SEOSiri-Official/biorobotics

An open-source, stateless Model Context Protocol (MCP) framework bridging the gap between biological datasets, physiological biosignals, and physical robotic actuation systems.
💖 Sponsorship & Open Source Attribution
This project is developed and maintained by **SEOSiri-Official** (Official website: seosiri.com).
To fund ongoing engineering research or scale the core physical kinematics engine, consider supporting the team via the SEOSiri Sponsors Page.
Architecture Overview
This framework acts as a stateless broker. Biological inputs (fetched dynamically from standard web APIs like UniProt or fallback reference data) and physiological biosignals (such as surface electromyography, or EMG) are digested, normalized via mathematical boundaries, and translated into explicit Cartesian physical coordinates represented strictly in International System (SI) units (meters). These coordinates are subsequently mapped to standardized G-code strings for physical motion planning or robotic prosthetic actuation.
Tools
This server exposes six MCP tools:
| Tool | Description |
|---|---|
| fetch_genomic_data | Queries live sequence parameters from the UniProt REST API, with a local fallback for offline or rate-limited conditions. |
| resolve_biotech_spatial_intent | Translates assay parameters (concentration, plate scale) into immutable spatial metrics in SI base units. |
| map_plate_coordinate | Translates alphanumeric well IDs (e.g. A1–H12) into exact millimeter offsets, per SLAS/SBS 96-well plate standards. |
| calculate_pipetting_speed | Calibrates G-code feedrate and pressure delay from reagent viscosity and target volume. |
| calculate_dna_melting_temp | Calculates GC-content and melting temperature (Tm) of a DNA sequence for thermal deck configuration. |
| translate_emg_to_actuation | Translates EMG muscle signals (µV) into safe joint angles and G-code velocity profiles, with a built-in safety envelope check. |
Quickstart (CLI Orchestrator)
This project utilizes a local-first Python runtime to bypass IDE proxy lags and regional API restrictions, offering a stable and deterministic execution channel.
1. **Install Package in Editable Mode:**
2. **Execute the Decoupled Orchestrator (Live UniProt Fetch):**
3. **Execute Using Fallback Database:**
4. **Verify the CI/CD Pipeline:**
🔌 How to Connect to Claude Desktop or Cursor IDE
You can connect this server to your local AI clients using one of two standard methods.
Method 1: Direct Execution from GitHub (Zero-Setup, Recommended)
If you have uv installed, you can run the server directly from our public repository without cloning it locally.
Open your claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json | macOS: ~/Library/Application Support/Claude/claude_desktop_config.json) and add this configuration:
Method 2: Local Execution (If Cloned)
If you have cloned this repository to your local drive (e.g., D:/my-century-biorobotics-core), configure your client to point to your local entry file:
Verified Live Test Results
All six tools have been independently tested against the running server via Glama.ai's browser-based MCP Inspector, with output matching each tool's closed-form mathematical model exactly: