Codeweaver MCP Server

codeweaver npm v4.0.2

Published by an unidentified publisher — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.

Trust grade
F
55/100
Last scanned
Trust
F · 55/100
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.
F Why this grade 100 − 45.5 = 55/100

Every server starts at 100. These are the exact deductions the deterministic engine applied — each one reproducible, none of it an opinion or an LLM's guess:

PointsWhat was foundCategory
−15.4 Dynamic evaluation of a non-literal value MTC-SRC-010 injection
−15.4 Assembled command execution and dynamic evaluation in the same server MTC-SRC-011 injection
−6.3 Unsafe deserialization MTC-SRC-007 permissions
−6.3 Untrusted input concatenated into a command sink MTC-SRC-009 injection
−2.1 Package has no source repository MTC-SUP-011 supply-chain

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 the deduction.

Findings 8

high Dynamic evaluation of a non-literal value (src/core/rate-limit/redis-store.ts)MTC-SRC-010

In the server's implementation (`src/core/rate-limit/redis-store.ts:92`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: eval(

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/core/rate-limit/redis-store.ts

high Assembled command execution and dynamic evaluation in the same serverMTC-SRC-011

The implementation builds shell commands out of runtime values AND evaluates runtime values as code. Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code.

Fix: Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.

Location: server implementation

high Dynamic code execution in server code (src/core/rate-limit/redis-store.ts)MTC-SRC-001

In the server's implementation (`src/core/rate-limit/redis-store.ts:92`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: eval(

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/core/rate-limit/redis-store.ts

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

In the server's implementation (`command.js:5`): 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: child_process

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 command.js

medium Untrusted input concatenated into a command sink (command.js)MTC-SRC-009

In the server's implementation (`command.js:22`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: exec(`git clone ${repoUrl} ${

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 command.js

medium Dynamic module load from a non-literal (src/main.ts)MTC-SRC-005

In the server's implementation (`src/main.ts:59`): 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(fullPath)

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/main.ts

medium Unsafe deserialization (src/core/file/file-helpers.ts)MTC-SRC-007

In the server's implementation (`src/core/file/file-helpers.ts:45`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: yaml.load(

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/core/file/file-helpers.ts

low Package has no source repositoryMTC-SUP-011

"codeweaver" declares no repository URL, so its published artifact cannot be compared against reviewable source.

Fix: Prefer packages that link to public, reviewable source.

Location: package codeweaver

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
v4.0.2 latest F 55/100 8 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: F · 55/100
Markdown (GitHub README)
[![MCP Trust Score](https://mcptrustchecker.com/registry/codeweaver/badge.svg)](https://mcptrustchecker.com/registry/codeweaver)
HTML
<a href="https://mcptrustchecker.com/registry/codeweaver"><img src="https://mcptrustchecker.com/registry/codeweaver/badge.svg" alt="MCP Trust Score" height="20"></a>
Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/codeweaver/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 codeweaver --online

Use the free API → How scoring works

More in Developer Tools