Genomics MCP

Official

Overview Schema Source Related Servers Discussions Admin

get_features

Read-only

Retrieve genomic features overlapping a specified interval from indexed BED, GFF3, GTF, or bigBed files, with optional feature-type and record limits.

Instructions

Features overlapping an interval from indexed BED/GFF3/GTF or bigBed. Available for: bed, bigbed, gff3, gtf.

Input Schema

TableJSON Schema

Name	Required	Description
`file`	Yes
`interval`	Yes
`max_records`	No	Lower the record limit.
`feature_types`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`error`	No	Set when status is error.
`errors`	No	Per-source failures in partial results.
`limits`	No
`status`	Yes
`warnings`	No
`operation`	Yes
`provenance`	No
`truncation`	No
`source_status`	No
`schema_version`	No		1
`metadata_omitted`	No	Entries dropped from provenance/source_status/errors/warnings (or text shortened) to fit max_response_bytes. Absent when metadata is complete.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.1Sep 28, 2026

addedOutput schema / properties / metadata_omitted

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "integer"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Entries dropped from provenance/source_status/errors/warnings (or text shortened) to fit max_response_bytes. Absent when metadata is complete.",
+  "title": "Metadata Omitted"
+}

First observedv0.1.0Sep 24, 2026

TDQS

B3.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the useful nuance that the source must be 'indexed' and enumerates supported formats, but says nothing about what happens when the index is missing, whether results are truncated, or how large result sets are limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler, and the core operation is front-loaded before the format list. It is efficient, though terse to the point of under-specification for a tool with four parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be described, but for a four-parameter genomic tool with a nested FileRef and an Interval requiring an explicit assembly, the description leaves the two optional parameters, result limiting, and index/assembly prerequisites unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% across 4 parameters. The description clarifies the interval/file-format dimension, but 'max_records' and 'feature_types' are completely undocumented in both the schema and the description, so the description does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('Features overlapping an interval') and the file formats it applies to (BED/GFF3/GTF/bigBed), so an agent can tell what it returns. It does not distinguish itself from siblings like get_variants, get_signal, or get_coverage, which also read interval-scoped data, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Available for: bed, bigbed, gff3, gtf' clause implicitly tells the agent the tool only applies to those formats, which is useful routing guidance. However, it never names the alternative tools for other formats or data types, nor states prerequisites (e.g. index required) beyond the word 'indexed'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.