# Genomicintelligence Genomic Intelligence MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.genomicintelligence%2Fgenomic-intelligence
Registry id: `mcp-registry/ai.genomicintelligence/genomic-intelligence`
Status: live (checked 2026-10-26T19:47:42.202Z)

## Verdict

Genomicintelligence Genomic Intelligence MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 591 ms median handshake and 6 outages in 90 days. Its agent-readiness grade is A (100/100) across 15 tools, costing an agent about 5,053 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 591 ms | 44% of MCP servers |
| p95 handshake latency | 2427 ms | — |
| Checks in 30 days | 4,882 | — |
| Outages, 90 days | 6 | — |
| Median recovery | 2 min | — |
| Agent-readiness score | 100/100 (A) | 94% of MCP servers |
| Tools | 15 | — |
| Tool-list size for an agent | ~5,053 tokens | 38% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "genomicintelligence-genomic-intelligence": {
      "type": "http",
      "url": "https://mcp.genomicintelligence.ai/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http genomicintelligence-genomic-intelligence https://mcp.genomicintelligence.ai/mcp
```

## Tools (15)

- `fetch_ensembl_sequence`: Fetch a gene's reference sequence from Ensembl and store it. Returns a handle ({ref, name, length, preview, ...}). Pass the `ref` to predict_* tools — the bases
- `fetch_gene_for_expression`: Fetch a gene's sequence prepared for expression prediction. Resolves the gene's canonical-transcript TSS via Ensembl and stores a gene-sense sequence centred on
- `fetch_region`: Fetch a genomic region by coordinates from Ensembl and store it. For "find the genes in chr8:127,680,000-127,800,000"-style requests: resolves a coordinate rang
- `find_genes`: Find genes (transcript intervals) in a genomic region (async, ~8-25s). Takes 1,000–500,000 bp. The floor is the strictest of the scanning tasks: gene finding ne
- `find_genes_and_predict_expression`: Find genes in a sequence, then predict each gene's expression (composite). Server-side chaining in ONE call: finds genes (transcript intervals, with their TSS) 
- `get_job`: Poll an async job once. Returns the {data, meta} result if complete, a progress envelope if still running, or an error envelope if it failed. 
- `list_jobs`: List the caller's recent async jobs (also available as gi://jobs/recent).
- `list_models`: List available models for a task. Use to discover model ids before passing one as the `model` argument to a predict tool. The same catalog is also available as 
- `load_demo_sequence`: Load a bundled demo reference sequence and return a handle. The server ships one curated, task-correct positive control per task (list them via the gi://sequenc
- `predict_chromatin`: Chromatin annotation across 919 features (G0 DeepSEA). 200–500,000 bp. The model reads a 1,000 bp context window; 200–999 bp is accepted and scored against a pa
- `predict_enhancer`: Predict enhancer activity (G0 DeepSTARR). 50–500,000 bp. 50 bp is the task's admission floor (the API 422s below it), not a statement about what the model reads
- `predict_expression`: Predict a gene's expression from the sequence around its TSS. Expression is cell-type-specific, so `description` (cell type / assay context, e.g. 'K562 cell lin
- `predict_promoter`: Predict promoter regions (G0). 300–500,000 bp. Returns the {data, meta} envelope: data.regions lists predicted promoters with start/end/score. 300 bp is the tas
- `predict_splice`: Predict splice donor/acceptor sites (G0 BigBird). 100–500,000 bp. The model reads a 15,000 bp context window, so anything shorter is scored against a padded win
- `store_inline_sequence`: Store a human-pasted sequence and return a handle to re-use it. For a sequence you've already pasted into the conversation, this gives back a short handle so yo

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.