Ellmos Filecommander MCP Server
ellmos-filecommander-mcp
npm
v1.10.4
Published by ellmos-ai — 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.
A comprehensive MCP server providing 46 tools for filesystem operations, process management, interactive sessions, async file search, JSON repair, encoding fix, duplicate detection, OCR, ZIP archives, Markdown export, read-only web fetch/extraction, and c
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 11 = 83. 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 |
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 21
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: fc_web_fetch → fc_read_file → fc_execute_command. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). 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 fc_web_fetch → fc_read_file → fc_execute_command
high Tool "fc_execute_command" exposes command/code executionMTC-CAP-001
Tool "fc_execute_command" appears to run shell commands or evaluate code (keyword "execute command" in tool name, parameter "command"). 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 fc_execute_command
high Tool "fc_start_session" exposes command/code executionMTC-CAP-001
Tool "fc_start_session" appears to run shell commands or evaluate code (parameter "command"). 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 fc_start_session
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:30`): 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: execSync, spawn } from "child_process"; import { promisify } from "util"; import * as yaml from 'js-yaml'; import * as t
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/index.js
high Shell/command execution in server code (dist/open-path.js)MTC-SRC-002
In the server's implementation (`dist/open-path.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: nodeSpawn } from "node:child_process"; import { realpath, stat } from "node:fs/promises"; import { resolve, win32 } fro
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/open-path.js
medium Untrusted input concatenated into a command sink (dist/index.js)MTC-SRC-009
In the server's implementation (`dist/index.js:3272`): 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: const result = execSync(`which ${cmd}`, { encoding: 'utf-8' }).trim(); if (result)
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/index.js
medium Unconstrained URL/host parameter "url" on "fc_web_fetch"MTC-CAP-007
Tool "fc_web_fetch" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool fc_web_fetch · inputSchema.properties.url
medium Tool "fc_write_file" can modify the filesystemMTC-CAP-002
Tool "fc_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 fc_write_file
medium Tool "fc_delete_file" can modify the filesystemMTC-CAP-002
Tool "fc_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 fc_delete_file
medium Tool "fc_edit_file" can modify the filesystemMTC-CAP-002
Tool "fc_edit_file" can write, overwrite or delete files (keyword "edit_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 fc_edit_file
medium Unconstrained command parameter "command" on "fc_execute_command"MTC-CAP-006
Tool "fc_execute_command" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool fc_execute_command · inputSchema.properties.command
medium Unconstrained command parameter "command" on "fc_start_session"MTC-CAP-006
Tool "fc_start_session" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool fc_start_session · inputSchema.properties.command
low Mutating tool "fc_write_file" declares no destructiveHintMTC-CAP-005
Tool "fc_write_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool fc_write_file
low Mutating tool "fc_delete_file" declares no destructiveHintMTC-CAP-005
Tool "fc_delete_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool fc_delete_file
low Mutating tool "fc_execute_command" declares no destructiveHintMTC-CAP-005
Tool "fc_execute_command" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool fc_execute_command
low Mutating tool "fc_edit_file" declares no destructiveHintMTC-CAP-005
Tool "fc_edit_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool fc_edit_file
low Mutating tool "fc_start_session" declares no destructiveHintMTC-CAP-005
Tool "fc_start_session" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool fc_start_session
low Unconstrained path parameter "path" on "fc_read_file"MTC-CAP-008
Tool "fc_read_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool fc_read_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "fc_write_file"MTC-CAP-008
Tool "fc_write_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool fc_write_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "fc_delete_file"MTC-CAP-008
Tool "fc_delete_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool fc_delete_file · inputSchema.properties.path
low Unconstrained path parameter "path" on "fc_edit_file"MTC-CAP-008
Tool "fc_edit_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool fc_edit_file · inputSchema.properties.path
Tools 49
Each tool and what it can reach — statically extracted from the published source.
fc_delete_filewrites filesfc_edit_filewrites filesfc_execute_commandruns code / shellfc_read_filereads sensitive datafc_start_sessionruns code / shellfc_web_fetchingests untrusted inputfc_write_filewrites filesfc_archiveno sensitive capabilityfc_batch_renameno sensitive capabilityfc_check_cloud_lockno sensitive capability
Show 39 more tools ↓
fc_checksumno sensitive capabilityfc_cleanup_fileno sensitive capabilityfc_clear_searchno sensitive capabilityfc_close_sessionno sensitive capabilityfc_convert_formatno sensitive capabilityfc_copyno sensitive capabilityfc_create_directoryno sensitive capabilityfc_delete_directoryno sensitive capabilityfc_detect_duplicatesno sensitive capabilityfc_file_infono sensitive capabilityfc_fix_encodingno sensitive capabilityfc_fix_jsonno sensitive capabilityfc_folder_diffno sensitive capabilityfc_get_languageno sensitive capabilityfc_get_search_resultsno sensitive capabilityfc_get_timeno sensitive capabilityfc_kill_processno sensitive capabilityfc_list_directoryno sensitive capabilityfc_list_processesno sensitive capabilityfc_list_searchesno sensitive capabilityfc_list_sessionsno sensitive capabilityfc_md_to_htmlno sensitive capabilityfc_md_to_pdfno sensitive capabilityfc_moveno sensitive capabilityfc_ocrno sensitive capabilityfc_open_pathno sensitive capabilityfc_read_multiple_filesno sensitive capabilityfc_read_outputno sensitive capabilityfc_safe_deleteno sensitive capabilityfc_search_contentno sensitive capabilityfc_search_filesno sensitive capabilityfc_send_inputno sensitive capabilityfc_set_languageno sensitive capabilityfc_set_safe_modeno sensitive capabilityfc_start_processno sensitive capabilityfc_start_searchno sensitive capabilityfc_stop_searchno sensitive capabilityfc_str_replaceno sensitive capabilityfc_validate_jsonno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (49 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 3
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.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.10.4 latest |
B 83/100 | 21 | 1.13.0 | 2026-09-07 |
v1.9.3 |
B 83/100 | 20 | 1.13.0 | 2026-08-25 |
v1.9.1 |
B 83/100 | 20 | 1.9.0 | 2026-07-23 |
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.
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 ellmos-filecommander-mcp --onlineMore in Files & Storage
Safe bulk Meta ads: launch 150+ campaigns from Drive folders with spend guardrails and validation.
CLI tool to add MCP servers to various AI coding clients
MCP compatibility adapter for Agent Tool Protocol
MCP server for multi-tenant DuckDB management with R2/S3 storage
A stdio-to-HTTP MCP proxy that transparently intercepts file parameters, reading local files and base64-encoding them before forwarding to the remote server.
Free buyer-side outcome verification and provider comparison for supplied agent receipts.