jean — Molecular Biology & Genomics
MCP server · hosted · v1.0.1 · io.github.genmnz/jean
Online · tested 2h agoNEW · 3h agoNew version 2h agoSeen in the registry 1h ago
Validated molecular biology tools: cloning, primers, CRISPR, Sanger, alignment, qPCR, phylogenetics
What it does
jean — Molecular Biology & Genomics is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.
No capability identified yet from its description.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence) and are not a test of the tool.
At a glance
Hosted (remote)YES
Local installNO
Live checkOnline · 289 tools
Version1.0.1
PriceNot in the registry
First seen20 Oct 2026
Last checked1h ago
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 2h ago (live check)Hosted endpoint
https://jeanslabs.vercel.app/mcpstreamable-http
In Claude Code: claude mcp add --transport http jean-molecular-biology-genomics https://jeanslabs.vercel.app/mcp
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"jean-molecular-biology-genomics": {
"url": "https://jeanslabs.vercel.app/mcp"
}
}
}Live check
Electra Index connected to the hosted endpoint 2h agoONLINE jean — Molecular Biology & Genomics answered an MCP connection on 20 Oct 2026 and introduced itself as jane-engine 1.0.0 (MCP protocol 2025-06-18).
289 tools offered to AI assistants
list_workflow_templates· The built-in starter workflows — id, name, what each does and which tools it chains. Pass an `id` to get that template’s graph back, ready to hand to `run_workflow`. This server is stateless, so these are the shipped templates only, not anyvalidate_workflow· Would this workflow graph run? Returns the blocking errors — an unknown tool, a wire into a port that does not exist, a cycle — each naming the node and the port, without running anything.run_workflow· Run a workflow graph: nodes naming tools, wires carrying one node’s output into another’s input, `$whenExpression` to make a step conditional, and `scatter` to run a step once per element of a list. Returns the run record — per-node status,get_open_record· Return the plasmid/sequence currently open in the editor. Emits it as a `record`, so it is the SOURCE node of a pipeline — wire its record into any downstream node's $subject.load_record· Read a CHOSEN project document as a record — the pipeline's data-reader source, for running on a specific file instead of whatever happens to be open in the editor. Wire its `record` into any downstream node's $subject.list_library· List the project's sequence documents (id, name, length, topology, kind).find_restriction_sites· Cut positions of the given enzymes on the open plasmid (top/bottom cut, overhang, kind).find_star_sites· Where the given enzymes could ALSO cut the open plasmid under non-standard conditions, from REBASE's own star-activity list and its one-base rule. Not cut sites: these need low ionic strength, high pH, Mn²⁺ for Mg²⁺, glycerol, DMSO or somecheck_methylation_block· Whether the host's own methylation blocks the given enzymes ON THIS PLASMID, from REBASE's methylation-sensitivity tables localised onto your sites. The other term of the same reaction question `find_star_sites` answers. It is deliberatelydigest_reaction_conditions· The reaction a digest needs, from NEB's own data: the NEBuffer that serves every enzyme together (scored on the WORST enzyme's percent activity, a star-activity buffer disqualified at any percent), the incubation temperature(s), any cofactoenzyme_cut_counts· Per-enzyme cut counts on the open plasmid (the EcoRI² superscript-badge numbers).export_map_svg· Render the open plasmid's circular map to a publication SVG string — the same figure the Export panel draws, with the same knobs and the same defaults. Give it enzymes to draw the outer restriction-site ring.
