Jean by Melad Labs

blast_project_sequences

Read-only

Search a sequence against THIS PROJECT'S OWN records with blastn or blastp, on this machine: the local database is built from every project record of the program's alphabet, and every E-value is computed from that database's own size. Use it to ask which of my constructs, reads or proteins carry this span. Nothing leaves the machine; for public databases use blast_search.

Input Schema

Name	Required	Description	Default
`_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.
`region`	No	which part of the open record to search, when no sequence is wired in. Values: whole (the whole record), selection (the current selection), feature (a named feature).	whole
`feature`	No	the feature's name, matched case-insensitively on the open record. Only applies when region is feature.
`program`	No	blastn searches the nucleotide records, blastp the protein records. Values: blastn (blastn · nucleotide query), blastp (blastp · protein query).	blastn
`_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.
`sequence`	No	the query. Wire a record or a sequence output, or paste raw/FASTA. Left empty, the region below is taken from the open record.
`maxExpect`	No	E-value cutoff (BLAST+'s -evalue); hits above it are not reported.

Output Schema

Name	Required	Description
`hits`	Yes	every hit, with its HSPs, accession, organism and the links the service sent
`topHit`	Yes	the best hit by E-value: what a "what is this?" step reads
`tabular`	Yes	the hits as BLAST's own outfmt 6 table, for download or a downstream parser
`hitCount`	Yes	how many subjects matched
`sequences`	Yes	the hit subjects as FASTA, ready to wire straight into an alignment or a tree
`topExpect`	Yes	the best hit's E-value; wire into a $when to branch on significance
`provenance`	Yes	the binary, the command line EBI ran, the databases as built, and the search space the E-values are relative to
`topCoverage`	Yes	what fraction of the query the best hit covers, 0–1
`topIdentity`	Yes	percent identity of the best hit's best HSP

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 25, 2026
- addedOutput schema / properties / topIdentity / x-unit
```
Added value: +"%"
```
First observedOct 20, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description still adds real substance: the database is built from every project record of the program's alphabet, so E-values are computed against that local database size, and nothing leaves the machine. That statistical caveat is exactly the kind of context annotations cannot convey, though return shape is left entirely to the output schema.

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

Conciseness5/5

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

Three sentences, front-loaded with the verb and the scope, then the use case, then the alternative. No filler and nothing repeated from structured fields.

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 7-parameter nested tool with an output schema, the description covers the things an agent cannot infer: local-vs-public routing, what populates the local database, and how E-values are affected. Return values are correctly left to the output schema.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description goes further by explaining that the program choice determines which records form the database ('of the program's alphabet'), tying blastn/blastp to search behavior rather than just declaring an enum, and it clarifies the fallback to the open record's region when no query sequence is wired in.

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?

States a specific verb (search) plus the exact resource and scope: this project's own records, on this machine, with blastn or blastp. It explicitly contrasts itself with blast_search, so an agent can pick it over that sibling without opening either schema.

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

Usage Guidelines5/5

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

Gives a concrete use case ('ask which of my constructs, reads or proteins carry this span') and an explicit exclusion plus alternative ('for public databases use blast_search'). The when-not condition is stated, not inferred.

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?