Mosaic MCP Tools Reference
Auto-generated from
src/mcp/server.py. Do not edit manually.
44 tools available for pre-clinical drug discovery intelligence.
Quick Reference
| # | Tool | Description |
|---|---|---|
| 1 | mosaic_assess_druggability | Assess structural druggability of a target from AlphaFold + fpocket. |
| 2 | mosaic_clinical_pipeline | Get clinical trial pipeline for compounds targeting a gene. |
| 3 | mosaic_compare_drugs | Side-by-side comparison of two compounds. |
| 4 | mosaic_compare_targets | Side-by-side comparison of 2-5 drug targets. |
| 5 | mosaic_competitive_landscape | Get the full competitive landscape for a drug target. |
| 6 | mosaic_compound_analogs | Get structural analogs of a compound with Tanimoto similarity. |
| 7 | mosaic_compound_polypharmacology | Get the polypharmacology profile of a compound — all targets it interacts with. |
| 8 | mosaic_compound_selectivity | Get the selectivity profile of a compound across all targets. |
| 9 | mosaic_drug_repurposing | Find new indications where a compound's primary targets are implicated. |
| 10 | mosaic_emerging_signals | Targets whose recent literature/patent activity significantly |
| exceeds their own ... | ||
| 11 | mosaic_evidence_map | Get the full evidence landscape for a drug target from semantic extraction. |
| 12 | mosaic_find_opportunities | Find underexplored high-potential drug targets — white-space opportunities. |
| 13 | mosaic_find_similar_targets | Structurally similar targets to a given gene, ranked by Foldseek |
| TM-score over t... | ||
| 14 | mosaic_find_undruggable_targets | Find validated targets that are structurally hard to hit with small molecules. |
| 15 | mosaic_get_target_compounds | Get compounds active against a specific drug target. |
| 16 | mosaic_get_target_papers | Get scientific papers mentioning a specific drug target. |
| 17 | mosaic_get_target_patents | Get patents mentioning a specific drug target. |
| 18 | mosaic_get_target_profile | Get a comprehensive intelligence dossier for a drug target. |
| 19 | mosaic_get_target_structure | Get the AlphaFold structural snapshot for a drug target. |
| 20 | mosaic_indication_landscape | Get the full therapeutic landscape for a disease indication. |
| 21 | mosaic_kg_stats | Get overall statistics for the Mosaic knowledge graph. |
| 22 | mosaic_kol_finder | Rank the top authors (KOLs) publishing on a target or indication. |
| 23 | mosaic_list_indications | List all therapeutic indications available in the knowledge graph. |
| 24 | mosaic_list_subindications | List fine-grained oncology sub-indications in the knowledge graph. |
| 25 | mosaic_modality_gaps | Which compound modalities are explored vs absent for a target. |
| 26 | mosaic_org_portfolio | Get a pharma/biotech organization's full portfolio. |
| 27 | mosaic_pathway_context | Get pathway context for a drug target. |
| 28 | mosaic_regulatory_status | Query openFDA for a drug's approval status, label indications, and adverse event... |
| 29 | mosaic_relation_search | Search the entire knowledge graph for entity pairs with a specific relation type... |
| 30 | mosaic_resistance_bypass_map | Candidate resistance-bypass / escape targets for a given target. |
| 31 | mosaic_search_targets | Search the knowledge graph for drug targets by gene symbol or keyword. |
| 32 | mosaic_subindication_breakdown | Break a target's oncology associations down by sub-indication. |
| 33 | mosaic_synthetic_lethal_whitespace | Find synthetic-lethal whitespace: targets functionally coupled to |
| a developed ... | ||
| 34 | mosaic_talent_migration | Who works on a target, recency-weighted, and what else they |
| work on — a talent... | ||
| 35 | mosaic_target_mechanisms | Get the mechanism-of-action profile for a drug target. |
| 36 | mosaic_target_network | Get the full knowledge graph network around a drug target. |
| 37 | mosaic_target_scores | Get computed attractiveness scores for a drug target. |
| 38 | mosaic_target_validation | Get experimental validation evidence for a drug target. |
| 39 | mosaic_target_wishlist_add | Request a target Mosaic does not yet cover. |
| 40 | mosaic_trial_results | Return real ClinicalTrials.gov records (NCT ID, title, phase, sponsor, status). |
| 41 | mosaic_watchlist_add_item | Add a watched entity (target/indication/organization/compound/ |
| relation_type) to... | ||
| 42 | mosaic_watchlist_create | Create a watchlist to track targets, indications, orgs, or compounds. |
| 43 | mosaic_watchlist_get | Get a watchlist with its items and recent detected events. |
| 44 | mosaic_watchlist_list | List an owner's watchlists with item and recent-event counts. |
mosaic_assess_druggability
Assess Target Druggability (AlphaFold + fpocket)
Read-only query — does not modify data.
