Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Coding / Desktop Commander MCP
◇MCP serverCodingFree

Desktop Commander MCP

Gives AI assistants terminal control, filesystem search, and diff-based file editing on your machine.

@ai-supply
Installs587
↗ Source repository
← More CodingCoding leaderboard →How we grade security →Source ↗

Desktop Commander MCP

Desktop Commander is a Model Context Protocol server that gives AI assistants like Claude terminal control, filesystem search, and diff-based file editing on your local machine.

It lets the agent read, update, and manage files, run and manage terminal processes, and automate multi-step tasks that go beyond in-editor AI tools. Because it runs locally through your MCP client, it can use your existing client subscription instead of separate API token costs.

It is aimed at developers and power users who want an AI assistant that can operate their filesystem and shell to automate real work.

Rating rank
#1
of 22 in Coding
Install rank
#20
of 22 in Coding
Security score
58/100 · D
review
Security rank
#10
of 22 in Coding
Installs
587
cat avg 190k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Coding leaderboard →
! Security: Review · 5858/100 · grade Dscanned 2h ago

Only compromise signals — malicious or tampered code (leaked secrets, backdoors, path traversal, a dropped executable) — reduce the score. Dangerous-by-capability traits (shell, network, injection strings, pickle) are shown as risk surface: expected for some capabilities — a security tool ships offensive code on purpose — so they do not sink the grade.

Compromise signals
Embedded credentialshighwonderwhy-er-DesktopCommanderMCP-0ad919b/src/ui/file-preview/src/markdown/editor.ts
found: hardcoded credential
What this capability can do · high confidence (static)
Tools (5)
read_multiple_fileswrite_filelist_directorystop_searchforce_terminate
⚑ filesystem⚑ shell⚑ network⚑ secretsinstall: postinstall
egress → registry.modelcontextprotocol.io, www.npmjs.com, telemetry.desktopcommander.app, dc-telemetry-proxy-83847352264.europe-west1.run.app, calendar.app.google, discord.com, claude.ai, mcp.desktopcommander.app +6
Risk surface (24)
External endpoints declaredlowwonderwhy-er-DesktopCommanderMCP-0ad919b/.codespellrc
1 distinct host(s)
External endpoints declaredlowwonderwhy-er-DesktopCommanderMCP-0ad919b/Dockerfile
2 distinct host(s)
Broad capability surfacelowwonderwhy-er-DesktopCommanderMCP-0ad919b/FAQ.md
4 high-impact capability categories referenced — verify least-privilege
External endpoints declaredlowwonderwhy-er-DesktopCommanderMCP-0ad919b/FAQ.md
5 distinct host(s)
External endpoints declaredlowwonderwhy-er-DesktopCommanderMCP-0ad919b/PUBLISH.md
3 distinct host(s)
Suspicious code patternshighwonderwhy-er-DesktopCommanderMCP-0ad919b/README.md
pipe-to-shell install
External endpoints declaredmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/README.md
36 distinct host(s)
External endpoints declaredlowwonderwhy-er-DesktopCommanderMCP-0ad919b/install-docker.sh
4 distinct host(s)
Suspicious code patternshighwonderwhy-er-DesktopCommanderMCP-0ad919b/install.sh
destructive rm -rf /
Path traversal sequencesmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/manifest.template.json
'../' present in content or name
External endpoints declaredlowwonderwhy-er-DesktopCommanderMCP-0ad919b/package-lock.json
7 distinct host(s)
Broad capability surfacelowwonderwhy-er-DesktopCommanderMCP-0ad919b/package.json
3 high-impact capability categories referenced — verify least-privilege
npm install-lifecycle scripthighwonderwhy-er-DesktopCommanderMCP-0ad919b/package.json
postinstall run on install — executes arbitrary code
Suspicious network referencesmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/plugins/claude/skills/ai-tools-setup/references/openclaw.md
raw IP URL (4 URLs)
Egress to a private/loopback hosthighwonderwhy-er-DesktopCommanderMCP-0ad919b/plugins/claude/skills/ai-tools-setup/references/openclaw.md
127.0.0.1
Suspicious code patternsmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/scripts/build-mcpb.cjs
child_process exec
Suspicious code patternsmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/scripts/publish-release.cjs
child_process exec; dynamic code execution
Potentially unbounded loopmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/src/tools/filesystem.ts
an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption
Suspicious code patternshighwonderwhy-er-DesktopCommanderMCP-0ad919b/src/ui/file-preview/src/host/external-actions.ts
encoded PowerShell command
Suspicious code patternsmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/src/ui/file-preview/src/markdown/editor.ts
dynamic code execution
Possible obfuscationmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/test/large_test_file.txt
very long lines
Suspicious code patternscriticalwonderwhy-er-DesktopCommanderMCP-0ad919b/test/test-blocked-commands.js
fork bomb; disk wipe command
Suspicious network referencesmediumwonderwhy-er-DesktopCommanderMCP-0ad919b/test/test-feature-flags-timeout.js
raw IP URL (5 URLs)
Vulnerable dependenciescritical
94 known vulnerabilities in: @hono/node-server@1.19.7, @modelcontextprotocol/sdk@1.25.1, ajv@8.17.1, basic-ftp@5.1.0, brace-expansion@1.1.12, brace-expansion@2.0.2, diff@4.0.2, fast-uri@3.1.0
✔ verified source · pinned wonderwhy-er-DesktopCommanderMCP-0ad919b
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/desktop-commander-mcp/check). Click a policy:

