Tools and processors reference

This page is the single entry point for everything Lucenia can do to your data: the tools an agent can call, the ingest processors that run while documents are written, and the search processors that run while queries are served.

note

The word tool means two different things in these docs. The Ingestion tools and utilities section covers third-party data shippers (Beats, Logstash, Fluentd, OpenTelemetry), the Lucenia CLI, and migration tooling — programs that run outside the cluster. This page covers the tools and processors that ship inside the cluster.

Ask the cluster, not the docs

A running cluster is always the authoritative inventory for the version you are on. Three requests cover the whole surface:

Surface	Request	Notes
Agent tools	GET /_plugins/_agent/tools	Returns name, type, description, and version for every registered tool type.
Ingest processors	GET /_nodes/ingest?filter_path=nodes.*.ingest.processors	Complete. Includes processors contributed by every installed module.
Search processors	GET /_nodes/search_pipelines	Incomplete — see the warning below.

warning

GET /_nodes/search_pipelines reports only request_processors and response_processors. It omits search phase results processors, which is where normalization-processor lives — the processor that makes hybrid search work. Do not treat its output as the full search processor list. The complete list is in Search processors.

Agent tools

A tool is a reusable building block an agent calls to perform one specific task — search an index, run a deployed model, call an external service. You reference a tool by its type when registering an agent. For parameters, examples, and per-tool detail, see Tools.

Tool type	What it does
AgentTool	Runs another agent by its agent ID.
CatIndexTool	Retrieves index health, status, document counts, and store sizes.
ChangeDetectionTool	Compares two time windows over indexed regions.
CheckAnalysisTool	Checks analysis code an agent authored against an allowlist before anything runs it, and states how much of it was examined. Executes nothing.
ComplianceTool	Reports kinds, counts, and offsets of sensitive matches in text.
ConceptSearchTool	Finds every document about a subject by expanding a concept through the vocabulary, and states its linked coverage.
ConnectorTool	Invokes an external service through a configured connector.
ContourTool	Finds where documents are concentrated, returning nested regions of density rather than a single bounding box.
DisseminationTool	Checks whether a scene may go to a named recipient.
GeoLayerTool	Finds where matching features are, with count, extent, a GeoJSON sample, and a tile URL.
GeoLineTool	Traces the path each moving thing travelled, stating per path whether it is complete or was shortened.
ImageRegionsTool	Reads a raster and returns labelled polygons as the tool answer.
IndexMappingTool	Retrieves mappings and settings for one or more indexes.
ListIndexTool	Lists the indexes in the cluster with health, status, and document counts.
McpSseTool	Invokes a tool hosted on a remote Model Context Protocol (MCP) server. See Using MCP tools.
MLModelTool	Runs any deployed machine learning model by its model ID.
QueryPlanningTool	Turns a natural-language question into a query DSL query using an LLM.
RAGTool	Runs a k-NN retrieval, then asks a generation model to answer from the retrieved context.
ReadFromScratchPadTool	Reads back notes an agent saved to its per-conversation scratchpad.
ReportTool	Assembles findings into a printable report.
ReprojectImageryTool	Fetches imagery a search pipeline has already reprojected.
RouteTool	Finds a path between two nodes on an indexed network.
SearchIndexTool	Searches an index using a query DSL query.
SimilarImageryTool	Finds imagery that looks like a given image.
TemporalCoverageTool	Reports when a place was imaged and where the coverage gaps are.
VectorDBTool	Embeds query text and runs a k-NN search, returning matching documents as context.
VisualizationTool	Finds saved visualizations by matching a search term against their titles.
WriteToScratchPadTool	Saves a short note to an agent's per-conversation scratchpad for later recall.

note

Two names in the shipped modules/agent JAR do not match the type you write in a request:

• The class VisualizationsTool registers the type VisualizationTool (no s). Use the type.
• McpSseTool is registered as a type but is constructed by the cluster when an MCP connector discovers a remote tool. It is bound to an MCP client at that point, so it is not listed by the MCP built-in tool registry when unbound.

Ingest processors

Ingest processors transform documents on the write path, inside an ingest pipeline. The complete table, with a link to each processor's own page, is in Ingest processors.

The processors below are specific to Lucenia and often decide whether the product fits a use case, so they are called out here:

Processor	What it does
chunk	Splits text into overlapping chunks using recursive, fixed, semantic, or topic-shift algorithms.
content_extract	Extracts structured content blocks from PDF, DOCX, HTML, and image sources.
embed	Generates text, image, or multimodal embeddings using Bedrock, OpenAI, or HTTP providers.
image_segment	Runs semantic image segmentation and indexes each region as a spatial shape.
image_tiling	Splits large images (including GeoTIFF/COG) into fixed-size tiles for multimodal vector search.
ml_inference	Calls a registered machine learning model during ingest and writes its output onto the document.
ocr	Performs optical character recognition on image blocks using LLM vision models or the HTTP inference provider.
rerank_prepare	Annotates chunks with document-level metadata and position scores for search-time reranking.
topic_drift	Scores how far an extraction has drifted from a mission goal and flags off-mission output.
vectorize	Turns a categorical raster into indexable geometry without a model or GPU.

Search processors

Search processors transform requests, responses, and intermediate phase results on the read path, inside a search pipeline. The complete tables are in Search processors.

They run in three places:

• Request processors rewrite the query before it is executed — for example query_embedding, which embeds query text at search time so clients do not have to.
• Response processors transform the hits that come back — for example multimodal_rerank and retrieval_grounding.
• Phase results processors run between search phases on the coordinating node. This is where normalization-processor lives, and it is the category GET /_nodes/search_pipelines does not report.

Related pages

• Agent — agents, tools, and MCP.
• Ingest pipelines — building and running write-path pipelines.
• Search pipelines — building and running read-path pipelines.
• Ingestion tools and utilities — Beats, Logstash, the Lucenia CLI, and migration tooling.
• Nodes Info API — the API behind GET /_nodes/ingest.