Accelerator MCP Server

@verevoir/accelerator npm v0.1.5

Published by @verevoir — 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.

View on npm ↗ Repository ↗ Raw report (JSON) ↗

Trust grade

89/100

Last scanned 2026-07-23

Trust

B · 89/100

Adoption risk for you: the threat score, then adjusted down for blast radius, publisher verification and how much the scan could see. Deterministic; every point is auditable.

Capability

Critical

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.

B Why this grade threat 100 − adoption risk = 89/100

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 − 11 = 89. 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
−10	capability blast radius (critical) — client exposure if the model is manipulated
−1	publisher verification (public source) — no provenance, but the source is public and inspectable
✓	inspection depth (source) — how much of the target the scan could see

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 29

critical Completed toxic-flow trifecta across toolsMTC-FLOW-002

This server (without client built-ins) exposes a complete data-exfiltration chain: get_card ⇒ commit_files → find_symbol. Untrusted input is ingested, private data is read, and it can be sent to an external sink — and at least one leg is a direct schema wire (⇒), where a producer's output drops straight into a free-text parameter of the next tool, so the chain needs little agent cooperation. Static analysis proves the primitive exists, not that a specific run will occur.

Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.

Location: flow get_card → commit_files → find_symbol

high Read-and-egress in one tool: "list_files"MTC-FLOW-003

Tool "list_files" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.

Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.

Location: flow list_files

high Read-and-egress in one tool: "grep"MTC-FLOW-003

Tool "grep" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.

Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.

Location: flow grep

high Read-and-egress in one tool: "find_symbol"MTC-FLOW-003

Tool "find_symbol" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.

Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.

Location: flow find_symbol

high Read-and-egress in one tool: "write_file"MTC-FLOW-003

Tool "write_file" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.

Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.

Location: flow write_file

high Tool "list_files" exposes command/code executionMTC-CAP-001

Tool "list_files" appears to run shell commands or evaluate code (keyword "shell"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.

Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.

Location: tool list_files

high Tool "grep" exposes command/code executionMTC-CAP-001

Tool "grep" appears to run shell commands or evaluate code (keyword "shell"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.

Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.

Location: tool grep

high Tool "find_symbol" exposes command/code executionMTC-CAP-001

Tool "find_symbol" appears to run shell commands or evaluate code (keyword "shell"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.

Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.

Location: tool find_symbol

high Tool "write_file" exposes command/code executionMTC-CAP-001

Tool "write_file" appears to run shell commands or evaluate code (keyword "shell"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.

Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.

Location: tool write_file

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

In the server's implementation (`dist/card-reconcile-bin.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: 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/card-reconcile-bin.js

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

In the server's implementation (`dist/router.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: child_process

Location: server dist/router.js

medium Tool "write_file" can modify the filesystemMTC-CAP-002

Tool "write_file" can write, overwrite or delete files (keyword "write_file"). Verify it is scoped to a safe directory.

Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.

Location: tool write_file

medium Tool "edit_file" can modify the filesystemMTC-CAP-002

Tool "edit_file" can write, overwrite or delete files (keyword "write_file"). Verify it is scoped to a safe directory.

Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.

Location: tool edit_file

medium Tool "multi_edit" can modify the filesystemMTC-CAP-002

Tool "multi_edit" can write, overwrite or delete files (keyword "edit_file"). Verify it is scoped to a safe directory.

Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.

Location: tool multi_edit

medium Tool "commit_files" can modify the filesystemMTC-CAP-002

Tool "commit_files" can write, overwrite or delete files (keyword "write_file"). Verify it is scoped to a safe directory.

Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.

Location: tool commit_files

low Mutating tool "list_files" declares no destructiveHintMTC-CAP-005

Tool "list_files" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.