# Obscurify.ai (npm · @obscurify/mcp)

Ask 200+ AI models privately from your agent: one-shot, chat, second opinions, prices, images.

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@obscurify/mcp`: 82/100 (this document), [markdown](https://verifymcp.io/servers/obscurify-ai-obscurify-mcp/obscurify-mcp.md), [page](https://verifymcp.io/servers/obscurify-ai-obscurify-mcp/obscurify-mcp)

## Channel facts

- Registry: `npm`
- Package: `@obscurify/mcp`
- Version: `0.1.0`
- 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 2026-11-05.

- **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.
  - 30 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Obscurify-ai/obscurify-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1371 tokens (~228/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 7 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 Obscurify.ai MCP server?

Obscurify.ai runs locally as an npm package, launched with npx -y @obscurify/mcp. 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 obscurify-ai-obscurify-mcp -- npx -y @obscurify/mcp
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "obscurify-ai-obscurify-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@obscurify/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add obscurify-ai-obscurify-mcp -- npx -y @obscurify/mcp
```

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

```json
{
  "McpServers": {
    "obscurify-ai-obscurify-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@obscurify/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add obscurify-ai-obscurify-mcp -t stdio -c npx -a -y @obscurify/mcp
```

### Other

```json
{
  "mcpServers": {
    "obscurify-ai-obscurify-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@obscurify/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.

### 2026-11-04 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 79)

First indexed and scored.

## MCP tools (6)

### `ask` (~300 tokens)

Ask a model

Send one prompt to any Obscurify.ai model and get its reply. Useful for delegating a subtask to a cheaper or specialised model, getting an outside view, or using a model you don't otherwise have. Prompts go through zero-data-retention routes and are not stored by Obscurify.ai. Default model: deepseek/deepseek-v4-flash (fast and cheap). Use list_models to find other model IDs. For follow-ups that need earlier turns use chat; to compare several models use second_opinion.

Input parameters:

- `max_tokens` (integer): Cap on the reply length in tokens (default 4096). Reasoning models spend some of these thinking.
- `model` (string): Model ID such as "anthropic/claude-sonnet-5.5" or "openai/gpt-5.5". Default: deepseek/deepseek-v4-flash.
- `prompt` (string, required): The full prompt. The model sees nothing else, so include any context it needs.
- `reasoning_effort` (string): How hard a reasoning model should think. Ignored by models without reasoning. Omit for the model's default.
- `show_reasoning` (boolean): Include the model's reasoning text, when it returns one (default false).
- `system` (string): Optional system prompt.
- `temperature` (number): Sampling temperature, 0-2. Omit for the model's default.

### `chat` (~213 tokens)

Multi-turn chat

Continue a multi-turn conversation with an Obscurify.ai model. Pass the whole history in `messages` (the server keeps no state) and get the next assistant reply. For a single question, ask is simpler. Default model: deepseek/deepseek-v4-flash.

Input parameters:

- `max_tokens` (integer): Cap on the reply length in tokens (default 4096). Reasoning models spend some of these thinking.
- `messages` (array, required): Conversation so far, oldest first. The last message is usually from the user.
- `model` (string): Model ID. Default: deepseek/deepseek-v4-flash.
- `reasoning_effort` (string): How hard a reasoning model should think. Ignored by models without reasoning. Omit for the model's default.
- `show_reasoning` (boolean): Include the model's reasoning text, when it returns one (default false).
- `temperature` (number): Sampling temperature, 0-2. Omit for the model's default.

### `second_opinion` (~205 tokens)

Second opinion from several models

Send the same prompt to 2-5 different models at once and return every answer side by side, so you can compare them, check a claim, review code or a plan, or break a tie. Default models: deepseek/deepseek-v4-flash, meta-llama/llama-3.3-70b-instruct, qwen/qwen3.8-27b.

