups for atomic connect/disconnect of sets of servers.

Input parameters:

- `action` (string, required): Action: list, create, delete, add_server, remove_server, connect (all in group), disconnect (all in group), show (details)
- `args` (array): Command arguments (for add_server with stdio)
- `command` (string): Explicit command for the server (for add_server with stdio)
- `description` (string): Group description (optional, for create)
- `name` (string): Group name (required for all actions except list)
- `slug` (string): Server slug to add/remove from a group
- `transportType` (string): Transport type (for add_server)
- `url` (string): Server URL (for add_server with SSE/WS/HTTP)

### `mcp_usage` (~127 tokens)

View usage analytics for connected MCP servers — call counts, latency, error rates, and recent activity.

Input parameters:

- `action` (string): Action: stats (default — summary), recent (recent calls), slow (slow calls), reset (clear all data)
- `limit` (number): Limit number of results for 'recent' and 'slow' actions (default: 20)
- `slug` (string): Filter stats to a specific server slug. Omit for global stats.
- `threshold` (number): Latency threshold in ms for 'slow' action (default: 5000)

### `mcp_recommend` (~147 tokens)

Get 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.

Input parameters:

- `category` (string): Optional category slug to filter (e.g. 'developer-tools', 'data-databases'). Only used with `query`.
- `limit` (number): Maximum number of recommendations (default 5, max 20)
- `query` (string): Free-text goal or task. When provided, recommends servers that match this intent using semantic/keyword/expansion search. When omitted, recommends based on usage history.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/io-mcprating-gateway/mcp-rating-gateway#diagnostics

## Score history

- 2026-09-21: 91
- 2026-09-20: 91
- 2026-09-19: 90
- 2026-09-18: 90
- 2026-09-17: 89
- 2026-09-16: 89
- 2026-09-15: 88
- 2026-09-14: 88
- 2026-09-13: 87
- 2026-09-12: 87
- 2026-09-11: 86
- 2026-09-10: 86
- 2026-09-09: 85
- 2026-09-08: 85
- 2026-09-07: 85
- 2026-09-06: 84
- 2026-09-05: 84
- 2026-09-04: 83
- 2026-09-03: 83
- 2026-09-02: 82
- 2026-09-01: 82
- 2026-08-31: 81
- 2026-08-30: 81
- 2026-08-29: 80
- 2026-08-28: 80
- 2026-08-27: 49

## Common questions

### What is the io.mcprating/gateway MCP server?

io.mcprating/gateway is an MCP server listed in the public MCP registry as io.mcprating/gateway. Discover, judge and safely run any MCP server: 57k+ scored servers, sandboxed. This page covers its npm package (@mcp-rating/gateway).

### Is the io.mcprating/gateway MCP server safe to use?

io.mcprating/gateway scores 91 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.mcprating/gateway MCP server expose?

io.mcprating/gateway exposes 13 tools: mcp_discover, mcp_connect, mcp_disconnect, mcp_list_active, mcp_server_info, and 8 more. Their descriptions and schemas cost roughly 1,636 tokens of context every time the server is loaded.

### Is the io.mcprating/gateway MCP server still maintained?

io.mcprating/gateway is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.mcprating/gateway MCP server under?

io.mcprating/gateway declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@mcp-rating/gateway
- Socket report: https://socket.dev/npm/package/@mcp-rating/gateway
- Repository: https://github.com/mcprating/mcp-gateway
- Website: https://mcprating.io/gateway
- Changelog RSS feed: https://verifymcp.io/servers/io-mcprating-gateway/mcp-rating-gateway.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-mcprating-gateway/mcp-rating-gateway.json
- HTML version of this page: https://verifymcp.io/servers/io-mcprating-gateway/mcp-rating-gateway