Skip to main content
Glama
anlimi555s

Katherine Communication MCP

by anlimi555s
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Katherine Communication MCP

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).

Quick Start

# 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.py

Related MCP server: EvalKit MCP Server

Tools

Tool

Description

proxy_check

Full pipeline: L2 transformation + dual-language canary + Neuro validation

proxy_status

Pipeline health, configuration, and transformation stats

toxicity_score

Cumulative context toxicity (censorship event counter)

toxicity_reset

Reset toxicity counter (call after context flush)

Architecture

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 + response

Pipeline

  • server.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

Configuration

{
  "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.

Experimental Results

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.

License

AGPL-3.0. See LICENSE.

Citation

@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 deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • ToGMAL MCP Server

    HeTalksInMaths
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides real-time, privacy-preserving analysis of LLM interactions to detect problematic behaviors like medical advice, dangerous file operations, physics speculation, and unsupported claims. Recommends safety interventions and builds a taxonomy of LLM limitations through crowdsourced evidence collection.
    -

  • EvalKit MCP Server

    tr4m0ryp
    A
    license
    B
    quality
    D
    maintenance
    Enables testing AI safety classifier robustness against query decomposition, obfuscation, and multi-agent attacks. Provides tools for full evaluation pipelines, query previews, and status checks.
    4
    5
    MIT
  • creedspace-mcp by Creed-Space

    creedspace-mcpofficial

    Creed-Space
    A
    license
    B
    quality
    A
    maintenance
    AI safety guardrails for any LLM in ~10 seconds: constitutional-AI content evaluation over MCP, with six configurable personas.
    16
    49 npm
    MIT
  • EVIDIQ Bulwark by evidiq

    EVIDIQ Bulwarkofficial

    evidiq
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides deterministic scanning and detection of prompt injection, jailbreak, data-exfiltration, and system-prompt leaks, with EIP-191 signed attestations and 0G Storage anchoring for verifiable safety reports.
    1
    MIT