# ai.spideriq/gate (npm · @spideriq/mcp-gate)

SpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)

- Trust score: 63/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@spideriq/mcp-gate`: 63/100 (this document), [markdown](https://verifymcp.io/servers/ai-spideriq-gate/spideriq-mcp-gate.md), [page](https://verifymcp.io/servers/ai-spideriq-gate/spideriq-mcp-gate)

## Channel facts

- Registry: `npm`
- Package: `@spideriq/mcp-gate`
- Version: `1.3.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (100 of 104), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (100 of 104), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1380 tokens (~72/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ai-spideriq-gate -- npx -y @spideriq/mcp-gate
```

### Codex

```bash
codex mcp add ai-spideriq-gate -- npx -y @spideriq/mcp-gate
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-spideriq-gate --command npx --arg -y --arg @spideriq/mcp-gate
```

### Hermes

```yaml
mcp_servers:
  ai-spideriq-gate:
    command: "npx"
    args: ["-y", "@spideriq/mcp-gate"]
```

### Other

```json
{
  "mcpServers": {
    "ai-spideriq-gate": {
      "command": "npx",
      "args": [
        "-y",
        "@spideriq/mcp-gate"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 63, +34)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional] Licence: MIT

### 2026-08-01 (score 29, +29)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass

### 2026-07-31 (score 0, −42)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 42, −30)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-29 (score 72, +53)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-07-28 (score 19, −21)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (19)

### `request_access` (~120 tokens)

Request access to SpiderIQ API. This sends an approval email to the admin.
After calling this, use check_access_status to poll for approval.
Once approved, the token is automatically saved for subsequent API calls.

Input parameters:

- `api_url` (string): API URL (default: https://spideriq.ai)
- `email` (string, required): Admin email address (the person who will approve access)
- `project` (string): Project name (shown in approval email)
- `scopes` (array): Requested permission scopes (default: jobs:submit, jobs:read)

### `check_access_status` (~152 tokens)

Check the status of a PAT access request.
Returns 'pending', 'active', 'denied', 'expired', or 'revoked' (matches the
backend PATRequestStatus enum). Once status==='active', the token is saved to
\~/.spideriq/credentials.json automatically. Multi-brand approvals save one
entry per workspace under client_id, with the first aliased as 'default' so
existing tools (upload_local_file, etc.) keep working without --workspace.

Input parameters:

- `api_url` (string): API URL (default: https://spideriq.ai)
- `poll_token` (string, required): Poll token from request_access
- `request_id` (string, required): Request ID from request_access

### `get_auth_status` (~33 tokens)

Check if you are authenticated and get current user info.

Input parameters:

- `workspace` (string): Workspace name (default: default)

### `logout` (~25 tokens)

Remove stored authentication credentials.

Input parameters:

- `workspace` (string): Workspace name (default: default)

### `list_workspaces` (~19 tokens)

List all configured workspaces and their authentication status.

### `health_check` (~51 tokens)

Check if the SpiderIQ API is healthy and responsive.

Input parameters:

- `api_url` (string): API URL (default: https://spideriq.ai)
- `workspace` (string): Workspace name (default: default)

### `get_queue_stats` (~48 tokens)

Get statistics about job queues (pending jobs, consumers, etc.).

Input parameters:

- `format` (string): Response format (default: json)
- `workspace` (string): Workspace name (default: default)

### `get_api_info` (~33 tokens)

Get information about the SpiderIQ API and your connection.

Input parameters:

- `workspace` (string): Workspace name (default: default)

### `gate_chat` (~411 tokens)

Send a chat completion via SpiderGate LLM gateway (OpenAI-compatible).
Use task aliases like "spideriq/fast", "spideriq/coding", "spideriq/research" or specific model IDs.
Supports JSON mode (response_format), tool/function calling (tools/tool_choice), and SpiderGate
extras via spidergate_options — { max_cost_usd } caps the per-request spend, { cache_enabled } caches
identical prompts, { fallback_models } extends the alias chain. The response carries
spidergate_metadata.cost_usd (the real per-call dollar cost) and provider_model (what actually served).
NEVER send client PII on a free-tier alias (spideriq/fast,/free,/extraction) — use spideriq/lead-analysis.