Assess structural druggability of a target from AlphaFold + fpocket.
Returns the top binding pockets (volume, druggability score), pocket
count, and a coarse structural_tier (highly_druggable / druggable /
challenging / undruggable) along with a plain-English interpretation.
This is the structural answer to "is this target small-molecule
tractable?" — orthogonal to literature-derived druggability heuristics.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_clinical_pipeline
Clinical Trial Pipeline
Read-only query — does not modify data.
Get clinical trial pipeline for compounds targeting a gene.
Returns compounds in clinical development with indications, trial phases, and status from ClinicalTrials.gov data.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_compare_drugs
Compare Two Drugs Head-to-Head
Read-only query — does not modify data.
Side-by-side comparison of two compounds.
Returns max_phase, first approval year, molecule type, shared targets, unique targets per side, and per-target potency (pChEMBL) for both. Use this for competitive analyses like "osimertinib vs erlotinib" or "imatinib vs dasatinib".
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
drug_a | <class 'str'> | Yes | |
drug_b | <class 'str'> | Yes |
mosaic_compare_targets
Compare Targets Side-by-Side
Read-only query — does not modify data.
Side-by-side comparison of 2-5 drug targets.
Returns compound counts, patent counts, paper counts, best IC50, max clinical phase, attractiveness scores, and momentum for each target.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbols | list[str] | Yes | 2-5 gene symbols to compare (e.g. ['EGFR', 'BRAF', 'ALK']) |
mosaic_competitive_landscape
Competitive Landscape
Read-only query — does not modify data.
Get the full competitive landscape for a drug target.
Multi-hop traversal: Target <- Compounds, Target <- Patents -> Organizations. Shows which pharma/biotech companies are active on this target, how many patents and compounds each has, and overall competitive intensity.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_compound_analogs
Compound Structural Analogs
Read-only query — does not modify data.
Get structural analogs of a compound with Tanimoto similarity.
Returns analogs with similarity scores, shared scaffolds, and their activity against targets. Useful for SAR analysis and lead optimization.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
compound_id | <class 'str'> | Yes | Compound identifier (e.g. 'CHEMBL25') |
limit | <class 'int'> | No (default: 10) | Maximum analogs to return |
mosaic_compound_polypharmacology
Compound Polypharmacology Profile
Read-only query — does not modify data.
Get the polypharmacology profile of a compound — all targets it interacts with.
Shows every target the compound has semantic relations with, the mechanism of action for each (inhibits, agonizes, degrades, etc.), and evidence counts. Useful for understanding off-target effects, repurposing potential, and selectivity from a semantic (not just activity) perspective.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
compound_name | <class 'str'> | Yes | Compound name (e.g. 'imatinib', 'osimertinib', 'pembrolizumab') |
mosaic_compound_selectivity
Compound Selectivity Profile
Read-only query — does not modify data.
Get the selectivity profile of a compound across all targets.
Shows activity values against every target the compound has been tested on. Critical for assessing off-target effects and safety liability.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
compound_id | <class 'str'> | Yes | Compound identifier — ChEMBL ID (e.g. 'CHEMBL25') or internal ID |
mosaic_drug_repurposing
Drug Repurposing Candidates
Read-only query — does not modify data.
Find new indications where a compound's primary targets are implicated.
Returns indications where the compound's targets have supporting evidence but the compound itself is not yet clinically active. Ranked by a simple target-support × avg-evidence score. Useful as a starting point for repurposing hypotheses — not a substitute for clinical review.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
compound_name | <class 'str'> | Yes | |
limit | <class 'int'> | No (default: 15) |
mosaic_emerging_signals
Emerging Activity Signals
Read-only query — does not modify data.
