prompt2mcp@0.5.1
CAUTION· not startedPublisher claims: "Build MCP servers from natural language prompts — local-first, privacy-focused" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
API_KEYJWT_SECRETOPENAI_API_KEYWEBHOOK_SECRETConfiguration, not credentials: API_BASE_URL, DB_PATH, DEFAULT_FROM, JIRA_BASE_URL, JIRA_EMAIL, JWT_EXPIRY_HOURS, MAX_ROWS, OPENAI_BASE_URL, PIPELINE_DATA_DIR, SMTP_HOST, SMTP_PASS, SMTP_PORT, SMTP_USER, USERS_DB- Where it talks to
- no vendor host named in the codeAlso nodejs.org, python.org, nodesource.com, slack.com, stripe.com, notion.com, notion.so, spotify.com, google.com, twitter.com, discord.com, linear.app, atlassian.net, atlassian.com, linkedin.com, microsoft.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names nodejs.org, python.org, nodesource.com, slack.com, stripe.com, notion.com, notion.so, spotify.com, google.com, twitter.com, discord.com, linear.app, atlassian.net, atlassian.com, linkedin.com, microsoft.com as well as its own vendor. The guard injects API_KEY, JWT_SECRET, OPENAI_API_KEY, WEBHOOK_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Privileged sudo command; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
"""MCP Factory CLI — Main entry point."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.f" • Linux: [cyan]curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo bash -[/cyan]\n"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Open .env and paste your API keyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""MCP Generator Engine — Analyzes prompts and generates production-quality MCP server code.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.env_content = "# Data Pipeline Configuration\n# Never commit .env to git!\n\nPIPELINE_DATA_DIR=./data\nMAX_ROWS=100000\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""MCP Factory CLI — Main entry point (re-export)."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Paste it in your .env file as OPENAI_API_KEY=sk-your-key-here",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_content = "# Auth Server Configuration\n# Never commit .env to git!\n\nJWT_SECRET=change-me-to-a-strong-secret\nJWT_EXPIRY_HOURS=24\nUSERS_DB=users.json\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env = (result.output_path / ".env.example").read_text(encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Check for .env.example and SETUP.md if the server uses env vars."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert ".env" in contentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Paste it in your .env file as SLACK_BOT_TOKEN=xoxb-your-token-here",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Paste it in your .env file as GITHUB_TOKEN=ghp_your_token_here",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose..envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Paste it in your .env file as STRIPE_SECRET_KEY=sk_test_your_key_here",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Paste it in your .env file as STRIPE_SECRET_KEY=sk_test_your_key_here",Fix: Never read or enumerate credential locations; accept a documented environment variable instead.f" cp .env.example .env\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Run: docker run -i --env-file .env {name}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result.warnings.append("Missing .env.example — users won't know which env vars to set")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Code Reviewer — LLM-powered review of generated MCP server code.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# Check .env.example has specific varFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert (result.output_path / ".env.example").exists()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_example = server_path / ".env.example"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# ---- .env.example (API-specific if detected) ----Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Run: docker run -i --env-file .env {name}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f" • Linux: [cyan]curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo bash -[/cyan]\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Tests for MCP Generator Engine."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# Check .env.example and SETUP.md (API key guidance)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""LLM module — Provides structured LLM calls for MCP Factory."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.console.print("[dim]ℹ Could not auto-update Claude Desktop config (use 'mcpfactory config-export' manually)[/dim]")Fix: Pin versions and sources; vendor anything fetched at install time.mcpfactory create <prompt> Generate a new MCP serverFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."""API-specific tool templates — Real working tools for known APIs.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.env_content = "# Notification Hub Configuration\n# Never commit .env to git!\n\nSMTP_HOST=smtp.gmail.com\nSMTP_PORT=587\nSMTP_USER=\nSMTP_PASS=\[email protected]\nWEBHOOK_SECRET=\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Interactive Prompt Refiner — Asks follow-up questions to improve vague prompts.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent..envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Paste it in your .env file as NOTION_API_KEY=ntn_your_key_here",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_content = "# Database Configuration\n# Never commit .env to git!\n\nDB_PATH=database.db\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Check .env.example and SETUP.md (API key guidance)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert ".env" in contentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for prompt2mcp@0.5.1 as of 35 min ago. This is the package itself, not its dependencies.
What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim jatintaori1904: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Stripe-like API key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.