Show 88 more
run_gel_lane· Resolve a gel lane (ladder / plasmid / digest / pcr) into [bp, form] bands for the open plasmid.draw_gel· Run an agarose gel and photograph it: every lane's fragments migrated by the validated pydna model, drawn as a gel-doc image with the marker ladder's bp marks and each lane's name. The same plate the gel panels draw, so the figure and the rprimer_check· Where a primer anneals on the open plasmid: 3'-anchored sites with identity % and the ✓/⚠/~/✗ verdict, graded at a bar you can move and that the answer states. The scan is 3'-anchored, so every site it reports matches the oligo's 3' seed exdesign_oligo_plate_order· Lay a set of oligos out as a supplier's PLATE order sheet: one worksheet per plate, in the well order the supplier's own order form fills, with the column shape its loading direction requires. A plate order is addressed BY WELL, which a flabuild_genbank_submission· Turn a record into the SUBMISSION SET NCBI's `table2asn` consumes: a `.fsa` whose defline carries the source modifiers, and a 5-column feature table (`.tbl`) beside it. This is not a GenBank export — GenBank's submission pipeline takes neitbuild_ena_submission· Turn a record into what ENA's Webin-CLI takes for an annotated sequence (`-context sequence`): an ENA flat file (`.embl`) and its manifest. Features are checked against the tables ENA's own validator reads, so what Webin-CLI would refuse (ascreen_oligo_structure· Fold a set of oligos and check them against each other: every oligo's hairpin, its self-dimer anywhere and its self-dimer at the 3' end, plus the cross-dimer with every other oligo in the set, at any position and at a 3' end. This is primercheck_manufacturability· Measure a sequence against what a NAMED synthesis vendor publishes it can make: length, average and windowed GC, homopolymer runs, tandem repeats, long repeats and hairpin-forming inverted repeats. Every threshold is the vendor's own, readclassify_grammar_part· Which Golden Braid / MoClo / Yeast ToolKit grammar, position and level the open plasmid represents (or null). Reads the record's own annotations, which is what lets an assembled transcription unit be recognised by its backbone half, and whaalign_read· Pairwise-align ONE sequencing read against a reference and hand on the two gapped rows, so the read can be graded. Needleman-Wunsch with free end gaps and the IUPAC substitution matrix — SeqTrace's aligner, the same call the trace editor matrim_reads· Trim sequencing adapters and low-quality ends off FASTQ reads before mapping, and report what was removed. This is cutadapt's algorithm: quality trimming is BWA's running-sum rule (not a threshold - a single bad base in a good tail is absormap_reads· Map sequencing reads (FASTQ or FASTA) or assembled contigs onto a reference and return the alignment as SAM, the file a pileup viewer, a variant caller or `samtools` reads next. This is minimap2 (minimizer seeds, chaining, banded dual-affinverify_read· Grade a sequencing read against a reference (✓ verified / ⚠ near / ~ partial / ✗ divergent) from an alignment.read_sequencing_qc· Read the QC files a sequencing provider returns alongside the reads: a per-base COVERAGE table, or a Plasmidsaurus summary (k-mer composition and the contamination estimate with its named source). These are the numbers that say whether a didomesticate_part· Silently recode the internal Type-IIS sites inside a part's coding sequence so the part can be used in a Golden Gate assembly — same protein, no recognition site. Only occurrences the given CDS covers can be fixed this way; any outside it adesign_fusion_site_primers· Design the PCR primers that ADD Type-IIS fusion sites to a part: enzyme site, spacer and the four-base overhang you chose, on a Tm-matched annealing footprint. This is how a sequence that is not yet a Golden Gate part becomes one, and it isnotebook_cross_refs· Extract @plasmid / !action / &gel cross-references from a lab-notebook markdown body.history_protocol· Render a construct's build history into a numbered bench-recipe protocol.scrub_restriction_sites· Propose the minimal SILENT synonymous edits that remove forbidden restriction sites from a CDS (a design/write).fold_rna· Minimum-free-energy secondary structure (dot-bracket + ΔG) of an RNA/DNA sequence (Turner-2004).pcr_amplify· Amplify the subject template with a forward + reverse primer (pydna Anneal). Emits the first product as a NEW sequence record so downstream tools (digest, gel, map) operate