Targets whose recent literature/patent activity significantly exceeds their own prior baseline (z-score > 2).
Simple statistics over monthly counts — no ML. Use to spot targets
heating up before they crowd. sparkline is recent monthly counts.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
window_months | <class 'int'> | No (default: 6) | Recent window length in months |
signal_type | <class 'str'> | No (default: 'paper_surge') | paper_surge or patent_surge |
limit | <class 'int'> | No (default: 20) | Max signals |
mosaic_evidence_map
Target Evidence Map
Read-only query — does not modify data.
Get the full evidence landscape for a drug target from semantic extraction.
Shows all relation types (validation, resistance, biomarker, safety, efficacy, expression, pathway, drug target ID) broken down by source type (paper vs patent), with confidence stats and top evidence snippets per relation type.
Use this to understand the strength and breadth of evidence for a target.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_find_opportunities
Find White-Space Opportunities
Read-only query — does not modify data.
Find underexplored high-potential drug targets — white-space opportunities.
Identifies targets with high scientific validation but low competitive intensity. These are the best opportunities for novel drug programs where the biology is strong but Big Pharma hasn't crowded the space.
Ranked by opportunity_score = validation × (1 - competition) × momentum_boost.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
therapy_area | `str | None` | No (default: None) |
limit | <class 'int'> | No (default: 20) | Max results |
mosaic_find_similar_targets
Find Similar Targets (structural)
Read-only query — does not modify data.
Structurally similar targets to a given gene, ranked by Foldseek TM-score over the AlphaFold PDB corpus.
Returns the top-k neighbours (default 10) with neighbour metadata (name, target_class, druggability_tier) and the structural-similarity metrics (tm_score normalised over query length, alntmscore over alignment length, evalue, lddt, rmsd). Use for paralog / fold-analog discovery, scaffold-hopping target ideation, and cross-family chemistry repurposing.
Source table is populated by scripts/build_foldseek_index.py. When
the index hasn't been built yet, returns an empty result with a
populate-hint rather than failing — degrades cleanly on fresh DBs.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene | <class 'str'> | Yes | Target gene symbol or UniProt id (e.g. 'EGFR') |
k | <class 'int'> | No (default: 10) | Max number of structurally similar neighbours to return |
mosaic_find_undruggable_targets
Find Structurally Intractable Targets
Read-only query — does not modify data.
Find validated targets that are structurally hard to hit with small molecules.
Returns targets in the 'challenging' or 'undruggable' tier (or with a top fpocket druggability score below the threshold), plus their pipeline gap signals (compound count, approved drug count, validation count) and a suggested modality (PROTAC / glue, biologic / PPI, fragment-based, or allosteric SBDD). This is the white-space tool for new-modality programs.
Ranked by opportunity_score = validation × (1 - top_pocket_score) × (1 - competitive_intensity).
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
therapy_area | `str | None` | No (default: None) |
max_pocket_score | <class 'float'> | No (default: 0.4) | Targets with top fpocket druggability score below this are eligible |
min_disorder_frac | <class 'float'> | No (default: 0.0) | If > 0, also include targets with this fraction of pLDDT<50 (disordered) residues, regardless of pocket score |
require_validation | <class 'bool'> | No (default: True) | Require validation evidence (paper_validations or scientific_validation >= 0.3) |
limit | <class 'int'> | No (default: 25) | Max targets to return |
mosaic_get_target_compounds
Get Target Compounds
Read-only query — does not modify data.
Get compounds active against a specific drug target.
Returns compounds with activity data (IC50, Ki, etc.) sorted by potency.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF') |
limit | <class 'int'> | No (default: 20) | Maximum number of results to return |
mosaic_get_target_papers
Get Target Papers
Read-only query — does not modify data.
Get scientific papers mentioning a specific drug target.
Returns publications from PubMed/OpenAlex with titles and dates.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF') |
limit | <class 'int'> | No (default: 20) | Maximum number of results to return |
mosaic_get_target_patents
Get Target Patents
Read-only query — does not modify data.
Get patents mentioning a specific drug target.
Returns patent filings with titles, dates, and assignee organizations.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF') |
limit | <class 'int'> | No (default: 20) | Maximum number of results to return |
mosaic_get_target_profile
Get Target Profile
Read-only query — does not modify data.
