Elodus

Create a new document in a workspace (write). The 'kind' MUST be one of THIS workspace's document_kinds — call list_object_types first and use a kind from its `document_kinds` list; do not assume generic kinds like 'blueprint'. To build a SLIDE DECK / presentation, pass kind='presentation' (a universal utility kind always accepted, even if it's not in the ontology): the document's sections become the slides — add each with append_section. PREFER REFERENCE SLIDES: to put existing workspace content on a slide, set the section body to a SINGLE reference token — '@present:document:42', '@present:section:99', '@present:widget:<slug>', '@present:bpmn:<slug>' — so the slide shows the LIVE object and stays in sync. If the slide's content does NOT exist yet, FIRST create a document for it (create_document) and link THAT — don't write a free-text slide. Do NOT retype an existing document/section's content into a text slide (it duplicates and goes stale). Use a plain markdown body only for title / intro / divider slides that have no underlying object. SLIDE SIZING: each slide is one full 16:9 screen shown from a distance, NOT a scrolling page — the presenter does not shrink to fit. Budget each slide to about a short heading plus ~6 bullet lines (~40 words), ~10 lines / ~90 words absolute max; split dense content across MORE slides rather than overflowing one. Prefer short bullets over paragraphs; one idea per slide.

create_document

Create an instance of an ontology object type. `attributes` are validated against the type's schema. For document types pass optional doc_kind; for record types optional entity_kind.

create_object

Create a new SDLC phase in a workspace.

create_phase

Save a named search so the team (and you) can re-run it. Stores CRITERIA, never results. Draft one when the researcher lands on a query worth keeping, then tell them you saved it. Defaults to 'available' — do NOT pin unless the researcher explicitly asks, because pinning makes it standing context in every future conversation. Criteria must match the source's schema (see the source's own search tool for the allowed keys).

create_saved_search

Create a Widget — a small self-contained interactive frontend mini-app (e.g. a mortgage calculator) to illustrate an interface/interaction. Seed any data with widget_store_set.

create_widget

Queue a new workorder in a workspace (write, requires per-user key).

create_workorder

Resolve a DOI to a ready-to-paste BibTeX entry (or a formatted citation). Feed the content straight into an Overleaf .bib via overleaf_write_file.

crossref_get_bibtex

Resolve a single DOI to canonical Crossref metadata.

crossref_get_work

Search Crossref for scholarly works by free text; find a DOI from a title. Returns normalized records (id/doi/title/authors/year/venue/type/url/oa_url/abstract). Chains into overleaf_write_file via crossref_get_bibtex.

crossref_search_works

Soft-delete a document (deleted_at stamp). Sections are preserved but hidden.

delete_document

Soft-delete an object instance.

delete_object

Delete a saved search (soft delete, like delete_document).

delete_saved_search

Hard-delete a section by id. Cannot be undone.

delete_section

Soft-delete a workorder (deleted_at stamp).

delete_workorder

Extract structured data from a business process diagram instead of raw XML: pools/lanes, every node (id, type, name), the sequence flows with their branch conditions, and summary counts. Use this to read/understand a process. (read)

extract_business_process

Return an artifact's metadata + extracted text (for text files) + any prior AI analysis. For images, call get_artifact_file for the bytes.

get_artifact

Fetch an artifact's bytes. Images return as an MCP image block (multimodal); text files return their extracted text; other binaries return a note.

get_artifact_file

Return a business process diagram's XML + any prior AI analysis.

get_business_process

What is on a collection's shelf. Each item carries the ref its SOURCE addresses it by (an NIH core project number, a DOI), so you can fetch the live record with nih_get_grant / crossref_get_work rather than trusting the stored snapshot.

get_collection

Return a data-model entity with all its fields.

get_data_model

Return a document with its sections, rendered as markdown.

get_document

Fetch one object instance: its attributes, plus sections (documents) or fields (records), and the type's guidance.

get_object

Get one phase with its dependencies.

get_phase

Read a single file from a synced workspace repo. Capped at 200KB; returns text only. Pass start/end (1-based) to get a line range.

get_repo_file

Full detail of one saved search: its exact criteria and the researcher's notes on why it exists and when to use it.

get_saved_search

Return a Designer screen's metadata + description + AI analysis. Does NOT include the image bytes — call get_screen_image for that.

get_screen

Fetch the uploaded mockup image for a Designer screen as an MCP image content block (base64 + mimeType). The agent gets this as a multimodal input it can analyze directly. Returns a text fallback if the screen has no image.

get_screen_image

Return the body of a section by id.

get_section

Get a widget's html + metadata by slug (read-only) — use to review before editing.

get_widget

Fetch one workorder (title + body + status + response).

get_workorder

Full detail for one open funding opportunity — eligibility, award ceiling/floor, estimated funding, expected number of awards, agency contact, and the complete call text. Look it up by opportunity number (e.g. RFA-CA-27-020).

grants_gov_get_opportunity

Search OPEN funding opportunities you can APPLY FOR (NOFOs) across all federal agencies, including NIH and NSF. This is the PROSPECTIVE tool — for grants already awarded use nih_search_grants / nsf_search_awards instead. Expired calls are never returned. Results are sorted by soonest deadline. Full-text over title + the call text.

grants_gov_search_opportunities

Create a directed relationship edge between two object instances. Validated against the ontology's relationship definition (endpoint types + cardinality).

link_objects

List files uploaded to a workspace for analysis (id, name, type, size, analyzed?).

list_artifacts

List business process diagrams in a workspace (id, name, analyzed?).

list_business_processes

List the workspace's COLLECTIONS — curated shelves of results a researcher chose to keep (grants, awards, open calls, papers), from any source. A saved search is a question; a collection is the answers a human kept. PINNED collections are standing context: consult them unprompted and cite them by name. ('off' ones are never shown.)

list_collections

List data-model entities in a workspace.

list_data_models

List a workspace's databases (Database designer), with a table count each.

list_databases

List documents in a workspace, optionally filtered by kind.

list_documents

List pending custom instructions queued by humans for the agent.

list_instructions