on the amplicon, not the template — the tool→tool hand-off.design_mutagenesis_primers· Design site-directed mutagenesis (SOE-PCR/QuikChange) primers for a point change on a CDS: the ranked inner mutagenic pairs, the constant outer pair, and the single spanning primer that replaces an outer when the site sits too near a CDS endesign_saturation_primers· Design site-saturation mutagenesis (SSM) primers: one overlapping forward/reverse pair per site, each carrying a degenerate codon, sharing ONE reaction-level overlap and 3' temperature so every site amplifies in the same tube (both of Mutatdesign_multisite_primers· Design QCLM (quick-change lightning multi-site) oligos: one primer per mutated site, all annealing in one reaction, with the codons drawn from an organism's usage table. A design/write.reverse_complement· Reverse-complement the subject sequence. Emits a NEW record, so downstream nodes (map, digest, gel, ORF) run on the revcomp rather than the original.translate_sequence· Translate the subject DNA to protein (Biopython `Bio.Seq.translate` semantics). The SUBJECT is the selection when there is one, the named feature when `feature` is given, and the whole record otherwise — the `region` output says which, so nfind_orfs· Find open reading frames on BOTH strands of the subject (origin-spanning when circular).digest_fragments· Digest the subject with the given enzymes into real fragments (sequence + both overhangs). Emits the selected fragment as a NEW record, so a downstream gel/map/ORF runs on that fragment — the digest→assembly hand-off.gc_content· GC fraction of the subject — whole-sequence, or a sliding window profile (DnaChisel).record_composition· What the subject record is MADE OF: molecular weight under its own topology and strand count, GC and AT over the resolved bases, and the per-symbol census with the ambiguity codes broken out. The nucleic-acid counterpart of `protein_propertprotein_properties· Molecular weight (average + monoisotopic), molecular formula, isoelectric point, instability index and amphipathicity (Boman index, Eisenberg hydrophobic moment) of a protein sequence (Biopython ProtParam + `peptides` + `pyteomics`).protein_profile· Windowed physicochemical profile along a protein (ExPASy ProtScale). Pass `scaleId` for any of the 57 scales ProtScale publishes plus the 14 Biopython tables it does not, with optional 0-1 normalisation; or pass `kind` for the five ProtParaprotein_signal_peptide· Signal-peptidase cleavage sites in a protein, by von Heijne's (1986) weight matrix as implemented by EMBOSS sigcleave. Scores a 15-residue window at every position (the 13 residues before the cut plus the first two after) against either theprotein_membrane_profile· Eisenberg hydrophobic-moment plot along a protein: per-window mean hydrophobicity and moment, each classified Globular / Transmembrane / Surface-seeking, plus those windows collapsed into residue spans. A hydrophobicity-based prediction, NOprotein_topology· Transmembrane topology of a protein by the HMM-TM 114-state hidden Markov model (JUCHMME, Bagos et al.), decoded residue by residue into inside / transmembrane-helix / outside runs. Reports the labelled path, the runs as residue spans, andprotein_disorder· Intrinsic disorder along a protein by FoldIndex (Prilusky 2005): I_F = 2.785·⟨H⟩ − |⟨R⟩| − 1.151 over a sliding window, where ⟨H⟩ is mean normalized Kyte-Doolittle hydropathy and ⟨R⟩ the mean net charge per residue. Negative means predictedprotein_disorder_metapredict· Per-residue intrinsic disorder by metapredict (Emenecker, Griffith & Holehouse, Biophys J 2021; V2/V3 the lab's successors), a bidirectional LSTM trained to reproduce a consensus of disorder predictors, run locally. Reports a 0–1 score perprotein_digest· In-silico proteolytic digest of a protein (ExPASy PeptideCutter / PeptideMass): peptides with coordinates, average and monoisotopic masses, m/z per charge state, and the MS mass-window filter. 