Get a comprehensive intelligence dossier for a drug target.
Returns UniProt biology, target scores, SAR summary, disease associations, validation evidence, pathways, PPIs, competitive landscape, clinical pipeline, and publication momentum. This is the primary tool for any target question.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_get_target_structure
Get Target Structure (AlphaFold)
Read-only query — does not modify data.
Get the AlphaFold structural snapshot for a drug target.
Returns AlphaFold model URLs (PDB / CIF / PAE), per-residue confidence
summary (mean pLDDT, fractions of residues at high / confident / low
confidence, disordered fraction), and protein length. Useful for
SBDD scoping, disorder/IDR risk, and confidence-aware target triage.
Pair with mosaic_assess_druggability for binding-pocket scoring.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_indication_landscape
Indication Landscape
Read-only query — does not modify data.
Get the full therapeutic landscape for a disease indication.
Shows all targets implicated in this indication, compounds in development, and clinical status.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
indication_name | <class 'str'> | Yes | Indication/disease name (e.g. 'oncology', 'breast_cancer') |
mosaic_kg_stats
Knowledge Graph Statistics
Read-only query — does not modify data.
Get overall statistics for the Mosaic knowledge graph.
Returns entity counts (targets, compounds, papers, patents), semantic relation totals and breakdown by type, coverage metrics, and ChEMBL activity counts. Use this to understand the scope and coverage of the KG.
No parameters required.
mosaic_kol_finder
Key Opinion Leader (KOL) Finder
Read-only query — does not modify data.
Rank the top authors (KOLs) publishing on a target or indication.
Scores by paper volume with recency weighting (papers since 2023 count 2x). Returns person name, paper count, most recent publication date, and affiliated organizations. Useful for advisory board assembly, trial PI scouting, and competitive intelligence.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | `str | None` | No (default: None) |
indication_name | `str | None` | No (default: None) |
limit | <class 'int'> | No (default: 15) |
mosaic_list_indications
List Indications
Read-only query — does not modify data.
List all therapeutic indications available in the knowledge graph.
Returns every indication with the number of associated targets. Use this to discover which disease areas are loaded.
No parameters required.
mosaic_list_subindications
List Sub-Indications
Read-only query — does not modify data.
List fine-grained oncology sub-indications in the knowledge graph.
Sub-indications are histology- or biomarker-defined cancer subtypes
(e.g. 'EGFR-mutant NSCLC', 'triple-negative breast cancer') organized
under broader parent indications. Optionally pass parent_indication
(id, name, or synonym, e.g. 'lung cancer' or 'NSCLC') to list only its
children. Each entry includes the number of linked targets.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
parent_indication | `str | None` | No (default: None) |
mosaic_modality_gaps
Modality Gaps
Read-only query — does not modify data.
Which compound modalities are explored vs absent for a target.
Modality is a heuristic SMILES classification (small_molecule,
covalent, degrader, macrocycle, peptide_like) over the top-ranked
compounds — partial coverage by design; unclassified is reported
explicitly. Target-level only: protein_family is not populated, so
family-level rollups are unavailable (stated, not silently wrong).
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
target_or_family | <class 'str'> | Yes | Target gene symbol (e.g. 'BRD4'). Family-level is not available — protein_family data is unpopulated. |
mosaic_org_portfolio
Organization Portfolio
Read-only query — does not modify data.
Get a pharma/biotech organization's full portfolio.
Shows which drug targets they're active on, their patent filings, therapy area focus, and competitive positioning. Use to understand what a company is working on and where they're investing.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
org_name | <class 'str'> | Yes | Organization name or partial name (e.g. 'Pfizer', 'Novartis', 'Roche') |
mosaic_pathway_context
Pathway Context
Read-only query — does not modify data.
Get pathway context for a drug target.
Shows which biological pathways the target participates in, other targets in the same pathways, and protein-protein interactions.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_regulatory_status
FDA Regulatory Status (openFDA)
Read-only query — does not modify data.
Query openFDA for a drug's approval status, label indications, and adverse events.
