Local Mcp MCP Server

https://local-mcp.com/mcp Remote v3.0.0

Published by local-mcp.com — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.

180 local tools from ChatGPT, Claude.ai & desktop AIs: Mail, iMessage, Teams, files. Local, free.

Open the endpoint ↗ Raw report (JSON) ↗

Trust grade

85/100

Last scanned 2026-09-08 get badge →

Trust

B · 85/100

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

High

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Live

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

B Why this grade threat 91 − adoption risk = 85/100

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 − 9.5 = 91. What the published surface and source actually contain:

Points	What was found	Category
−9.5	Annotation contradicts behavior on "gdrive_write_file" ×2 MTC-CAP-003	permissions

2. Client adoption risk — 91 − 6 = 85. 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
−6	capability blast radius (high) — client exposure if the model is manipulated

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 18

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

This server (without client built-ins) exposes a complete data-exfiltration chain: list_email_accounts → file_read ⇒ m365_send_email. 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 list_email_accounts → file_read → m365_send_email

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

Tool "gdrive_delete_file" can write, overwrite or delete files (keyword "delete_file" in tool name). Verify it is scoped to a safe directory.

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

Location: tool gdrive_delete_file

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

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

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

Location: tool gdrive_write_file

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

Tool "onedrive_delete_file" can write, overwrite or delete files (keyword "delete_file" in tool name). Verify it is scoped to a safe directory.

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

Location: tool onedrive_delete_file

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

Tool "onedrive_move_file" can write, overwrite or delete files (keyword "move_file" in tool name). Verify it is scoped to a safe directory.

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

Location: tool onedrive_move_file

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

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

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

Location: tool onedrive_write_file

medium Annotation contradicts behavior on "gdrive_write_file"MTC-CAP-003

Tool "gdrive_write_file" advertises destructiveHint=false but its derived capabilities include state-modifying actions (file-write). Tool annotations are attacker-controllable and must never be trusted; a mismatch like this is exactly how a hostile server hides a destructive tool.

Fix: Ignore server-provided annotations for security decisions; gate destructive tools on explicit user consent.

Location: tool gdrive_write_file

medium Annotation contradicts behavior on "onedrive_write_file"MTC-CAP-003

Tool "onedrive_write_file" advertises destructiveHint=false but its derived capabilities include state-modifying actions (file-write). Tool annotations are attacker-controllable and must never be trusted; a mismatch like this is exactly how a hostile server hides a destructive tool.

Fix: Ignore server-provided annotations for security decisions; gate destructive tools on explicit user consent.

Location: tool onedrive_write_file

low Unconstrained path parameter "path" on "file_read"MTC-CAP-008

Tool "file_read" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.