49 proteases and chemicals — or an enzyme of yopeptide_mass· Monoisotopic and average mass of a peptide, and its m/z at each charge state (validated against pyteomics). Plain one-letter sequences also take an ion type (b, y, c, z, a, x and their neutral-loss forms); a ProForma peptidoform with modififragment_ions· Theoretical MS/MS fragment ion ladder of a peptide: a, b, c from the N-terminus and x, y, z from the C-terminus, with neutral-loss and radical variants, at each charge up to a maximum (validated against pyteomics, cross-checked against Openisotopic_composition· The most probable isotopic composition of a peptide (e.g. how many 13C atoms it most likely carries) and that composition's relative abundance, from natural isotope abundances (validated against pyteomics).isotope_envelope· Coarse isotope pattern of a peptide or of an elemental formula (C29H31N7O, as a compound's formula reads): the relative heights and masses of its M, M+1, M+2 … peaks as an instrument that does not resolve isotopic fine structure sees them,score_spectrum· Score how well an MS/MS spectrum matches a peptide with the X!Tandem HyperScore (validated against OpenMS): b and y ions are generated for the peptide, matched to the observed peaks within a tolerance, and scored as ln(1 + dot product) + lnread_mgf· Read the MS/MS spectra of a Mascot Generic Format (MGF) file: each spectrum's title, precursor m/z, precursor intensity, declared charge states and peak list, interpreted as pyteomics reads MGF (validated on every spectrum of PXD000001). Aread_mzml· Read the spectra of a PSI mzML run file: each spectrum's native id, MS level, centroid or profile, scan start time and unit, base peak, total ion current, precursor (selected ion m/z, charge, intensity, isolation window) and peak arrays, ininfer_proteins· Protein inference from peptide-spectrum matches (validated against OpenMS BasicProteinInferenceAlgorithm on PXD000001): maps each peptide to the protein database, keeps the best match per spectrum, scores each protein by aggregating its pepbayesian_protein_inference· Bayesian protein inference, Epifany (validated against OpenMS BayesianProteinInferenceAlgorithm on PXD000001): the posterior probability that each protein, each indistinguishable group and each peptide-spectrum match is present, from the matarget_decoy_qvalues· False discovery rate and q-values for peptide-spectrum matches by target-decoy competition (validated against pyteomics): give each match's score and whether it hit a decoy; returns every match's q-value, the whole set's FDR, and how many tcrispr_design_guides· Design and score CRISPR guides on the subject — on/off-target scores, QC flags, and cloning-enzyme conflicts. Nuclease list comes from the real nuclease registry.crispr_design_library· Turn the open record's annotated targets into an ORDERABLE sgRNA oligo pool: the best N guides per target, filtered at order time (Pol-III terminator, Graf inactive motif, cloning-enzyme site, minimum on-target score), each composed into thcrispr_analyze_screen· Call HITS from a pooled CRISPR screen: per-guide read counts in, a gene-level Bayes factor and a precision/recall curve out. This is the other end of a screen from the pool designer — it reads what came back rather than deciding what to orddesign_knockout_package· The complete build package for a knockout or knock-in, as one object: guides inside the target, an off-target census for the chosen one within this molecule, a repair template with real homology arms, a screening PCR whose primers sit OUTSIscreen_guides· Screen guide spacers the way CHOPCHOP does before it accepts them: GC gate, self-complementary hairpins inside the spacer, and hairpins against the sgRNA backbone. A guide that folds onto its own scaffold is loaded into Cas9 poorly howeversearch_off_targets· Search a sequence for sites a guide could also cut, allowing mismatches, and score each one (MIT and CFD) plus the aggregate specificity of the guide WITHIN that sequence. This is specificity against what you searched — it is not a genome-wsurvey_off_targets· Count every guide's off-target sites by mismatch class across one sequence, in one pass — the question that comes BEFORE opening any single guide's site table: which of these spacers is worth looking at. Returns counts and the aggregate spefold_guide· Fold a guide RNA — the spacer alone, and the whole sgRNA on a real published scaffold — and report which bases of the spacer pair with the scaffold. A spacer that base-pairs into the scaffold disrupts the structure Cas9 binds, which is a phlist_sgrna_scaffolds· Every sgRNA scaffold this workbench has sourced, with the nucleases each covers and the publication it comes from. A scaffold not listed here is one we do not have — the list is what we ship, not what exists.scan_splice_sites· Find the splice sites a sequence accidentally spells - the check a codon-optimised CDS needs before it goes into a plant or any other eukaryotic host, because a synonymous