Semiotic MCP Server

semiotic npm v3.8.4 Source verified

Published by nteract — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.

Trust grade
A
100/100
Last scanned
Trust
A · 100/100
How safe the published surface and source look. Deterministic; every point is auditable.
Capability
High
Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.
Coverage
Source
How much the scan could actually inspect. Shallow coverage is stated, never hidden.
A Why this grade

Started at 100 and nothing was deducted: the deterministic scan raised no scored threat in the published surface it inspected. Capability observations and advisory notes are recorded but never lower the score.

Findings 15

high Shell/command execution in server code (dist/chunk-chunk-FP44FHFO.module.min.js)MTC-SRC-002

In the server's implementation (`dist/chunk-chunk-FP44FHFO.module.min.js:2`): 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: spawn(

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 dist/chunk-chunk-FP44FHFO.module.min.js

high Shell/command execution in server code (dist/chunk-chunk-HKXUAEPJ.module.min.js)MTC-SRC-002

In the server's implementation (`dist/chunk-chunk-HKXUAEPJ.module.min.js:2`): 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: spawn(

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 dist/chunk-chunk-HKXUAEPJ.module.min.js

high Shell/command execution in server code (dist/chunk-chunk-LQBSXO7K.module.min.js)MTC-SRC-002

In the server's implementation (`dist/chunk-chunk-LQBSXO7K.module.min.js:2`): 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: spawn(

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 dist/chunk-chunk-LQBSXO7K.module.min.js

high Shell/command execution in server code (dist/chunk-chunk-LRIFN2HK.module.min.js)MTC-SRC-002

In the server's implementation (`dist/chunk-chunk-LRIFN2HK.module.min.js:1`): 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: spawn(

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 dist/chunk-chunk-LRIFN2HK.module.min.js

high Shell/command execution in server code (dist/components/stream/GeoParticlePool.d.ts)MTC-SRC-002

In the server's implementation (`dist/components/stream/GeoParticlePool.d.ts:38`): 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: spawn(

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 dist/components/stream/GeoParticlePool.d.ts

high Shell/command execution in server code (dist/geo.min.js)MTC-SRC-002

In the server's implementation (`dist/geo.min.js:2`): 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: spawn(

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 dist/geo.min.js

high Shell/command execution in server code (dist/network.min.js)MTC-SRC-002

In the server's implementation (`dist/network.min.js:2`): 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: spawn(

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 dist/network.min.js

high Shell/command execution in server code (dist/physics.min.js)MTC-SRC-002

In the server's implementation (`dist/physics.min.js:2`): 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: spawn(

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 dist/physics.min.js

high Shell/command execution in server code (dist/physicsWorker.js)MTC-SRC-002

In the server's implementation (`dist/physicsWorker.js:1`): 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: spawn(

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 dist/physicsWorker.js

high Shell/command execution in server code (dist/realtime.min.js)MTC-SRC-002

In the server's implementation (`dist/realtime.min.js:2`): 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: spawn(

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 dist/realtime.min.js

medium Dynamic module load from a non-literal (ai/chartSuggestions.cjs)MTC-SRC-005

In the server's implementation (`ai/chartSuggestions.cjs:43`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: require(candidate)

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 ai/chartSuggestions.cjs

medium Dynamic module load from a non-literal (ai/cli.js)MTC-SRC-005

In the server's implementation (`ai/cli.js:315`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: require(distPath)

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 ai/cli.js

medium Dynamic module load from a non-literal (dist/chunk-chunk-CA3YDW6F.module.min.js)MTC-SRC-005

In the server's implementation (`dist/chunk-chunk-CA3YDW6F.module.min.js:1`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: import(n.packageName)

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 dist/chunk-chunk-CA3YDW6F.module.min.js

medium Dynamic module load from a non-literal (dist/physics-matter.min.js)MTC-SRC-005

In the server's implementation (`dist/physics-matter.min.js:1`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: import(e.packageName)

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 dist/physics-matter.min.js

medium Dynamic module load from a non-literal (dist/physics-rapier.min.js)MTC-SRC-005

In the server's implementation (`dist/physics-rapier.min.js:1`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: import(e.packageName)

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 dist/physics-rapier.min.js

What this scan could not see

Versions

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.

VersionScoreFindingsEngineScanned
v3.8.4 latest A 100/100 15 1.5.0 2026-07-22

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.

MCP Trust Score: A · 100/100
Markdown (GitHub README)
[![MCP Trust Score](https://mcptrustchecker.com/registry/semiotic/badge.svg)](https://mcptrustchecker.com/registry/semiotic)
HTML
<a href="https://mcptrustchecker.com/registry/semiotic"><img src="https://mcptrustchecker.com/registry/semiotic/badge.svg" alt="MCP Trust Score" height="20"></a>
Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/semiotic/badge.json via https://img.shields.io/endpoint?url=…

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 semiotic --online

Use the free API → How scoring works

More in Developer Tools