Returns: FDA approval dates, brand/generic names, sponsor, product type, route of administration, and a summary count of serious adverse events. Data is live from openFDA — does not require local ingestion.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
drug_name | <class 'str'> | Yes | Brand or generic drug name (e.g. 'imatinib') |
mosaic_relation_search
Search by Semantic Relation Type
Read-only query — does not modify data.
Search the entire knowledge graph for entity pairs with a specific relation type.
Returns the highest-confidence entity pairs for a given relation (e.g. all 'degrades_protac' relations, or all 'resistance_mechanism' edges). Useful for cross-target analysis like "which targets have PROTAC degraders?" or "where are resistance mechanisms documented?"
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
relation_type | <class 'str'> | Yes | Semantic relation type. Options: validates_therapeutic_target, resistance_mechanism, biomarker, safety_concern, clinical_efficacy, expression_change, pathway_involvement, drug_target_identification, inhibits, inhibits_covalent, inhibits_allosteric, inhibits_competitive, agonizes, antagonizes, degrades_protac, modulates_allosteric, partial_agonist |
min_confidence | <class 'float'> | No (default: 0.1) | Minimum confidence threshold (0.0-1.0) |
limit | <class 'int'> | No (default: 30) | Maximum results to return |
mosaic_resistance_bypass_map
Resistance Bypass Map
Read-only query — does not modify data.
Candidate resistance-bypass / escape targets for a given target.
From a deterministic keyword pass over the literature (resistance_relations — GLiREL has no resistance edge type), surfaces targets co-mentioned with the query target in resistance-context abstracts, ranked by a drugability-gap score (strong resistance evidence, low development activity). Hypothesis generator, not evidence — every row carries its source snippet.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
target | <class 'str'> | Yes | Target whose therapies face resistance (e.g. 'EGFR') |
indication | `str | None` | No (default: None) |
mosaic_search_targets
Search Drug Targets
Read-only query — does not modify data.
Search the knowledge graph for drug targets by gene symbol or keyword.
Returns matching targets with basic metadata. Optionally filter by therapeutic indication. Use this as the starting point to explore targets.
Returns: JSON list of matching targets with gene_symbol, name, target_class, and counts of related compounds, patents, and papers.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
query | <class 'str'> | Yes | Gene symbol or keyword to search (e.g. 'EGFR', 'kinase') |
indication | `str | None` | No (default: None) |
mosaic_subindication_breakdown
Target Sub-Indication Breakdown
Read-only query — does not modify data.
Break a target's oncology associations down by sub-indication.
For the given gene, returns the most relevant cancer sub-indications (e.g. EGFR -> NSCLC subtypes vs. colorectal) with the evidence type and confidence of each link. Complements mosaic_get_target_profile with finer indication granularity.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_synthetic_lethal_whitespace
Synthetic-Lethal Whitespace
Read-only query — does not modify data.
Find synthetic-lethal whitespace: targets functionally coupled to a developed (drugged) target but themselves undeveloped.
For an anchor target with chemical matter, surfaces partners that share STRING protein-protein interactions and/or Reactome pathways with it yet have < 5 patents and no clinical compound — i.e. strong biological coupling, low competitive activity. Ranked by a whitespace score and returned with a deterministic suggested experimental approach.
Scope: co_functionality_proxy is a PPI + shared-pathway proxy for
co-essentiality, NOT DepMap co-essentiality (DepMap ingestion is a
later sprint). Treat it as a hypothesis generator, not evidence.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
approved_target | `str | None` | No (default: None) |
lineage | `str | None` | No (default: None) |
limit | <class 'int'> | No (default: 20) | Max pairs |
mosaic_talent_migration
Researcher / Talent Migration
Read-only query — does not modify data.
Who works on a target, recency-weighted, and what else they work on — a talent-flow signal.
Surfaces the most active researchers on a target (publication-based, using the resolved persons table) and, for each, the other targets they've published on over time — i.e. "people who worked on X now also on Y". Patent inventors are not included (not ingested).
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
target | <class 'str'> | Yes | Target gene symbol (e.g. 'EGFR') |
lookback_years | <class 'int'> | No (default: 5) | Years of history to weight |
mosaic_target_mechanisms
Target Mechanism of Action Profile
Read-only query — does not modify data.
Get the mechanism-of-action profile for a drug target.
