# Ranomics Platform

> Wet-lab triage for AI binder-design agents. Yeast display, mammalian display, DMS at library scale.

- name: com.ranomics/mcp
- version: 0.1.0
- connection class: R1 (autonomous)
- trust: 89/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.ranomics%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/com.ranomics%2Fmcp/tools

**An agent can connect on its own if it already holds `RANOMICS_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ranomics": {
      "type": "http",
      "url": "https://mcp.ranomics.com/mcp",
      "headers": {
        "Authorization": "Bearer ${RANOMICS_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${RANOMICS_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-133d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_targets (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_experiment_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_experiment_results (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,098 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 7, about 1,098 tokens to load them all
- tool set hash: 588bf1020cba29ce1c2b8faa48eb2227
- badge: [![protogrid quality](https://protogrid.dev/badge/com.ranomics/mcp.svg)](https://protogrid.dev/servers/com.ranomics/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.ranomics.com/mcp (streamable-http, auth api_key ${RANOMICS_TOKEN}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.