Skip to content

MCP Tools Reference

This is the complete 25-tool contract exposed by the official ForeverLM remote connector used by ChatGPT, Claude, Gemini, and Grok. See Connect an AI Assistant for setup.

The native app contains additional device-internal tools for ingestion, connectors, local files, and app automation. Those are not part of the official remote connector and are intentionally omitted here. A connector you build yourself uses that separate device-hosted integration surface.

Status and sources

ToolParametersDescription
get_mcp_statusnoneReport connection mode and capabilities. Call this first.
list_sourcesnoneList source metadata from the library.
get_source_contentsource_idReturn canonical readable text for one exact source ID.
search_sources_semanticquery, limit?, threshold?, project_id?, exclude_project_id?Search on-device source embeddings. This requires an active Mac; hosted MCP reports the capability as unavailable instead of silently changing the result.

Projects

Projects are explicit scopes. The connector never infers a Project from the app's current selection. A Project's scope includes its own sources plus the sources of Projects it directly lists under Uses context from; responses identify the context Project rather than presenting those sources as copied membership.

ToolParametersDescription
list_projectsinclude_completed?List Projects and their source counts.
get_projectproject_idReturn one Project's instructions, research questions, notes, open gaps, and source IDs.
list_project_sourcesproject_idList approved sources and understanding state for one Project.
get_project_contextproject_id, max_source_chars?, include_emergent_state?, include_source_content?Return Project metadata, linked sources, open gaps, artifact metadata, review state, and optional source excerpts. Project workspace-file bodies and artifact Markdown live in iCloud Drive and are unavailable to the always-on hosted service; the response reports that limitation explicitly.

Schedule and Learning Journey

Read the current Schedule before proposing or changing a plan. Dates use YYYY-MM-DD in the learner's local calendar.

ToolParametersDescription
get_learning_journeygoal_id?, include_completed?Return the current Schedule week, placements, completion state, and goal tags.
get_today_sourcesgoal_id?, date?, date_basis?, activity_kind?, include_completed?, max_chars_per_source?Return readable content for sources planned, used, or completed on a chosen day.
create_learning_journeytitle?, source_ids?, start_date?, end_date?Create a Schedule goal and optionally place existing sources.
add_learning_journey_sourcessource_ids, goal_id?, date?Add existing sources and optionally assign a date.
assign_learning_journey_sources_to_daysource_ids, date, goal_id?Assign or move sources to a calendar day. goal_id is required when placing a source not already on the Schedule.
remove_learning_journey_sourcessource_ids, goal_id?Remove sources from a Schedule goal.
clear_learning_journey_daydate, goal_id?, include_completed?Remove matching placements from one day.
mark_learning_journey_day_donedate, goal_id?Mark every pending source on one day complete.
set_learning_journey_source_completionsource_id, is_completed, goal_id?Complete or reopen one scheduled source.
update_learning_journeygoal_id, title?, start_date?, end_date?Update the title or date range. The merged final range is validated even when only one boundary changes.
delete_learning_journeygoal_id?Delete a Schedule goal and detach its placements.

Review sessions

A completed MCP review keeps the actual exported transcript, not just summary metadata. Source links and Schedule completion are updated only after the review is durably recorded.

ToolParametersDescription
start_review_sessiontopic, source_id?, source_ids?, project_id?, operation_id?Create a durable source-grounded Feynman review session.
end_review_sessionsession_id, overall_score, summary, transcript?, chat_export?, source_ids?, topic?, gaps?, memory_attempts?Complete the review, save its transcript, and link Schedule state. The always-on host requires a transcript because it does not own an in-app chat; structured Memory Review evidence requires an active Mac.
get_review_sessionstopic?, source_id?List saved reviews, optionally filtered by topic or source.
get_review_session_transcriptsession_idReturn the stored transcript and parsed exchanges.
import_review_chattitle, transcript, source_ids?, summary?, overall_score?, model_provider?, model_id?Import an externally completed review as searchable per-turn exchanges and link its completed state. The hosted service requires explicit source_ids; only an active Mac can use its current app selection.
search_review_sessionsquery, limit?Search saved review topics, summaries, and transcript text.

Hosted and active-Mac execution

The official connector has one stable list and public input contract regardless of execution mode. Most calls can run from the always-on hosted CloudKit projection. The semantic index, iCloud Drive workspace-file bodies, structured Memory Review completion, and ambient app selection remain device-local. Calls that need those capabilities route to an active Mac when available; otherwise get_mcp_status and the affected response state the limitation directly. Enabling hosted MCP never removes a tool or silently substitutes a different result.