Input parameters:

- `max_tokens` (integer): Cap on the reply length in tokens (default 4096). Reasoning models spend some of these thinking.
- `models` (array): Model IDs to ask (2-5). Pick different families for independent views.
- `prompt` (string, required): The full prompt, with all the context the models need.
- `reasoning_effort` (string): How hard a reasoning model should think. Ignored by models without reasoning. Omit for the model's default.
- `system` (string): Optional system prompt for every model.

### `list_models` (~234 tokens)

List models

List Obscurify.ai chat models with their IDs, context window, price per million input/output tokens (USD), tool-calling support and the plan they need (any = every account with a balance; casual = Casual or Pro; pro = Pro only). Filter by name, plan, price or tool support. Use it to find a model ID for ask, chat or second_opinion, or the cheapest model with what you need. Doesn't need an API key.

Input parameters:

- `limit` (integer): Max rows (default 60).
- `max_output_price` (number): Only models whose output price is at most this many USD per million tokens.
- `plan` (string): Only models usable on this plan: any (Pay As You Go and up), casual, or pro (everything).
- `search` (string): Case-insensitive text to match in the model ID or name, e.g. "claude", "deepseek", "coder".
- `sort` (string): Sort order (default id). price = cheapest output first.
- `tools_only` (boolean): Only models that support tool/function calling.

### `generate_image` (~219 tokens)

Generate an image

Generate an image from a text prompt with Obscurify.ai's Stable Diffusion image models (SDXL, SD 1.5 and LCM checkpoints). Returns the image. Costs a fraction of a cent per image from the account balance. Pass `list: true` to see the available image models and prices instead.

Input parameters:

- `height` (integer): Height in pixels (default: the model's).
- `list` (boolean): List image models and prices instead of generating.
- `model` (string): Image model ID (default "realvis-xl-v4", photorealistic). Others include "juggernaut-xl-v10" and "animagine-xl-v-3-1" (anime). Use list: true for all.
- `negative_prompt` (string): Things to keep out of the image.
- `prompt` (string): What to draw. Required unless list is true.
- `seed` (integer): Seed for reproducible results.
- `width` (integer): Width in pixels (default: the model's).

### `balance` (~70 tokens)

Account balance and plan

Show the Obscurify.ai account's balance (USD), plan, included credit used this billing period, token usage, and whether it can use frontier and uncensored models. Use it before a large batch of calls, or when a call fails with a balance (402) or plan (403) error.

## Diagnostics

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

## Score history

- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 80
- 2026-10-31: 80
- 2026-10-30: 79
- 2026-10-29: 79
- 2026-10-28: 79

## Common questions

### What is the Obscurify.ai MCP server?

Obscurify.ai is an MCP server listed in the public MCP registry as io.github.Obscurify-ai/obscurify-mcp. Ask 200+ AI models privately from your agent: one-shot, chat, second opinions, prices, images. This page covers its npm package (@obscurify/mcp).

### Is the Obscurify.ai MCP server safe to use?

Obscurify.ai scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 Obscurify.ai MCP server expose?

Obscurify.ai exposes 6 tools: ask, chat, second_opinion, list_models, generate_image, balance. Their descriptions and schemas cost roughly 1,241 tokens of context every time the server is loaded.

### Is the Obscurify.ai MCP server still maintained?

Obscurify.ai is still listed as active in the MCP registry. We last reached this channel on 5 November 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 Obscurify.ai MCP server under?

Obscurify.ai 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/@obscurify/mcp
- Socket report: https://socket.dev/npm/package/@obscurify/mcp
- Repository: https://github.com/Obscurify-ai/obscurify-mcp
- Website: https://obscurify.ai/?utm_source=mcp
- Changelog RSS feed: https://verifymcp.io/servers/obscurify-ai-obscurify-mcp/obscurify-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/obscurify-ai-obscurify-mcp/obscurify-mcp.json
- HTML version of this page: https://verifymcp.io/servers/obscurify-ai-obscurify-mcp/obscurify-mcp