swap chosen for codon usage or GC can spell a donor or acceptor thatscan_motif_sites· Find every place a transcription-factor binding motif (a position-frequency matrix, such as a JASPAR matrix's counts) matches a DNA sequence, on both strands, at a threshold set per motif as a fraction of that matrix's own score range. It iscan_sigma70_promoters· Find σ70 (housekeeping) promoters in a bacterial sequence and say how strong each one is, using the published La Fleur-Hossain-Salis biophysical model - six interaction motifs (UP element, -35, spacer, extended -10, -10, discriminator) plusscan_intrinsic_terminators· Find rho-independent (intrinsic) transcription terminators in a bacterial sequence: a stem-loop followed by a thymine-rich tail, scored by TransTermHP's published model (Kingsford, Ayanbule & Salzberg 2007). TWO NUMBERS, BOTH LOWER IS STRONscore_rbs· Score the ribosome-binding site already in front of a start codon: the Shine-Dalgarno hybridisation energy, the mRNA folding that competes with it, the spacing it implies, and the resulting relative initiation strength. This reads an existiassemble_operon· Stack several CDSs into one contiguous operon, designing a fresh ribosome-binding site in front of each one AGAINST ITS REAL UPSTREAM CONTEXT — which is why the RBS for gene 2 is not the RBS design_rbs would give it in isolation. Returns thcodon_usage_analysis· Codon-usage analysis of an in-frame CDS: CAI / expression stats, GC, and every rare-codon occurrence for the chosen organism (pydna port), plus the two bias measures that need NO reference table — ENC (Wright 1990) and RCBS (Roymondal 2009)codon_usage_distance· How this region's codon usage compares with the record's OTHER genes (CUFS, Diament, Pinter & Tuller 2014). Every other codon score grades one sequence against a reference TABLE; this one grades two sequences against each other, so it stayscheck_invariants· Decide whether a sequence is scientifically admissible: protein unchanged, forbidden restriction sites absent, reading frame intact, length/GC/CAI inside stated bounds. Every verdict names what broke, where, and the remedy. Run this after adesign_expression_variants· The expression-design deliverable: several coding sequences for one protein, each variant following a different published strategy (maximise codon adaptation, match the host's codon usage, harmonise with the native host, or preserve the inioptimize_sequence· Run the DnaChisel optimizer over the subject with real constraints/objectives (GC window, pattern avoidance, translation enforcement, …). Emits the optimized sequence as a NEW record for downstream nodes.design_rbs· Design a 5'UTR (Shine-Dalgarno + spacer) in front of a CDS to hit a target translation-initiation strength (SC-08 engine, Turner-2004 folding).design_lamp_primers· Design LAMP (loop-mediated isothermal amplification) primer SETS - four core oligos (F3 · B3 · FIP · BIP) plus optional loop primers, judged against Eiken's own PrimerExplorer V5 criteria. Not a pair: LAMP needs six binding regions in the pdesign_codehop· Design CODEHOP hybrid oligos from a block of aligned PROTEIN - for homologues too diverged for nucleotide-level design to see at all. Each primer is a 3' DEGENERATE core over a few conserved residues fused to a 5' non-degenerate consensus cdesign_degenerate_primers· Design degenerate primers from a multiple-sequence ALIGNMENT - the 'amplify every homologue in this family' question, which a single-template designer cannot answer because it only ever sees one sequence. A faithful port of DegePrime (Hugerdesign_bisulfite_primers· Design BSP or MSP primers for a methylation assay, on the CONVERTED strands: after bisulfite treatment every unmethylated C reads as T, which is a different template from the one every other designer sees. BSP primers avoid CpGs so they ampdesign_sequencing_primers· Design a WALK of sequencing primers that reads a whole region, not one pair: tiled reads with confirmed overlap, on both strands by default, plus the coverage the walk actually achieves and any stretch it cannot reach. This is the 'how do Idesign_primers· Design a forward + reverse primer pair to amplify the subject (pydna `primer_design`), with Tm, Ta and suggested Taq/Phusion cycling programs. Emits both primers so a downstream pcr_amplify runs on them — the design→PCR→gel loop.align_sequences· Multiple-sequence alignment over several sequences, under either of TWO engines that answer different questions and