Jean by Melad Labs

recombine

Recombination between molecules — Gateway BP/LR (att sites), Cre/loxP, a serine integrase whose two half-sites you supply, plain homologous recombination through shared arms, or a CRISPR knock-in that keeps only products whose repair region contains every guide's cut.

Input Schema

Name	Required	Description	Default
`site1`	No	the recombinase's first half-site (e.g. attP). Case is meaningful: the lower-case middle is the overlap the enzyme crosses over in. Only applies when system is recombinase.
`site2`	No	the recombinase's second half-site (e.g. attB), same convention. Only applies when system is recombinase.
`_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.
`greedy`	No	permissive att core matching. Only applies when system is gateway-BP or gateway-LR. Advanced.
`guides`	No	protospacers whose cut must fall inside the repaired region — a product cut elsewhere by any of them is discarded and counted. Only applies when system is crispr-knock-in.
`system`	No	recombination system. Values: gateway-BP (Gateway BP (attB × attP → entry)), gateway-LR (Gateway LR (attL × attR → expression)), cre-lox (Cre / loxP), recombinase (Serine integrase (your two half-sites)), homologous (Homologous recombination (shared arms)), crispr-knock-in (CRISPR knock-in (guide-gated HR)).	gateway-LR
`_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.
`fragments`	No	the molecules to react — wire upstream `record` outputs here, or name library documents.
`homology_bp`	No	shortest homology arm that counts as a shared end. In bp. Only applies when system is homologous or crispr-knock-in.
`circular_only`	No	report only circular products.
`include_subject`	No	also include the node's subject as a reactant.
`multi_site_only`	No	keep only products where BOTH sites recombined (drops single-site intermediates). Only applies when system is gateway-BP or gateway-LR.

Output Schema

Name	Required	Description
`sites`	Yes	per-input report of the recombination sites found
`record`	Yes	the first product, as a record
`products`	Yes	every product
`discarded`	Yes	CRISPR knock-in only: products dropped because a guide also cuts OUTSIDE the repair. A non-zero count is a finding about the guide, not a warning to swallow
`productCount`	Yes	number of products

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already mark this as a non-read-only, non-destructive, closed-world computation. The description adds real behavioral context for crispr-knock-in ('keeps only products whose repair region contains every guide's cut'), but says nothing about default filtering behavior (multi_site_only, circular_only defaulting true) or what is discarded and counted.

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?

A single front-loaded sentence with a scannable enumeration of the six modes. Slightly dense but every clause maps to a real system choice; no filler.

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

Completeness3/5

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

With 12 params, nested _subject/_files wiring, a default system, and an output schema, the description covers the mode menu but omits the project/file input model and default filtering defaults. Adequate but not complete for a tool this broad.

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 100%, so the params are fully documented in the schema (site1/site2 scope, greedy, guides, homology_bp). The description's 'two half-sites you supply' paraphrases the schema and adds no meaning beyond it, so the baseline 3 applies.

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?

States a specific verb and resource ('Recombination between molecules') and enumerates the six reaction modes matching the system enum, so the agent knows exactly what the tool does. It does not differentiate from sibling assembly tools such as gibson_assemble, golden_gate_assemble, or ligate_fragments.

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 list of systems implicitly tells the agent which biology maps here (Gateway, Cre/lox, integrase, HR, CRISPR knock-in), but there is no explicit when-to-use/when-not, no mention of the default system being gateway-LR, and no routing away from the assembly siblings.

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?