plant-genomics-mcp

Overview Schema Source Related Servers Discussions Admin

ThaleMine: Experimental Interactions

experimental_interactions

Read-onlyIdempotent

Retrieve curated experimental protein and genetic interactions for an Arabidopsis locus, with detection methods, source databases, and PubMed evidence from ThaleMine.

Instructions

Fetch CURATED EXPERIMENTAL protein/genetic interaction partners for an Arabidopsis locus from ThaleMine (BAR's InterMine instance; free, no key), sourced from BioGRID, IntAct and PSI-MI. Unlike string_interactions (predicted / text-mined, scored) and bar_aiv_interactions (which returns GRN paper references for Arabidopsis, not partner pairs), every partner here carries the actual experimental provenance: detection method (two hybrid, pull down, genetic interference, ...), PSI-MI relationship type, physical vs genetic class, source database, and the PubMed IDs that reported it. ThaleMine emits one row per evidence record, so rows are aggregated to one entry per partner with evidence_count as a crude support signal; partners are ordered by that count. found=false means the gene is real but has no curated interaction on record — a normal outcome; an unknown locus raises a typed NotFoundError. Arabidopsis only (ThaleMine carries genes for taxon 3702; other organisms raise OrganismNotSupported).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`locus`	Yes	AGI locus, e.g. AT5G11260 (HY5)
`organism`	No	Plant organism — accepts canonical slug (arabidopsis_thaliana), scientific or common name, or NCBI taxid. ThaleMine supports Arabidopsis only.	arabidopsis_thaliana

Output Schema

TableJSON Schema

Name	Required	Description
`found`	Yes	True if any curated interaction exists for this locus
`locus`	Yes
`total`	Yes	How many interaction partners exist upstream for this query, all pages (pre-cap) (#123)
`organism`	Yes	Canonical organism slug (Arabidopsis only)
`partners`	No	Partners ordered by evidence count, descending
`returned`	Yes	Rows in this payload (#123)
`truncated`	Yes	True if the partner list was capped
`source_url`	Yes	ThaleMine gene report page — a link for the client to open or fetch; no tool on this server dereferences it
`gene_symbol`	No	Gene symbol from ThaleMine
`partner_count`	Yes	Total distinct partners (pre-cap)
`evidence_count`	Yes	Total evidence records across all partners (pre-cap) — counted over every partner upstream, not only the partners listed here

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.22.0Sep 24, 2026

addedOutput schema / properties / returned

Added value: +{
+  "description": "Rows in this payload (#123)",
+  "title": "Returned",
+  "type": "integer"
+}

changedOutput schema / properties / source_url / description

Previous value: -"ThaleMine gene report page"New value: +"ThaleMine gene report page — a link for the client to open or fetch; no tool on this server dereferences it"

addedOutput schema / properties / total

Added value: +{
+  "description": "How many interaction partners exist upstream for this query, all pages (pre-cap) (#123)",
+  "title": "Total",
+  "type": "integer"
+}

changedOutput schema / required

Previous value: -[
-  "locus",
-  "organism",
-  "found",
-  "partner_count",
-  "evidence_count",
-  "truncated",
-  "source_url"
-]New value: +[
+  "total",
+  "returned",
+  "locus",
+  "organism",
+  "found",
+  "partner_count",
+  "evidence_count",
+  "truncated",
+  "source_url"
+]

Changed1 schema field changedv1.19.4Jul 28, 2026

changedOutput schema / properties / evidence_count / description

Previous value: -"Total evidence records across all partners"New value: +"Total evidence records across all partners (pre-cap) — counted over every partner upstream, not only the partners listed here"

Addedv1.18.2Jul 24, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds substantial behavioral context: one row per evidence record is aggregated to one row per partner, partners are ordered by evidence_count, found=false semantics, NotFoundError for unknown loci, and OrganismNotSupported for non-Arabidopsis organisms. No contradiction with annotations exists.

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?

Although long, the description is dense and each sentence earns its place: source, data provenance, sibling distinctions, aggregation behavior, ordering, found=false semantics, error behavior, and organism restriction. It is front-loaded with the core purpose and then adds necessary caveats in a logical order.

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?

Given the tool's moderate complexity and the existing annotations/output schema, the description covers all necessary operational context: data sources, result granularity, support signal, ordering, normal vs error outcomes, and organism limitations. An agent has enough information to call it correctly and interpret its results.

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 adds value beyond the schema by giving an example locus (AT5G11260), clarifying that organism accepts slug/name/taxid but ThaleMine only supports Arabidopsis, and explaining how the locus parameter maps to the returned evidence. This goes beyond the structured schema.

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?

The description uses a specific verb ('Fetch') with a precise resource: curated experimental protein/genetic interaction partners for an Arabidopsis locus. It explicitly differentiates itself from string_interactions (predicted/text-mined) and bar_aiv_interactions (GRN paper references), so an agent can distinguish it without inspecting the 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?

The description explicitly names alternatives and states when they are not appropriate, contrasting with string_interactions and bar_aiv_interactions. It also gives clear selection constraints: Arabidopsis only, other organisms raise OrganismNotSupported, and found=false is a normal outcome rather than an error.

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

Deploy Server