foro-sh /

pii-mcp

Redact PII from MCP tool results before they reach the LLM. One-line FastMCP middleware, Python + TypeScript, Rust core

A new way for AI to search for data
View on GitHub
10GitHub stars

Rust, Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit c9cef47acf (2026-10-05).

Selected work

KD
@krishyaid-coder

“match street addresses with a comma before the house number”. 6 files, 210 lines in crates/pii-core, typescript, tests.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-11. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

fastmcpgdprmcppiiprivacyredactionai-securityanonymization

Example questions

The prompt

Paste it into your AI agent. It clones foro-sh/pii-mcp at the pinned commit and indexes it on your machine.

Search the GitHub repository foro-sh/pii-mcp with XERJ (https://hub.xerj.org/corpus/foro-sh--pii-mcp).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/foro-sh/pii-mcp pii-mcp && git -C pii-mcp checkout c9cef47acfbf6e8509d0a0d8bef916480ee5b024
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./pii-mcp --url http://127.0.0.1:9200 --prefix pii-mcp --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

KDAI, prompts and agents corporafastmcpgdpr-commonaccordeurlex-corebastyn-labs/bastyn-scanCIRVIX/agent-controlNavras98/PrivacyBridge

Selected work and consent: the XERJ registry.