Prompt Cleaner
Prompt Cleaner MCP server by David Colon that provides AI assistants with tools to sanitize, redact, and professionally reformat user prompts before they're processed by language models. The implementation integrates with local OpenAI-compatible APIs to intelligently clean prompts while automatically detecting and redacting sensitive information like API keys, tokens, emails, and other secrets using pattern matching. Features comprehensive retry logic with exponential backoff, structured JSON output with notes and risk assessments, configurable temperature settings, and multiple tool aliases (cleaner, sanitize-text, normalize-prompt) for different use cases, making it valuable for developers who want to ensure prompt hygiene and prevent accidental exposure of sensitive data in AI workflows.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- communication
- Source
- PulseMCP
- Repository
- github.com/dacebt/prompt-cleaner-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Prompt Cleaner from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.