OWASP AI control mapping
7passed
8flagged
0runtime-enforced
5governance

Evaluated against the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any control to see the findings.

OWASP Top 10 for LLM Applications
✓LLM01Prompt InjectionPassed
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: hardcoded credential (CWE-798)
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 46 npm dependencies declared
•npm install-lifecycle script — postinstall run on install — executes arbitrary code (CWE-506)
•Vulnerable dependencies — 94 known vulnerabilities in: @hono/node-server@1.19.7, @modelcontextprotocol/sdk@1.25.1, ajv@8.17.1, basic-ftp@5.1.0, brace-expansion@1.1.12, brace-expansion@2.0.2, diff@4.0.2, fast-uri@3.1.0 (CWE-1395)
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
⚠LLM05Improper Output Handlingcritical
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — pipe-to-shell install (CWE-494)
•Suspicious code patterns — destructive rm -rf / (CWE-78)
•Path traversal sequences — '../' present in content or name (CWE-22)
•Suspicious code patterns — child_process exec (CWE-78)
•Suspicious code patterns — child_process exec; dynamic code execution (CWE-78)
•Suspicious code patterns — encoded PowerShell command
•Suspicious code patterns — dynamic code execution (CWE-95)
•Suspicious code patterns — fork bomb; disk wipe command
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s)
•External endpoints declared — 2 distinct host(s)
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege (CWE-272)
•External endpoints declared — 5 distinct host(s)
•External endpoints declared — 3 distinct host(s)
•External endpoints declared — 36 distinct host(s)
•External endpoints declared — 4 distinct host(s)
•External endpoints declared — 7 distinct host(s)
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege (CWE-272)
•Egress to a private/loopback host — 127.0.0.1 (CWE-918)
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: hardcoded credential (CWE-798)
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption (CWE-835)
OWASP Machine Learning Security Top 10
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 46 npm dependencies declared
•npm install-lifecycle script — postinstall run on install — executes arbitrary code (CWE-506)
•Vulnerable dependencies — 94 known vulnerabilities in: @hono/node-server@1.19.7, @modelcontextprotocol/sdk@1.25.1, ajv@8.17.1, basic-ftp@5.1.0, brace-expansion@1.1.12, brace-expansion@2.0.2, diff@4.0.2, fast-uri@3.1.0 (CWE-1395)
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
⚠ML09Output Integritycritical
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — pipe-to-shell install (CWE-494)
•Suspicious code patterns — destructive rm -rf / (CWE-78)
•Path traversal sequences — '../' present in content or name (CWE-22)
•Suspicious code patterns — child_process exec (CWE-78)
•Suspicious code patterns — child_process exec; dynamic code execution (CWE-78)
•Suspicious code patterns — encoded PowerShell command
•Suspicious code patterns — dynamic code execution (CWE-95)
•Suspicious code patterns — fork bomb; disk wipe command
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.

Consume Desktop Commander MCP programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/desktop-commander-mcp

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/desktop-commander-mcp/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add desktop-commander-mcp

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/desktop-commander-mcp/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "desktop-commander-mcp" })
OpenAPI spec →
vlatest
! Security: Review · 582h ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy