Back to search
100
MCP live v1.0.0 MCP 2025-11-25 streamable-http

Genomic Intelligence

ai.genomicintelligence/genomic-intelligence

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

Uptime
5.9%
17 probes
Response
1404ms
last probe
Tools
15
callable
Resources
6
readable
Prompts
2
available
Primary URL
https://mcp.genomicintelligence.ai/mcp

Tools · 15

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 `g…

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 …

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…

fetch_gene_for_expression

Fetch a gene's sequence prepared for expression prediction. Resolves the gene's TSS via Ensembl and returns the exact TSS-centred window the expression model needs, as a handle to …

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. …

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…

predict_promoter

Predict promoter regions (G0). Up to 500,000 bp. Returns the {data, meta} envelope: data.regions lists predicted promoters with start/end/score.

predict_splice

Predict splice donor/acceptor sites (G0 BigBird). Up to 500,000 bp.

predict_enhancer

Predict enhancer activity (G0 DeepSTARR). Up to 500,000 bp.

predict_chromatin

Chromatin annotation across 919 features (G0 DeepSEA). Up to 500,000 bp.

predict_expression

Predict a gene's expression from a TSS-centred input window. Expression is cell-type-specific, so `description` (cell type / assay context, e.g. 'K562 cell line') is REQUIRED — the AP…

find_genes

Find genes (transcript intervals) in a genomic region (async, ~8-25s). Gene-finding: detects transcript boundaries (TSS + PolyA) and returns one interval per predicted transcript — st…

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 p…

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).

Resources · 6

GI model catalog

All models across the six tasks, with their bio specs.

gi://models
GI task overview

What each of the six tasks does, sync/async, and length bounds.

gi://docs/tasks
GI OpenAPI contract

Live OpenAPI 3.0 spec for the /v1 API.

gi://openapi.json
GI demo sequences

Curated reference FASTAs bundled with the server (one positive control per task). Load one into a handle with load_demo_sequence.

gi://sequences
GI recent jobs

The caller's recent async inference jobs and their status.

gi://jobs/recent
GI account / connectivity

Configured backend, health, and the tasks this server exposes.

gi://account

Prompts · 2

gi-promoter-screen

Fetch a gene and scan it for promoters, reporting strong hits.

gi-expression-screen

Predict expression for a gene from its TSS-centred window.

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "genomic_intelligence": {
      "url": "https://mcp.genomicintelligence.ai/mcp",
      "transport": "streamable-http"
    }
  }
}