Skip to main content
Glama

Ensembl

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Vep

vep
Read-onlyIdempotent

"What's the effect of [variant]" / "predict consequences of [genomic change]" / "VEP for [chrom:pos]" — Variant Effect Predictor for a specified region + allele. Returns consequences (missense, synonymous, splice, etc.), affected genes, transcript impacts, SIFT/PolyPhen predictions. Use for variant interpretation in clinical or research genomics. THE REGION IS REQUIRED — there is no default. A GRCh37/hg19 position is also a valid GRCh38 position, so an unstated build cannot be detected, only guessed wrong, and a wrong guess returns confident annotations for a DIFFERENT gene rather than an error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
alleleYese.g. "C"
regionYese.g. "9:22125504-22125504:1" — in the build named by assembly.
speciesYes
assemblyYesREQUIRED. The genome build your region is in: "GRCh38" (= hg38) or "GRCh37" (= hg19). There is no default on purpose — a genomic position is valid in BOTH builds, so an unstated build cannot be detected, only guessed wrong, and a wrong guess returns confident consequence calls for a different gene instead of an error.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNumber of items returned.
itemsYesVariant Effect Predictor results

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "allele": "C",
-    "region": "9:22125504-22125504:1",
-    "species": "human"
-  },
-  {
-    "allele": "A",
-    "assembly": "GRCh37",
-    "region": "1:11856378-11856378:1",
-    "species": "human"
-  }
-]New value: +[
+  {
+    "allele": "C",
+    "assembly": "GRCh38",
+    "region": "9:22125504-22125504:1",
+    "species": "human"
+  },
+  {
+    "allele": "A",
+    "assembly": "GRCh37",
+    "region": "1:11856378-11856378:1",
+    "species": "human"
+  }
+]
    • changedInput schema / properties / assembly / description
      Previous value: -"Human genome build: \"GRCh38\" (the default) or \"GRCh37\" (= hg19). Coordinates you pass and coordinates you get back are both in this build. Older variant lists, spreadsheets and published tables are usually GRCh37."New value: +"REQUIRED. The genome build your region is in: \"GRCh38\" (= hg38) or \"GRCh37\" (= hg19). There is no default on purpose — a genomic position is valid in BOTH builds, so an unstated build cannot be detected, only guessed wrong, and a wrong guess returns confident consequence calls for a different gene instead of an error."
    • changedInput schema / properties / region / description
      Previous value: -"e.g. \"9:22125504-22125504:1\" — in the build named by assembly (GRCh38 by default)."New value: +"e.g. \"9:22125504-22125504:1\" — in the build named by assembly."
    • changedInput schema / required
      Previous value: -[
-  "species",
-  "region",
-  "allele"
-]New value: +[
+  "species",
+  "region",
+  "allele",
+  "assembly"
+]
  2. Changed3 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "allele": "C",
-    "region": "9:22125504-22125504:1",
-    "species": "human"
-  }
-]New value: +[
+  {
+    "allele": "C",
+    "region": "9:22125504-22125504:1",
+    "species": "human"
+  },
+  {
+    "allele": "A",
+    "assembly": "GRCh37",
+    "region": "1:11856378-11856378:1",
+    "species": "human"
+  }
+]
    • addedInput schema / properties / assembly
      Added value: +{
+  "description": "Human genome build: \"GRCh38\" (the default) or \"GRCh37\" (= hg19). Coordinates you pass and coordinates you get back are both in this build. Older variant lists, spreadsheets and published tables are usually GRCh37.",
+  "type": "string"
+}
    • changedInput schema / properties / region / description
      Previous value: -"e.g. \"9:22125504-22125504:1\""New value: +"e.g. \"9:22125504-22125504:1\" — in the build named by assembly (GRCh38 by default)."
  3. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "allele": "C",
+    "region": "9:22125504-22125504:1",
+    "species": "human"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Number of items returned.",
+      "type": "integer"
+    },
+    "items": {
+      "description": "Variant Effect Predictor results",
+      "items": {
+        "properties": {
+          "allele_string": {
+            "description": "Reference/alternate alleles",
+            "type": "string"
+          },
+          "end": {
+            "description": "End position",
+            "type": "integer"
+          },
+          "seq_region_name": {
+            "description": "Chromosome",
+            "type": "string"
+          },
+          "start": {
+            "description": "Start position",
+            "type": "integer"
+          },
+          "strand": {
+            "description": "Strand",
+            "type": "integer"
+          },
+          "transcript_consequences": {
+            "description": "Predicted consequences",
+            "items": {
+              "properties": {
+                "biotype": {
+                  "description": "Transcript biotype",
+                  "type": "string"
+                },
+                "consequence_terms": {
+                  "description": "Consequence term list",
+                  "items": {
+                    "type": "string"
+                  },
+                  "type": "array"
+                },
+                "gene_id": {
+                  "description": "Gene ID",
+                  "type": "string"
+                },
+                "hgvsc": {
+                  "description": "HGVS cDNA notation",
+                  "type": "string"
+                },
+                "hgvsp": {
+                  "description": "HGVS protein notation",
+                  "type": "string"
+                },
+                "impact": {
+                  "description": "Predicted impact",
+                  "type": "string"
+                },
+                "transcript_id": {
+                  "description": "Transcript ID",
+                  "type": "string"
+                }
+              },
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "variant_id": {
+            "description": "Variant identifier",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "items",
+    "count"
+  ],
+  "type": "object"
+}
  4. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description's main job is to add operational caveats. It does so strongly: there is no default region or assembly, and it explains that guessing the build can silently return confident annotations for a different gene rather than an error. This is exactly the kind of failure-mode transparency that helps an agent call the tool safely.

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?

The description leads with concrete query phrasings, immediately states the tool's purpose, and front-loads the required-region warning. The assembly caveat is somewhat repetitive with the schema description, but it is important enough to merit emphasis. Overall the structure is efficient and scannable.

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

Completeness5/5

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

For a read-only lookup tool with four required parameters and a provided output schema, the description covers all critical operational context: what the tool returns, when to use it, that region is required, and the build-ambiguity hazard. The output schema handles return-shape documentation, and annotations cover safety, so nothing essential is missing.

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

Parameters3/5

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

Schema description coverage is 75%, so the schema already documents region, allele, assembly, and species reasonably well. The description reinforces that region is required and explains assembly ambiguity, but it largely duplicates the assembly text already present in the schema. It does not add new semantic detail about the allele parameter's format or species values, so it provides only marginal value beyond the schema.

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

Purpose5/5

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

The description opens with natural-language phrasings of the task ('What's the effect of [variant]', 'predict consequences of [genomic change]'), then names the resource precisely: Variant Effect Predictor for a specified region plus allele. It enumerates outputs (consequences, genes, transcript impacts, SIFT/PolyPhen), making its purpose unambiguous and readily distinguishable from sibling tools like sequence or variation.

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

Usage Guidelines4/5

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

The description gives an explicit use context: 'Use for variant interpretation in clinical or research genomics.' It also warns strongly about the required region and genome build, which is important guidance for correct invocation. However, it does not explicitly name alternatives or state when not to use VEP versus other lookup tools, so it stops short of a 5.

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

All Ensembl toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources