Ranomics Platform
About
Wet-lab triage for AI binder-design agents. Submit computational protein designs, get back yeast-display enrichment and called hits.
Details
- Author
- leowan7
- Downloads
- 287
- Categories
- Other, AI
Jump to
- Programmatic access to wet-lab protein validation
- Supports yeast surface display, mammalian display, DMS
- Returns enrichment ratios, NGS counts, and called hits
- Designed for AI workflows with 10,000+ candidates
- Seven tools cover the full experiment lifecycle
- Uses streamable-http transport with Bearer token auth
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Ranomics PlatformCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Obtain a Bearer token from https://tools.ranomics.com/account/api-keys and configure the server with that token. Then invoke any of the seven tools: list_targets, estimate_cost, submit_experiment, get_experiment_status, get_experiment_quote, confirm_quote, or get_experiment_results.
list_targets
List the calibrated antigen catalogue. Each entry carries target_id, supported_experiment_types, and typical_campaign_range_usd. Use the target_id on submit_experiment to skip human scoping, or use the custom target shape for a one-off antigen.
estimate_cost
Non-binding USD cost estimate for a hypothetical submission. Pass target_kind='catalog' + target_id for a calibrated band (requires_human_quote=false), or target_kind='custom' for a placeholder order-of-magnitude band (requires_human_quote=true). Call BEFORE submit_experiment when budgeting matters.
submit_experiment
Submit a binder panel for wet-lab triage. The experiment_spec mirrors the curl /api/v1/experiments contract: experiment_type (yeast_display/mammalian_display/dms), target (target_id or custom), library_design, and sequences as {user_key: amino_acid_string} (use ':' as a multi-chain separator). Optional webhook_url receives signed POSTs on every status transition. Optional idempotency_key dedupes retries. Returns the created experiment with status WaitingForConfirmation and a status_log. Poll get_experiment_status to track progress, get_experiment_results when status_log shows Done.
get_experiment_status
Poll an experiment by id. Returns the current status (Draft/WaitingForConfirmation/QuoteSent/WaitingForMaterials/LibraryConstruction/Sorting/NGS/DataAnalysis/InReview/Done), the orthogonal results_status (none/partial/all), and the status_log. Cheap; safe to poll every few minutes. Webhooks are preferred for production agents.
get_experiment_quote
Fetch the quote for an experiment once status is QuoteSent. Returns quote_id, total_usd, currency (default USD), line_items, valid_until, and terms_url. If status is QuoteSent but the scoping team has not posted a price yet, total_usd is null and a 'note' field explains it is being finalised; poll again until total_usd populates. Pass the quote_id to confirm_quote to accept.
confirm_quote
Accept a quote. Moves the experiment from QuoteSent to WaitingForMaterials. Call after a human (or budget guard) has approved the total_usd from get_experiment_quote. Returns 409 quote_not_confirmable if status is not QuoteSent, or 409 quote_not_finalized if a price has not been posted yet (total_usd null). Fetch get_experiment_quote and wait for total_usd before confirming.
get_experiment_results
Fetch results once results_status is 'partial' or 'all' (check via get_experiment_status first). Returns per-sequence pre/post counts, log2_enrichment, percentile, called_hit booleans, plus signed download URLs for the enrichment table CSV, hits FASTA, and (when opted in) raw FASTQ. Yeast-display result shape; mammalian and DMS use the same envelope.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ranomics platform": {
"ranomics": {
"url": "https://mcp.ranomics.com/mcp",
"headers": {
"Authorization": "Bearer rk_live_..."
}
}
}
}
}McpServers
{
"ranomics": {
"url": "https://mcp.ranomics.com/mcp",
"headers": {
"Authorization": "Bearer rk_live_..."
}
}
}The Ranomics MCP server gives AI binder-design agents programmatic access to wet-lab validation. Submit a panel of computationally designed proteins or antibody binders against a target, and the upstream Ranomics Platform runs yeast surface display, mammalian display, or deep mutational scanning at library scale. You get back per-sequence enrichment ratios, NGS counts, and called hits.
Library-scale triage. Designed for the AI workflow that has 10,000+ MPNN, RFdiffusion, or BindCraft candidates and can't afford per-sequence kinetics on all of them. Use Ranomics first to enrich down to the top 100 or 200, then take those to a biophysics vendor for binding kinetics.
Seven tools cover the full lifecycle: list_targets, estimate_cost, submit_experiment, get_experiment_status, get_experiment_quote, confirm_quote, get_experiment_results.
Transport: streamable-http. Auth: Bearer token from https://tools.ranomics.com/account/api-keys.
Also published to the official MCP Registry as com.ranomics/mcp.
Contact: info@ranomics.com
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
