Pseudonym MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 163 installs a week from npm. Last commit 4 Sep 2026.
Locally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward.
Today is the operative word: we check Pseudonym MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pseudonym-mcp -- npx -y pseudonym-mcp
{
"mcpServers": {
"pseudonym-mcp": {
"command": "npx",
"args": [
"-y",
"pseudonym-mcp"
]
}
}
}
[mcp_servers.pseudonym-mcp]
command = "npx"
args = ["-y", "pseudonym-mcp"]
{
"mcpServers": {
"pseudonym-mcp": {
"command": "npx",
"args": [
"-y",
"pseudonym-mcp"
]
}
}
}
{
"servers": {
"pseudonym-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pseudonym-mcp"
]
}
}
}
Pseudonymizes PII before your LLM and returns a cryptographically signed receipt per response.
Anonymize client files on your computer before Claude reads them; real values restored locally.
Detect and redact PII and secrets (API keys, tokens) in text, HTML or PDF before it reaches an LLM.
Clean raw HTML into LLM-ready text before agents spend tokens.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.
Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.
Answers built from our own checks of this server.