Nexotype MCP Server — biomedical knowledge graph for drug discovery, genomics, and market intelligence
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":"nexotype-mcp","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.
# Nexotype MCP Server AI-powered biomedical knowledge graph for drug discovery, genomics, and market intelligence. Connect your AI tools to the Nexotype platform and query the biomedical knowledge graph through conversation. ## Installation ```bash pip install nexotype-mcp ``` Or with uv: ```bash # Install uv (if not already installed) brew install uv # Add uv tools to PATH (one-time setup) echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc source ~/.zshrc # Install nexotype-mcp uv tool install nexotype-mcp ``` Already installed? Update: ```bash pip install --upgrade nexotype-mcp # or uv tool upgrade nexotype-mcp ``` ## Authentication ```bash nexotype-cli login ``` Enter your email and password. Credentials are stored securely at `~/.nexotype/credentials.json` (chmod 600). ## Configure Your AI Client ### Claude Desktop Edit `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows): ```json { "mcpServers": { "nexotype": { "command": "nexotype-mcp" } } } ``` ### Claude Code ```bash claude mcp add nexotype -- nexotype-mcp ``` ### VS Code / Cursor Add to your MCP settings: ```json { "nexotype": { "command": "nexotype-mcp" } } ``` Restart the application after saving. ## Tools (28) ### Graph Intelligence (6 tools) | Tool | Description | |------|-------------| | `explore_network` | N-hop neighborhood of any entity | | `find_path` | Shortest path between two entities | | `find_similar` | Entities sharing the most relationships | | `company_deep_dive` | Full portfolio of a pharma/biotech company | | `drug_discovery` | Targets, pathways, indications for a drug | | `competitive_landscape` | All drugs and companies targeting a protein | ### AI Query (1 tool) | Tool | Description | |------|-------------| | `ask_knowledge_graph` | Natural language question → grounded answer from graph | ### Search & Browse (2 tools) | Tool | Description | |----…
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.