Zero-Trust PII & secrets sanitizer. Locally scrubs data in-memory before sending context to LLMs.
Zero-Trust PII & secrets sanitizer. Locally scrubs data in-memory before sending context to LLMs.
All sensitive parameters, identifiers, and variables are intercepted locally inside your machine's RAM. They are replaced by tokens (e.g. [EMAIL_1]) before being sent to the AI. Once the AI responds, the tokens are safely swapped back to original values in your local context.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"privacyscrubber": {
"command": "npx",
"args": ["-y", "@privacyscrubber/mcp-server"],
"env": {
"PRIVACYSCRUBBER_KEY": "YOUR_LICENSE_KEY_HERE"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PRIVACYSCRUBBER_KEY | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Durable user/project memory for MCP clients: recall context and remember selected facts.
Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI
This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from Agent Voice Response Wiki.JS instance.
A comprehensive Model Context Protocol (MCP) server for satellite orbital mechanics calculations with natural language processing capabilities.