neither of which is a fallback for the other. `poa` (partial-order, poapy) aligns into a graph, keeps every path a read tookdraw_alignment· Draw a block of an alignment as an SVG figure: the rows named, the residues shaded by how much of their column agrees with them, the column numbers over the block and Easel's Clustal conservation line under it. Wire `alignedSequences` fromread_structure_consensus· Read the consensus RNA secondary structure a Stockholm alignment states in its `#=GC SS_cons` line (WUSS, the notation Rfam and Infernal write), and measure how well the aligned rows actually support it. Reports the base pairs, what each ungibson_assemble· Assemble fragments by terminal homology (Gibson / NEBuilder / In-Fusion, DnaCauldron). Emits the first product as a NEW record for downstream nodes.design_gibson_primers· Design the PCR primers that CREATE the terminal homology a Gibson/NEBuilder/In-Fusion assembly needs: a Tm-matched pair per fragment, each carrying the 5' overhang that fuses it to its neighbour in the order given (pydna assembly_fragments)golden_gate_assemble· Assemble parts with a Type-IIS enzyme (Golden Gate / MoClo, DnaCauldron). Emits the first construct as a NEW record for downstream nodes.check_golden_gate_parts· Check parts BEFORE a Type-IIS assembly: how many recognition sites each carries, which of them are the two deliberate flanking sites and which are internal sites that will mis-cut the part. This is what answers “why will this assembly not wscore_overhang_fidelity· Score a Golden Gate junction (fusion-site) set against MEASURED T4 DNA ligase end-joining data. It is the number NEB's Ligase Fidelity Viewer reports: the expected fraction of assemblies in which EVERY junction ligated correctly. This is thdesign_split_sites· Decide where to CUT one sequence into Golden Gate fragments, optimising the split positions and the overhangs they create together. Where design_overhang_set proposes junctions for parts you already have, this fragments a sequence you are adesign_overhang_set· Design a high-fidelity Golden Gate overhang set of a given size against measured ligation data, optionally pinning junctions you cannot change (a fixed vector's own overhangs). The counterpart to score_overhang_fidelity: that grades a set yassembly_plan_simulate· Run a MULTI-LEVEL assembly plan (DnaCauldron `AssemblyPlan`): several assemblies arranged into dependency levels, where each level's products become parts for the next. Emits the FINAL construct as a record. The plan is DnaCauldron's own spmelt_profile· DNA melting behaviour of the subject by the Poland–Scheraga model (DECIPHER): the melt curve (mean helicity vs temperature), its Tm50, and the cooperatively-melting domains behind each HRM peak.design_ish_probes· Design an in-situ hybridization probe against the subject: tile it into candidate oligos that meet a melting-temperature, G+C and composition specification, screen them for off-target binding against an alignment, and gather the survivors i
The first 100 are shown.
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Hosted endpoint | https://jeanslabs.vercel.app/mcp | DECLARED | SRC-001 Official MCP Registry | 1h ago |
| Website | https://jeanslabs.vercel.app/docs/api/mcp | DECLARED | SRC-001 Official MCP Registry | 1h ago |
| Version | 1.0.1 | DECLARED | SRC-001 Official MCP Registry | 1h ago |
| Local install (package) | no | DECLARED | SRC-001 Official MCP Registry | 1h ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 1h ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 1h ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 1h ago |
Change history
- VERSION20 Oct 20261.0.0 → 1.0.1
- NEW20 Oct 2026first seen in the index
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is jean — Molecular Biology & Genomics still online?
Free alerts · no accountQuestions about jean — Molecular Biology & Genomics
How do I connect jean — Molecular Biology & Genomics?
Use the hosted endpoint https://jeanslabs.vercel.app/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
What tools does jean — Molecular Biology & Genomics offer?
When Electra Index connected on 20 Oct 2026, it listed 289 tools: list_workflow_templates, validate_workflow, run_workflow, get_open_record, load_record, list_library, find_restriction_sites, find_star_sites and more. The full list is in "Live check" above.
Is jean — Molecular Biology & Genomics online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 2h ago.