Name: Obscurify.ai
Author: Obscurify-ai

Obscurify.ai MCP

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

Grade A Local · stdio API key 6 tools v0.1.0 MIT

No reviews yet by Obscurify-ainpm Runs on your machine, nothing hosted

97/100

trust score

tools declared

local

runs on your machine

—

downloads a day

What it does

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

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'OBSCURIFY_API_KEY=${OBSCURIFY_API_KEY}' --transport stdio obscurify-ai-mcp '--' npx -y @obscurify/mcp

# 2 — ask your agent for something these tools do
#   ask, chat, second_opinion and 3 more

It needs OBSCURIFY_API_KEY: this reads it from your environment, so export it first.

Obscurify.ai costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

Obscurify-ai1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Obscurify.ai as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads OBSCURIFY_API_KEY (Obscurify.ai API key (sk-obs1_...) from obscurify.ai/account) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx OBSCURIFY_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'OBSCURIFY_API_KEY=${OBSCURIFY_API_KEY}' --transport stdio obscurify-ai-mcp '--' npx -y @obscurify/mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: OBSCURIFY_API_KEY — Obscurify.ai API key (sk-obs1_...) from obscurify.ai/account. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Send one prompt to any Obscurify.ai model and get its reply. Useful for delegating a subtask to a cheaper or

Parameter	Type	Required	Notes
prompt	string	yes	The full prompt. The model sees nothing else, so include any context it needs.
model	string	no	Model ID such as "anthropic/claude-sonnet-5.5" or "openai/gpt-5.5". Default: ….
system	string	no	Optional system prompt.
reasoning_effort	string	no	How hard a reasoning model should think. Ignored by models without reasoning. Omit for the model's default.
max_tokens	integer	no	Cap on the reply length in tokens (default 4096). Reasoning models spend some of these thinking.
temperature	number	no	Sampling temperature, 0-2. Omit for the model's default.
show_reasoning	boolean	no	Include the model's reasoning text, when it returns one (default false).

Continue a multi-turn conversation with an Obscurify.ai model. Pass the whole history in messages

Parameter	Type	Required	Notes
messages	array	yes	Conversation so far, oldest first. The last message is usually from the user.
model	string	no	Model ID. Default: ….
reasoning_effort	string	no	How hard a reasoning model should think. Ignored by models without reasoning. Omit for the model's default.
max_tokens	integer	no	Cap on the reply length in tokens (default 4096). Reasoning models spend some of these thinking.
temperature	number	no	Sampling temperature, 0-2. Omit for the model's default.
show_reasoning	boolean	no	Include the model's reasoning text, when it returns one (default false).

Send the same prompt to 2-5 different models at once and return every answer side by side, so you can compare

Parameter	Type	Required	Notes
prompt	string	yes	The full prompt, with all the context the models need.
models	array	no	Model IDs to ask (2-5). Pick different families for independent views.
system	string	no	Optional system prompt for every model.
reasoning_effort	string	no	How hard a reasoning model should think. Ignored by models without reasoning. Omit for the model's default.
max_tokens	integer	no	Cap on the reply length in tokens (default 4096). Reasoning models spend some of these thinking.

List Obscurify.ai chat models with their IDs, context window, price per million input/output tokens (USD),

Parameter	Type	Required	Notes
search	string	no	Case-insensitive text to match in the model ID or name, e.g. "claude", "deepseek", "coder".
plan	string	no	Only models usable on this plan: any (Pay As You Go and up), casual, or pro (everything).
max_output_price	number	no	Only models whose output price is at most this many USD per million tokens.
tools_only	boolean	no	Only models that support tool/function calling.
sort	string	no	Sort order (default id). price = cheapest output first.
limit	integer	no	Max rows (default 60).

Generate an image from a text prompt with Obscurify.ai's Stable Diffusion image models (SDXL, SD 1.5 and LCM checkpoints).

Parameter	Type	Required	Notes
prompt	string	no	What to draw. Required unless list is true.
model	string	no	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	no	Things to keep out of the image.
width	integer	no	Width in pixels (default: the model's).
height	integer	no	Height in pixels (default: the model's).
seed	integer	no	Seed for reproducible results.
list	boolean	no	List image models and prices instead of generating.

Show the Obscurify.ai account's balance (USD), plan, included credit used this billing period, token usage,

No parameter schema on file.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Obscurify.ai or to call it, at any volume.

ATrust score 97 / 100

Release 0.1.0 · scanned 30 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score97

Findings0 threat · 1 capability

Capabilitymoderate

Coveragesource

Verificationsource

Surface digest18f5171d785f9335a02dfe121b72d9b049a46d6b5fe58469b4c152da66260dcd

Score vectorthreat 100 → client 97

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	source	publisher verification (provenance) — cryptographic build provenance ties the artifact to its source	−0
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (6 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
ask	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
chat	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
second_opinion	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
list_models	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
generate_image	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true
balance	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest18f5171d785f9335

Scanned2026-10-30

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.