Returns how compounds interact with this target — inhibitors (covalent, allosteric, competitive), agonists, antagonists, degraders (PROTAC). Also shows semantic edge types: validation evidence, resistance mechanisms, biomarker roles, safety concerns, and clinical efficacy signals.
Extracted by GLiREL from paper and patent abstracts.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_target_network
Target Knowledge Graph Network
Read-only query — does not modify data.
Get the full knowledge graph network around a drug target.
Returns all connected entities (compounds, diseases, pathways, organizations, interacting proteins) as nodes and edges. Shows how a target connects to the broader drug discovery landscape.
Useful for understanding the full context of a target and finding non-obvious connections.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_target_scores
Target Attractiveness Scores
Read-only query — does not modify data.
Get computed attractiveness scores for a drug target.
Returns overall target attractiveness, scientific validation, druggability, competitive intensity, and research momentum (0-1 scale) with direction.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_target_validation
Target Validation Evidence
Read-only query — does not modify data.
Get experimental validation evidence for a drug target.
Returns genetic (CRISPR/siRNA), in vivo (animal models), clinical (patient data), and pharmacological validation evidence from literature. Includes specific papers with model systems and outcomes.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol of the target (e.g. 'EGFR', 'BRAF', 'TP53') |
mosaic_target_wishlist_add
Request Out-of-Scope Target
Request a target Mosaic does not yet cover.
Use this when a gene is outside the current covered set so the operator can prioritise it in the next ingestion batch. Idempotent: re-requesting the same gene/email bumps a counter. Also returns the closest covered targets so the user still gets a useful answer.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | <class 'str'> | Yes | Gene symbol to request (e.g. 'GPR55') |
user_email | <class 'str'> | No (default: 'anonymous') | Optional requester email so they can be notified |
notes | `str | None` | No (default: None) |
mosaic_trial_results
Clinical Trial Results (ClinicalTrials.gov)
Read-only query — does not modify data.
Return real ClinicalTrials.gov records (NCT ID, title, phase, sponsor, status).
Filters by any combination of gene symbol, compound name, or indication.
Unlike mosaic_clinical_pipeline which can synthesize from max_phase, every
row returned here has a real NCT ID and brief title. Use this when you need
to cite specific trials or highlight read-outs.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
gene_symbol | `str | None` | No (default: None) |
compound_name | `str | None` | No (default: None) |
indication_name | `str | None` | No (default: None) |
has_results_only | <class 'bool'> | No (default: False) | Only return trials with posted results |
limit | <class 'int'> | No (default: 25) |
mosaic_watchlist_add_item
Add Watchlist Item
Add a watched entity (target/indication/organization/compound/ relation_type) to a watchlist. Idempotent — re-adding is a no-op.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
watchlist_id | <class 'str'> | Yes | Watchlist UUID |
item_type | <class 'str'> | Yes | One of: target, indication, organization, compound, relation_type |
item_value | <class 'str'> | Yes | The entity value, e.g. 'EGFR' or 'non_small_cell_lung_carcinoma' |
mosaic_watchlist_create
Create Watchlist
Create a watchlist to track targets, indications, orgs, or compounds.
owner_key is the user id, email, or an 'anon:<token>' for anonymous sessions. Returns the new watchlist id to use with mosaic_watchlist_add_item.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
owner_key | <class 'str'> | Yes | Owner identifier: user id, email, or 'anon:<token>' |
name | <class 'str'> | No (default: 'My watchlist') | Watchlist name |
mosaic_watchlist_get
Get Watchlist
Read-only query — does not modify data.
Get a watchlist with its items and recent detected events.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
watchlist_id | <class 'str'> | Yes | Watchlist UUID |
mosaic_watchlist_list
List Watchlists
Read-only query — does not modify data.
List an owner's watchlists with item and recent-event counts.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
owner_key | <class 'str'> | Yes | Owner identifier: user id, email, or 'anon:<token>' |
Confidence Thresholds
Semantic relation results include confidence badges:
| Badge | Confidence | Meaning |
|---|---|---|
high | >= 0.3 | Strong model confidence, likely correct |
moderate | 0.1 - 0.3 | Plausible but verify independently |
low | < 0.1 | Not displayed by default |
Generated by scripts/generate_mcp_docs.py