MCP Tools

RushDB MCP exposes 37 tools. Names below use the exact lower camel case identifiers published in the MCP manifest.

The connected MCP client receives the full JSON schema for each tool. This page is the quick reference for choosing the correct tool and understanding its main inputs.

Safety Levels

Level	Meaning
Read	Retrieves or computes data without changing the project
Write	Creates or updates project data
Destructive	Deletes or replaces data; preview and confirm first

An asterisk marks a required input.

Discovery and Properties

Tool	Level	Main inputs	Purpose
getOntologyMarkdown	Read	labels?, force?	Return the complete graph ontology as compact Markdown. Call once at session start.
getOntology	Read	labels?, force?	Return structured ontology JSON, including property IDs and vector indexes.
findLabels	Read	where?, limit?, skip?, orderBy?	List or filter record labels and counts.
findProperties	Read	where?, limit?, skip?, orderBy?	Discover property names, types, IDs, and record counts.
findPropertyById	Read	propertyId*	Fetch metadata for one property.
propertyValues	Read	propertyId*, query?, orderBy?, limit?, skip?	Return numeric or date ranges, or distinct string and boolean values.
deleteProperty	Destructive	propertyId*	Permanently remove a property and its values from all records.
getSearchQuerySpec	Read	none	Return the complete SearchQuery syntax reference.
getQueryBuilderPrompt	Read	none	Return the built-in discovery-first query builder prompt.

Records

Tool	Level	Main inputs	Purpose
findRecords	Read	labels?, where?, limit?, skip?, orderBy?, select?, groupBy?	Search records and run grouped metrics queries.
findOneRecord	Read	labels?, where?	Return the first matching record for entity resolution probes.
findUniqRecord	Read	labels?, where?	Return exactly one matching record; fail when zero or multiple records match.
getRecord	Read	recordId*	Fetch one record by ID.
getRecordsByIds	Read	recordIds*	Fetch multiple records by ID.
createRecord	Write	label*, data*, options?, transactionId?	Insert or upsert one record.
updateRecord	Write	recordId*, label*, data*, transactionId?	Partially update one record while preserving unspecified fields.
setRecord	Destructive	recordId*, label*, data*, transactionId?	Replace all fields on one record.
deleteRecord	Destructive	recordId*, transactionId?	Delete one record by ID after previewing it with findRecords.
deleteRecordById	Destructive	recordId*, transactionId?	Delete one record by ID after previewing it with getRecord.
bulkCreateRecords	Write	label*, data*, options?, transactionId?	Insert or upsert multiple records with the same label.
bulkDeleteRecords	Destructive	where*, labels?, transactionId?	Delete all records matching a query. Preview with findRecords first.
exportRecords	Read	labels?, where?, limit?, orderBy?	Export matching records as CSV.

Relationships

Tool	Level	Main inputs	Purpose
findRelationships	Read	where?, limit?, skip?, orderBy?	Inspect edges and discover graph paths before traversal queries.
attachRelation	Write	sourceId*, targetId?, targetIds?, relationType?, direction?, transactionId?	Create relationships between existing records.
detachRelation	Destructive	sourceId*, targetId?, targetIds?, relationType?, direction?, transactionId?	Remove relationships between records.

Suggested Relationship Patterns

Tool	Level	Main inputs	Purpose
listRelationshipPatterns	Read	none	List inferred patterns, ontology relationship summaries, and analysis status.
analyzeRelationshipPatterns	Write	none	Queue ontology analysis. This may invoke the configured LLM.
approveRelationshipPattern	Write	id*	Approve and apply a suggested pattern.
ignoreRelationshipPattern	Write	id*	Ignore a suggested pattern without applying it.
deleteRelationshipPattern	Destructive	id*, deleteExisting?	Delete a stored pattern and optionally its materialized relationships.

See Suggested Relationship Patterns for lifecycle details and REST and SDK examples.

Semantic Search

Tool	Level	Main inputs	Purpose
findEmbeddingIndexes	Read	none	List embedding index policies configured for the project.
createEmbeddingIndex	Write	label*, propertyName*, sourceType?, similarityFunction?, dimensions?	Create a managed or external embedding index policy.
getEmbeddingIndexStats	Read	indexId*	Check indexing progress for an embedding index.
upsertEmbeddingVectors	Write	indexId*, items*	Write pre-computed vectors to an external index.
deleteEmbeddingIndex	Destructive	indexId*	Delete an embedding index and its stored vectors.
semanticSearch	Read	propertyName*, labels*, query?, queryVector?, sourceType?, similarityFunction?, where?, topK?, limit?, skip?	Rank records by vector similarity, optionally after exact filtering.

Utilities

Tool	Level	Main inputs	Purpose
helpAddToClient	Read	none	Return instructions for adding RushDB MCP to a client.

Query Rules

• Never guess labels or property names. Start with getOntologyMarkdown.
• Call getSearchQuerySpec before complex findRecords queries.
• Do not pass limit with select; it restricts the record scan and produces incorrect metrics.
• For a simple count, read total from findRecords.
• Preview and explicitly confirm destructive operations.