Jean by Melad Labs

browse_region

Read-only

Read one window of a genome the way a genome browser shows it: the cytogenetic bands it spans, the transcripts in the chosen RefSeq set, which residues of each protein the window encodes (translated from the assembly’s own bases), how many dbSNP 155 variants fall in it and how many ClinVar calls pathogenic, and every CRISPR site for the chosen nuclease (SpCas9 unless told otherwise) with its strand, cut position and on-target scores.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "assembly": "<assembly>"
    },
    "name": "browse_region"
  }
}

Input Schema

Name	Required	Description	Default
`gene`	No	a gene symbol; the window is its MANE Select (or HGNC) transcript with a 2% margin either side. Takes precedence over `locus`.
`locus`	No	the window, 1-based and inclusive, when no `gene` is given.
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
`assembly`	Yes	the UCSC assembly name (hg38, hg19, mm39…).
`nuclease`	No	which nuclease the CRISPR sites are enumerated for (its PAM and cut rule). On-target scores are SpCas9-trained and come back null for any other. Values: SpCas9 (SpCas9 · NGG), SpCas9-NG (SpCas9-NG · NG), SpG (SpG · NGN), SpRY (SpRY · NRN), xCas9 (xCas9 · NG), SaCas9 (SaCas9 · NNGRRT), SaCas9-KKH (SaCas9-KKH · NNNRRT), AsCas12a (AsCas12a · TTTV), LbCas12a (LbCas12a · TTTV), enAsCas12a (enAsCas12a · TTTV).	SpCas9
`gene_track`	No	which RefSeq set the transcripts and protein residues come from. Values: ncbiRefSeqSelect (RefSeq Select and MANE), ncbiRefSeqCurated (RefSeq Curated), ncbiRefSeq (RefSeq All), ncbiRefSeqPredicted (RefSeq Predicted).	ncbiRefSeqSelect

Output Schema

Name	Required	Description
`sites`	Yes	CRISPR sites: spacer, PAM, strand, 1-based protospacer bounds, cut position and Rule Set 1 / CRISPRscan scores
`window`	Yes	the window read, 1-based inclusive, and how it was reached
`protein`	Yes	per transcript: accession, strand, the first and last residue numbers in the window and the residues themselves
`summary`	Yes	what each lane found in the window, generated from the run
`refusals`	Yes	each lane that did not run for this window, and why

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered; the description usefully adds what external sources are touched (UCSC assembly bases, RefSeq sets, dbSNP 155, ClinVar) and that protein residues are translated from the assembly's own bases rather than an external protein record. It also warns that on-target scores come back null for non-SpCas9 nucleases. Remaining gaps are practical: nothing about cost, latency, or behavior on very large windows or unknown genes.

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?

It is front-loaded with the verb and resource, and every clause in the enumeration corresponds to a real output class, so there is little pure filler. The weakness is structure: it is one long comma-chained sentence whose payload list would read better as separate statements.

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

Completeness4/5

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

For a read-only browsing tool with a full output schema and 100%-covered parameters, the description supplies enough for correct invocation, and it wisely does not re-document input formats. Its main inefficiency is that most of the text re-enumerates return content already described by the output schema, while practical constraints (window size limits, missing-gene behavior) go unmentioned.

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 coverage is 100%, so every parameter already carries its own documentation, including the gene-vs-locus precedence and the full nuclease enum with PAM rules. The description only echoes 'the chosen RefSeq set', 'the chosen nuclease', and the SpCas9 default, adding no syntax, format, or edge-case meaning beyond the schema. Baseline 3 is correct here.

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 gives a specific verb and resource ('Read one window of a genome') and then enumerates exactly the deliverables: cytogenetic bands, RefSeq transcripts, encoded protein residues, dbSNP 155/ClinVar counts, and CRISPR sites with strand, cut position and on-target scores. That is far beyond a restatement of the name. It stops short of naming how it differs from close siblings such as annotate_region or lookup_gene, so it lands at 4 rather than 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?

Framing it as 'the way a genome browser shows it' implies the browsing use case, and 'SpCas9 unless told otherwise' hints at the default nuclease path. But there is no explicit when-to-use versus when-to-use-something-else guidance, no mention of when a caller should prefer annotate_region, lookup_gene, or crispr_design_guides, and no stated prerequisites.

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

All Jean by Melad Labs tools Inspect

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

Need Help?