Claude Faf MCP Server

claude-faf-mcp npm v5.20.0

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

Trust grade
A
94/100
Last scanned
Trust
A · 94/100
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 100 − 6.3 = 94/100

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
−6.3 Package runs install-time scripts MTC-SUP-010 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 9

high Reads a sensitive credential path or dumps the environment (dist/src/handlers/fileHandler.js)MTC-SRC-006

In the server's implementation (`dist/src/handlers/fileHandler.js:133`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: ~/.ssh

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/src/handlers/fileHandler.js

high Reads a sensitive credential path or dumps the environment (dist/src/utils/safe-path.d.ts)MTC-SRC-006

In the server's implementation (`dist/src/utils/safe-path.d.ts:9`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: ~/.ssh

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/src/utils/safe-path.d.ts

high Reads a sensitive credential path or dumps the environment (dist/src/utils/safe-path.js)MTC-SRC-006

In the server's implementation (`dist/src/utils/safe-path.js:10`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: ~/.ssh

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/src/utils/safe-path.js

high Shell/command execution in server code (dist/src/handlers/engine-adapter.js)MTC-SRC-002

In the server's implementation (`dist/src/handlers/engine-adapter.js:37`): 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 dist/src/handlers/engine-adapter.js

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

In the server's implementation (`dist/src/handlers/tools.js:1906`): 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 dist/src/handlers/tools.js

high Shell/command execution in server code (dist/src/utils/auto-path-detection.js)MTC-SRC-002

In the server's implementation (`dist/src/utils/auto-path-detection.js:49`): 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 dist/src/utils/auto-path-detection.js

high Shell/command execution in server code (dist/src/utils/cli-detector.js)MTC-SRC-002

In the server's implementation (`dist/src/utils/cli-detector.js: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: 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 dist/src/utils/cli-detector.js

high Shell/command execution in server code (dist/src/utils/memory-parser.js)MTC-SRC-002

In the server's implementation (`dist/src/utils/memory-parser.js:59`): 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 dist/src/utils/memory-parser.js

medium Package runs install-time scripts (postinstall)MTC-SUP-010

"claude-faf-mcp" executes postinstall script(s) at install time. The large majority of malicious packages abuse install hooks to run code before you ever import them.

Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.

Location: package claude-faf-mcp

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
v5.20.0 latest A 94/100 9 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 · 94/100
Markdown (GitHub README)
[![MCP Trust Score](https://mcptrustchecker.com/registry/claude-faf-mcp/badge.svg)](https://mcptrustchecker.com/registry/claude-faf-mcp)
HTML
<a href="https://mcptrustchecker.com/registry/claude-faf-mcp"><img src="https://mcptrustchecker.com/registry/claude-faf-mcp/badge.svg" alt="MCP Trust Score" height="20"></a>
Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/claude-faf-mcp/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 claude-faf-mcp --online

Use the free API → How scoring works

More in Other