# ai.proxyllm/proxyllm-mcp (npm · proxyllm-mcp)

OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup

- Trust score: 64/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `proxyllm-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/ai-proxyllm-proxyllm-mcp/proxyllm-mcp.md), [page](https://verifymcp.io/servers/ai-proxyllm-proxyllm-mcp/proxyllm-mcp)

## Channel facts

- Registry: `npm`
- Package: `proxyllm-mcp`
- Version: `1.0.2`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 18 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 597 tokens (~66/item across 9 items; 9 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**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 13% 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-proxyllm-proxyllm-mcp -- npx -y proxyllm-mcp
```

### Codex

```bash
codex mcp add ai-proxyllm-proxyllm-mcp -- npx -y proxyllm-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-proxyllm-proxyllm-mcp --command npx --arg -y --arg proxyllm-mcp
```

### Hermes

```yaml
mcp_servers:
  ai-proxyllm-proxyllm-mcp:
    command: "npx"
    args: ["-y", "proxyllm-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "ai-proxyllm-proxyllm-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "proxyllm-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 64, +44)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Stability: unverified → 0.27
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-02 (score 20, +14)

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

### 2026-08-01 (score 6, −25)

- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-07-31 (score 31, −2)

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

### 2026-07-30 (score 33, −40)

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

### 2026-07-29 (score 73, +47)

- [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 26, −16)

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

### 2026-07-27 (score 42)

First indexed and scored.

## MCP tools (9)

### `proxyllm_savings_calculator` (~76 tokens)

LLM spend: API vs subscription math

Given a monthly OpenAI API bill in USD, returns the ChatGPT/Codex subscription tier that absorbs that workload through ProxyLLM Codex Hosted, the flat total (subscription + $129 fee), and the monthly savings. Free, no auth.

Input parameters:

- `monthly_openai_bill_usd` (number, required)

### `proxyllm_list_models` (~50 tokens)

List models

OpenAI-shaped model list from the gateway. No auth required; with a routing key it reflects that key's lanes, including the live Codex catalog.

Input parameters:

- `routing_key` (string)

### `proxyllm_introspect_key` (~57 tokens)

Introspect a routing key

GET /v1/key: the key's provider lanes, reachable models, whether a Codex subscription backs it, and monthly budget state. Authed by the routing key itself.

Input parameters:

- `routing_key` (string)

### `proxyllm_signup` (~86 tokens)

Create a ProxyLLM account (email OTP)

Starts autonomous account creation: a 6-digit code is emailed to the operator's inbox (no captcha, no browser). New accounts are unpaid and are removed after 48 hours unless a human activates the membership. Follow with proxyllm_verify_signup.

Input parameters:

- `email` (string, required): The human operator's email
- `source` (string): Attribution slug; defaults to mcp

### `proxyllm_verify_signup` (~72 tokens)

Verify the emailed code, receive the account token

Exchanges the 6-digit code for an sk_ account token. The token is returned exactly once: store it (PROXYLLM_ACCOUNT_TOKEN). While the account is unpaid the response carries a checkout link to relay to the operator.

Input parameters:

- `code` (string, required)
- `email` (string, required)

### `proxyllm_account` (~59 tokens)

Account state (poll until paid)

GET /v1/organizations/me. Works while unpaid: plan is "free" plus a payment block until the operator activates the membership, then "pro". Poll this after handing over the checkout link.

Input parameters:

- `account_token` (string)

### `proxyllm_create_routing_key` (~103 tokens)

Create a routing key

Mints a pllm_ routing key (returned once) for OPENAI_API_KEY-style use against the gateway. Optionally wires the provider chain in the same call; discover wireable lane ids with proxyllm_list_routing_keys include_lanes.

Input parameters:

- `account_token` (string)
- `label` (string)
- `mode` (string)
- `monthly_budget_usd` (number)
- `providers` (array)

### `proxyllm_list_routing_keys` (~64 tokens)

List routing keys (and wireable lanes)

Lists the account's routing keys. include_lanes adds the wireable lanes (connected Codex sessions, bridges, saved provider keys) with the ids provider chains reference.

Input parameters:

- `account_token` (string)
- `include_lanes` (boolean)

### `proxyllm_usage` (~30 tokens)

30-day usage summary

GET /v1/organizations/usage for the account.

Input parameters:

- `account_token` (string)

## Diagnostics

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

## Score history

- 2026-08-03: 64
- 2026-08-02: 20
- 2026-08-01: 6
- 2026-07-31: 31
- 2026-07-30: 33
- 2026-07-29: 73
- 2026-07-28: 26
- 2026-07-27: 42

## Links

- npm package: https://www.npmjs.com/package/proxyllm-mcp
- Socket report: https://socket.dev/npm/package/proxyllm-mcp
- Repository: https://github.com/proxyllm-ai/proxyllm-mcp
- Website: https://proxyllm.ai/docs/api
- Changelog RSS feed: https://verifymcp.io/servers/ai-proxyllm-proxyllm-mcp/proxyllm-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-proxyllm-proxyllm-mcp/proxyllm-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-proxyllm-proxyllm-mcp/proxyllm-mcp