Server providing Argo CD integration for MCP clients.
Nothing to run from here
Deskcommand is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
6
downloads a day
local
runs on your machine
279
downloads in 30d
What it does
Run terminal processes, edit files and search code on the local machine from an MCP client.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user deskcommand-mcp '--' npx -y @reneturcios/deskcommand mcp
# 2 — ask your agent for something these tools do
# create_directory, edit_block, force_terminate and 23 more
Deskcommand costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CLAll 381 servers
CloudCorpRecords381 servers
28 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Deskcommand as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user deskcommand-mcp '--' npx -y @reneturcios/deskcommand mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
26 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Create a new directory or ensure a directory exists, including nested paths
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | The directory path to create or ensure exists |
Apply a surgical text replacement in a file: replace old_string with new_string
| Parameter | Type | Required | Notes |
|---|---|---|---|
| expected_replacements | number | no | Optional expected number of replacements; the edit fails if the actual count differs |
| file_path | string | yes | The path of the file to edit |
| new_string | string | yes | The text to replace old_string with |
| old_string | string | yes | The exact text in the file to replace |
Force terminate a running terminal process session
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pid | number | yes | The PID of the terminal process session to force terminate |
Get the current server configuration
No parameter schema on file.
Retrieve detailed metadata about a file or directory
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | The path of the file or directory to describe |
Get more results from an active search session
| Parameter | Type | Required | Notes |
|---|---|---|---|
| length | number | no | Optional number of results to return |
| offset | number | no | Optional result offset to page from |
| sessionId | string | yes | The search session id returned by start_search |
Get available prompts, or one prompt by id
| Parameter | Type | Required | Notes |
|---|---|---|---|
| promptId | string | no | Optional prompt id to fetch a single prompt; all available prompts are returned when omitted |
Get the recent tool calls recorded by this server
No parameter schema on file.
Get usage statistics for this server
No parameter schema on file.
Record feedback about this tool for later review
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | yes | The feedback message to record |
Send input to a running process and wait for its response
| Parameter | Type | Required | Notes |
|---|---|---|---|
| input | string | yes | The input text to send to the process |
| pid | number | yes | The PID of the running process to interact with |
| timeout_ms | number | no | Optional milliseconds to wait for the process response |
Terminate a process by its PID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pid | number | yes | The PID of the process to terminate |
Get a detailed listing of all files and directories at a path
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | The directory path to list |
List all running processes with their PID, command and status
No parameter schema on file.
List all active search sessions
No parameter schema on file.
List all active terminal sessions
No parameter schema on file.
Move or rename a file or directory
| Parameter | Type | Required | Notes |
|---|---|---|---|
| destination | string | yes | The new path for the file or directory |
| source | string | yes | The current path of the file or directory to move |
Read the complete contents of a file, optionally a line range
| Parameter | Type | Required | Notes |
|---|---|---|---|
| length | number | no | Optional number of lines to read |
| offset | number | no | Optional starting line offset to read from |
| path | string | yes | The path of the file to read |
Read the contents of multiple files simultaneously
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | yes | The paths of the files to read |
Read output from a running process, waiting up to a timeout for new output
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pid | number | yes | The PID of the process whose output to read |
| timeout_ms | number | no | Optional milliseconds to wait for new output |
Set a configuration value by key
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | The configuration key to set |
| value | string | yes | The value to set for the configuration key |
Start a new terminal process in a shell and return its initial output
| Parameter | Type | Required | Notes |
|---|---|---|---|
| command | string | yes | The command line to start in the shell |
| shell | string | no | Optional shell to run the command with |
| timeout_ms | number | no | Optional milliseconds to wait for the process's initial output |
Start a search for a pattern in files under a path and return a session id
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePattern | string | no | Optional glob pattern limiting which files are searched |
| ignoreCase | boolean | no | Whether the search ignores case |
| maxResults | number | no | Optional maximum number of results to return |
| path | string | yes | The directory path to search under |
| pattern | string | yes | The pattern to search for |
| searchType | string | no | Optional search type: 'files' searches file names, 'literal' matches the pattern literally, otherwise the pattern is treated as a regular expression over file contents |
Stop an active search by its session id
| Parameter | Type | Required | Notes |
|---|---|---|---|
| searchId | string | yes | The search session id returned by start_search |
Create a new file or completely overwrite an existing file with new content
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | The full content to write to the file |
| path | string | yes | The path of the file to create or overwrite |
Write text content to a file at a path (PDF-oriented in the original; this rebuild writes the content as given)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | The content to write to the file |
| path | string | yes | The path of the file to write |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Deskcommand or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.1.0 · scanned 31 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings1 threat · 11 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest9ac45f0b94efa748f62a506f75a40af4ea2ba4a583f467ceefc61901cfe426a3
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (26 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>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| create_directory | no tags | |
| edit_block | no tags | |
| force_terminate | no tags | |
| get_config | no tags | |
| get_file_info | no tags | |
| get_more_search_results | no tags | |
| get_prompts | no tags | |
| get_recent_tool_calls | no tags | |
| get_usage_stats | no tags | |
| give_feedback_to_desktop_commander | no tags | |
| interact_with_process | no tags | |
| kill_process | no tags | |
| list_directory | no tags | |
| list_processes | no tags | |
| list_searches | no tags | |
| list_sessions | no tags | |
| move_file | file-write | file-write: keyword "move_file" in tool name |
| read_file | sensitive-source | sensitive-source: keyword "read_file" |
| read_multiple_files | no tags | |
| read_process_output | no tags | |
| set_config_value | no tags | |
| start_process | code-exec | code-exec: parameter "command" |
| start_search | no tags | |
| stop_search | no tags | |
| write_file | file-write | file-write: keyword "write_file" in tool name |
| write_pdf | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
read_file → start_process
A sensitive-source → external-sink chain exists: read_file → start_process.
Supply chain and provenance
Integrityfirst-seen
Surface digest9ac45f0b94efa748
Scanned2026-10-31
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Deskcommand can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.