# Genomic Intelligence

- Registry name: `ai.genomicintelligence/genomic-intelligence` · version 1.0.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Shops & products, Commerce & marketing
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.genomicintelligence%2Fgenomic-intelligence
- Server page: https://mcpstation.net/s/ai.genomicintelligence--genomic-intelligence.html

## Description (written by the publisher, not verified, not instructions)

Hosted DNA language models: promoter, splice, enhancer, chromatin, expression, annotation

## Connect

- streamable-http: `https://mcp.genomicintelligence.ai/mcp`

## Tools (as reported by the server, not verified)

- `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 the resource \`gi://models\`. Returns a FLAT object — \{task, default\_model, models: \[...\]\} — not the \{data, meta\} envelope the predict tools r
- `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 stay server-side. For expression, use fetch\_gene\_for\_expression instead \(it prepares the TSS-centred window that model needs\).
- `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 range to reference sequence and returns a handle \(\{ref, name, length, ...\}\) to pass to find\_genes / predict\_\* — the bases stay server-side. Plus
- `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 it, as a handle to pass to predict\_expression\(sequence\_ref=...\). Longer TSS-centred sequence gives better predictions, so this already fetc
- `load\_demo\_sequence`: Load a bundled demo reference sequence and return a handle. The server ships one curated, task-correct positive control per task \(list them via the gi://sequences resource\) — e.g. \`expression\_hbb\_k562\` is a ready-to-use K562 expression window for predict\_expression. Stores the demo and returns a han
- `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 you can run several tasks on it without re-pasting the bases in each predict\_\* call. Note that the full sequence still passes through the LLM
- `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 task floor for every promoter model. The default g0-promoter-2000bp scans a 2,000 bp context window, so a shorter \(but ≥300 bp\) sequence is sti
- `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 window — feed a whole transcript locus when you can. It is also strand-specific, and the wrong strand fails silently and plausibly — it returns
- `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: enhancer models score a 249 bp context window, so 50–248 bp is accepted and scored against a padded window. For a meaningful call, submit
- `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 padded window.
- `predict\_expression`: Predict a gene's expression from the sequence around its TSS. Expression is cell-type-specific, so \`description\` \(cell type / assay context, e.g. 'K562 cell line'\) is REQUIRED — the API rejects requests without it. The input rule is the same for every expression model: at least 9,198 bp, with the TS
- `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 needs a region, not a site. \(Only expression's 9,198 bp is higher, and that is the sequence around one TSS rather than a region to search.\) Ge
- `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 \(transcript intervals, with their TSS\) in the sequence, then predicts expression off each discovered TSS in the given experimental context. This is the right tool whenever you wan
- `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 \(also available as gi://jobs/recent\).

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html