MCP server for political bias detection using fine-tuned T5 model with LoRA adapters
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"bias-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Bias MCP Server [](https://badge.fury.io/py/bias-mcp-server) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://modelcontextprotocol.io/) A **Model Context Protocol (MCP)** server for political bias detection using a fine-tuned T5-large model with LoRA adapters. This server provides tools for analyzing news articles, opinion pieces, and political commentary for political leaning. ## Features - **Political Bias Detection**: Analyzes text for Left/Center/Right political leaning - **Bias Intensity**: Measures Low/Medium/High degree of bias - **Reasoning**: Provides explanations for classifications - **Hardware Acceleration**: Supports MPS (Apple Silicon), CUDA, and CPU - **MCP Integration**: Works with AI assistants that support the Model Context Protocol - **Batch Processing**: Analyze multiple texts efficiently ## Installation ### From PyPI (Recommended) ```bash pip install bias-mcp-server ``` **That's it!** The package includes the trained LoRA adapter (~18MB), so it works out of the box. ### Quick Start ```python from mcp_bias_server.bias_engine import BiasEngine # Works immediately - no additional setup needed engine = BiasEngine() result = engine.analyze("Your news text here...") print(result.to_dict()) ``` ### From Source ```bash git clone https://github.com/yourusername/bias-mcp-server.git cd bias-mcp-server pip install -e . ``` ## Usage ### As an MCP Server Add to your MCP settings configuration: **macOS/Linux:** ```json { "mcpServers": { "bias-analyzer": { "command": "bias-mcp-server", "env": { "BIAS_MODEL_PATH": "/path/to/bias-detector-output", "BIAS_BASE_MODEL": "t5-large", "BIAS_DEVICE": "a…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.