Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Katherine Communication MCP run a proxy check on this prompt"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Privacy-preserving real-time diagnostic for AI agent communication integrity. Detects model provider content manipulation via cross-lingual self-consistency — no model internals, no second provider, no prior knowledge of triggers required.
Reference implementation for: Privacy-Preserving Detection of Model Provider Content Manipulation via Cross-Lingual Self-Consistency (PoPETs 2027, under review).
# Clone
git clone https://github.com/anlimi555s/katherine-comm-mcp.git
cd katherine-comm-mcp
# Configure
cp config.example.json config.json
# Edit config.json with your API key, base URL, and model
# Run (MCP stdio protocol)
python server.pyRelated MCP server: EvalKit MCP Server
Tool | Description |
| Full pipeline: L2 transformation + dual-language canary + Neuro validation |
| Pipeline health, configuration, and transformation stats |
| Cumulative context toxicity (censorship event counter) |
| Reset toxicity counter (call after context flush) |
User Prompt
│
▼
[L0] Aho-Corasick multi-pattern match (CCP_GFW lexicon, <10ms)
│
├─ low risk ──▶ direct forward ──▶ response
│
└─ high risk ──▶ [L2] Chinese→English + abstraction
│
▼
[L3] Dual-language canary routing
(zh first → 400? → en fallback)
│
▼
[L4] Neuro: 4-judge validation
(length / status / refusal / entity)
│
▼
diagnostic label + responseserver.py (~100 lines): MCP stdio JSON-RPC server, 4 tools
pipeline.py (~200 lines): Core orchestration — pre-hook → send → post-hook
transform.py (~180 lines): Aho-Corasick word detection + L2 semantic transformation
toxicity.py: Cumulative toxicity scoring with configurable thresholds
{
"api": {
"base_url": "https://api.deepseek.com/v1",
"model": "deepseek-chat",
"format": "openai",
"timeout_s": 30
},
"wordlist": {
"path": "path/to/CCP_GFW_detector/words_list",
"tiers": ["red_light_word", "orange_light_word", "yellow_light_word"]
},
"toxicity": {
"threshold": 5,
"window_seconds": 3600
}
}Note: The CCP_GFW_detector word lists are pre-existing open-source data, re-used without modification. They are not included in this repository. Obtain them from their original source.
Validated on two Chinese-origin production models:
Model | Strategy | MCP CLEAN Rate | Baseline | Gain |
Qwen-Max | Symmetric hard blocking | 57.3% | 39.3% | +18pp |
DeepSeek V4 Pro | Asymmetric soft refusal | 70.8% ZH_REFUSED detected | 32.2% baseline | +38.6pp sensitivity |
Full experimental data, analysis scripts, and prompt sets: included in experiments/ (this repository). See experiments/README.md for dataset documentation and reproduction instructions.
AGPL-3.0. See LICENSE.
@article{cheng2026crosslingual,
title={Privacy-Preserving Detection of Model Provider Content Manipulation via Cross-Lingual Self-Consistency},
author={Cheng, Le},
journal={Proceedings on Privacy Enhancing Technologies},
year={2027},
note={Under review}
}This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
Deterministic AI audit layer for LLM/agent outputs: policy checks, tamper-evident log, x402.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/anlimi555s/katherine-comm-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server