Cascade Img MCP Server
cascade-img
PyPI
v0.1.1
Published by laffeyp — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
LLM-operable image-generation pipeline. Midjourney via Discord at v0.1, pluggable backends after.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 4 = 96. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 11
medium Hardcoded egress to an external endpoint (src/cascade_img/backends/midjourney_discord/diagnostics.py)MTC-SRC-003
In the server's implementation (`src/cascade_img/backends/midjourney_discord/diagnostics.py:86`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: k) try: r = requests.get("https://discord.com/api/v9/gateway", timeout=5) checks.append(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/cascade_img/backends/midjourney_discord/diagnostics.py
medium Hardcoded egress to an external endpoint (src/cascade_img/backends/midjourney_discord/transport/discord_send.py)MTC-SRC-003
In the server's implementation (`src/cascade_img/backends/midjourney_discord/transport/discord_send.py:45`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: http"], lambda: requests.post( "https://discord.com/api/v9/interactions", json=payload,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/cascade_img/backends/midjourney_discord/transport/discord_send.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tools/mj_capture_animate.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/mj_capture_animate.py:107`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ne, lambda: requests.post( "https://discord.com/api/v9/interactions", json=payload, headers=
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/mj_capture_animate.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tools/mj_capture_buttons.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/mj_capture_buttons.py:76`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: None, lambda: requests.post( "https://discord.com/api/v9/interactions", json=payload, headers=head
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/mj_capture_buttons.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tools/mj_capture_results.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/mj_capture_results.py:108`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ne, lambda: requests.post( "https://discord.com/api/v9/interactions", json=payload, headers=
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/mj_capture_results.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tools/mj_capture_video.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/mj_capture_video.py:121`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ne, lambda: requests.post( "https://discord.com/api/v9/interactions", json=payload, headers=
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/mj_capture_video.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tools/mj_capture_video_actions.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/mj_capture_video_actions.py:119`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ne, lambda: requests.post( "https://discord.com/api/v9/interactions", json=payload, headers=
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/mj_capture_video_actions.py
low Shell/command execution in packaging/dev tooling (tests/e2e/conftest.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/e2e/conftest.py:64`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ing="utf-8") proc = subprocess.Popen( [sys.executable, "-u", "-m", "cascade_img.backends.midjourney_discord.
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/e2e/conftest.py
low Shell/command execution in packaging/dev tooling (tests/e2e/test_smoke_walk.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/e2e/test_smoke_walk.py:46`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: mcp_walk.py" proc = subprocess.run( [ sys.executable, str(script), "--en
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/e2e/test_smoke_walk.py
low Shell/command execution in packaging/dev tooling (tests/e2e/test_trace_gate_live.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/e2e/test_trace_gate_live.py:79`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: lations).""" proc = subprocess.run( [sys.executable, "-m", "cascade_img.vocabulary.trace_check", str(event_l
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/e2e/test_trace_gate_live.py
low Shell/command execution in packaging/dev tooling (tools/smoke_mcp_walk.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/smoke_mcp_walk.py:175`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ing="utf-8") return subprocess.Popen( [ sys.executable, "-u", "-m",
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/smoke_mcp_walk.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.1 latest |
A 96/100 | 11 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan cascade-img --online --registry pypiMore in Design & Media
Turn designs into shipped parts: quote 3D printing, CNC, and decals, then check out.
Aleph's official SiliconFlow media-generation MCP server (image / video / TTS)
MCP server for image generation using Google Gemini AI
Ambience AI MCP Server - Generate images, videos, and audio through Model Context Protocol
MCP server exposing every endpoint of the AstroWay Calculation API as tools — natal, synastry, transits, Vedic dashas, Tarot, Numerology, Human Design, AI horoscopes — for Claude Desktop, Cursor and any MCP-compatible AI agent.
Audio-guide and trip-planning tools for 1,100+ cities from Audiala. Free, no API key.