12 entities and 60 agent-callable operations in investigation. Each operation is addressed as {mega_tool}/investigation/{entity}/{operation} and carries the same permission check over MCP and REST.
60 of 60 shown
analysis_request
Operation
Mega-tool
What it does
list
entity_crud
List analysis_requests with filtering and pagination
read
entity_crud
Get detailed analysis request information
search
entity_crud
Search analysis_requests with fuzzy matching
deidentification
Operation
Mega-tool
What it does
approvals
report_query
Export approvals recorded for a DFCS investigation: who approved which scope under which method version and date granularity, the sample counts they approved…
approve_export
smart_action
Approve the export of a de-identified scope.
counts
report_query
What the de-identification pass actually did, by type: entities detected, values restored by the allowlist, detections dropped below threshold, and the…
export
smart_action
Write the approved de-identified records of a scope to a JSONL file on the host.
list
report_query
De-identified records you may see, newest month first: id, record key, status, review decision, stratum and token counts.
review_decision
smart_action
Record a human accept or reject decision on ONE de-identified record, after reading its text in the review tab.
revoke_export
smart_action
Revoke a live export approval.
sample
report_query
The human review sample for one de-identification run — the 40 records drawn by stratum (records carrying child/relative pseudonyms, records the residual…
set_profile
smart_action
Set this organization's de-identification profile: which agency and provider domains and names are correspondents rather than patients (and so are restored…
start
smart_action
Start a de-identification pass over a DFCS (also written DFACS) investigation: segment every held record, scrub it with AWS Comprehend Medical DetectPHI plus…
status
report_query
State of one de-identification pass over a DFCS (also written DFACS) investigation: the run row (state, stop reason, spend against ceiling), how many text…
investigation
Operation
Mega-tool
What it does
create
entity_crud
Create a new investigation
delete
entity_crud
Delete an investigation
list
entity_crud
List investigations with filtering and pagination
list
smart_action
List investigations matching the supplied filters.
publish
smart_action
Publish an investigation report from a Typst source.
read
entity_crud
Get detailed investigation information
search
entity_crud
Search investigations by text query
update
entity_crud
Update an investigation
investigation_finding
Operation
Mega-tool
What it does
create
entity_crud
Create a new investigation finding
delete
entity_crud
Delete an investigation finding
list
entity_crud
List investigation findings with filtering
read
entity_crud
Get detailed finding information
search
entity_crud
Search investigation findings
update
entity_crud
Update a finding
investigation_folder
Operation
Mega-tool
What it does
create
entity_crud
Create a new investigation folder
delete
entity_crud
Delete an investigation folder
list
entity_crud
List investigation folders
read
entity_crud
Get folder details
search
entity_crud
Search investigation folders by name
update
entity_crud
Update a folder
investigation_folder_assignment
Operation
Mega-tool
What it does
create
entity_crud
Create a new investigation folder assignment
list
entity_crud
List investigation_folder_assignments with filtering and pagination
read
entity_crud
Get detailed investigation folder assignment information
investigation_phase
Operation
Mega-tool
What it does
create
entity_crud
Create a new phase
delete
entity_crud
Delete a phase
list
entity_crud
List investigation phases
read
entity_crud
Get phase details
search
entity_crud
Search investigation phases
update
entity_crud
Update a phase
investigation_run
Operation
Mega-tool
What it does
calibration
report_query
The model-selection evidence for this investigation: per-rung F1 / recall on dfacs_related, macro-F1 on interaction type, exact match on referral outcome…
cancel
smart_action
Request cancellation of a running DFCS investigation stage.
counts
report_query
The monthly series behind the DFCS timeline, keyed YYYY-MM: the referral funnel (inquiries → referrals → admissions, with declines split by side) over…
dry_run
smart_action
Project what the next DFCS stage would cost on this run — rows remaining, per-item list price, projected USD and whether it fits the ceiling.
list
report_query
Every DFCS investigation run you may see, newest first: kind, state, stop reason, spend against ceiling and the models chosen.
start
smart_action
Start one stage of the DFCS (also written DFACS) relationship investigation pipeline on an existing restricted investigation: stage0 (metadata census, free)…
status
report_query
State of one DFCS (also written DFACS) investigation run — stage, stop reason, spend against ceiling, chosen models, per-model usage and the stage counters…
investigation_share
Operation
Mega-tool
What it does
list
entity_crud
List investigation_shares with filtering and pagination
read
entity_crud
Get detailed investigation share information
investigation_workstream
Operation
Mega-tool
What it does
create
entity_crud
Create a new workstream
delete
entity_crud
Delete a workstream
list
entity_crud
List investigation workstreams
read
entity_crud
Get workstream details
search
entity_crud
Search workstreams
update
entity_crud
Update a workstream
problem_list
Operation
Mega-tool
What it does
problem_list_summary
smart_action
Summarize a patient's active problem list (EHR investigation context).
report
Operation
Mega-tool
What it does
publish_investigation
smart_action
Publish an investigation report from a Typst source file.
Parameter schemas and permissions
Parameter schemas and permission codenames are in the full reference — sign in — or call prism_introspect(dimension="capability_search", query="…") with your key.