Input parameters:

- `max_tokens` (number): Max tokens to generate.
- `messages` (array, required): Chat messages
- `model` (string, required): Model or task alias (e.g., "spideriq/fast", "spideriq/coding")
- `response_format` (object): Structured output: {"type":"json_object"} or {"type":"json_schema","json_schema":{...}}.
- `seed` (number): Random seed for reproducibility.
- `spidergate_options` (object): SpiderGate extras: { max_cost_usd, cache_enabled, cache_ttl_seconds, fallback_models, preferred_providers, excluded_providers, timeout_ms, retry_count }.
- `stop`: Stop sequence(s) — a string or array of strings.
- `temperature` (number): Sampling temperature 0.0–2.0 (default 1.0).
- `tool_choice`: "none" | "auto" | "required" | {type:"function",function:{name}}.
- `tools` (array): OpenAI tool/function definitions for tool calling.
- `top_p` (number): Nucleus sampling 0.0–1.0.
- `workspace` (string): Workspace name

### `gate_models` (~30 tokens)

List all available LLM models on SpiderGate with usage stats.

Input parameters:

- `workspace` (string): Workspace name

### `gate_aliases` (~42 tokens)

List SpiderGate task aliases (spideriq/fast, spideriq/coding, etc.) with their model chains.

Input parameters:

- `workspace` (string): Workspace name

### `gate_health` (~25 tokens)

Check SpiderGate LLM gateway health.

Input parameters:

- `workspace` (string): Workspace name

### `gate_stats` (~43 tokens)

Get your brand's SpiderGate overview — active agents, total requests, spend.

Input parameters:

- `brand_id` (string, required): Brand ID
- `workspace` (string): Workspace name

### `gate_usage` (~65 tokens)

Get your brand's usage analytics — requests, tokens, cost by model/provider/day.

Input parameters:

- `brand_id` (string, required): Brand ID
- `days` (number): Time window in days (default: 7, max: 90)
- `workspace` (string): Workspace name

### `gate_agents` (~43 tokens)

List your brand's agent tokens with budgets, rate limits, and model access.

Input parameters:

- `brand_id` (string, required): Brand ID
- `workspace` (string): Workspace name

### `gate_providers` (~38 tokens)

List available LLM providers with logos and descriptions.

Input parameters:

- `brand_id` (string, required): Brand ID
- `workspace` (string): Workspace name

### `gate_traces` (~104 tokens)

List LLM request traces for your brand — filter by agent, model, status, date.

Input parameters:

- `agent_id` (string): Filter by agent ID
- `brand_id` (string, required): Brand ID
- `limit` (number): Max results (default: 20)
- `model` (string): Filter by model name
- `offset` (number): Offset for pagination
- `status` (string): Filter by status
- `workspace` (string): Workspace name

### `gate_trace_detail` (~52 tokens)

Get full trace detail with spans, input/output messages, and timing.

Input parameters:

- `brand_id` (string, required): Brand ID
- `trace_id` (string, required): Trace ID
- `workspace` (string): Workspace name

### `gate_trace_stats` (~46 tokens)

Get aggregated trace statistics — total traces, success/error counts, p95 latency, cost.

Input parameters:

- `brand_id` (string, required): Brand ID
- `workspace` (string): Workspace name

## Diagnostics

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

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 29
- 2026-07-31: 0
- 2026-07-30: 42
- 2026-07-29: 72
- 2026-07-28: 19
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/@spideriq/mcp-gate
- Socket report: https://socket.dev/npm/package/@spideriq/mcp-gate
- Changelog RSS feed: https://verifymcp.io/servers/ai-spideriq-gate/spideriq-mcp-gate/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-spideriq-gate/spideriq-mcp-gate/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-spideriq-gate/spideriq-mcp-gate