get_indexed_file
Get Indexed File ·read-only · non-destructive · idempotent · closed-world
Retrieve the complete indexed file by source_file, assembled in source order.
Unlike search (which caps per-source content chunks at
MAX_CHUNKS_PER_SOURCE = 2), this tool returns all chunks for an exact
source_file path, joined in chunk_index order. Use when you already know
the canonical source_file (from a prior search result) and need the
full document.
Returns: str
Source: backend/src/engram/mcp/tools/context.py
Parameters
Exact source_file value (e.g., ‘projects/engram/investment-memo.md’, ‘github:B3dmar/b3dmar-hq:projects/engram/investment-memo.md’).
Optional life-context filter (‘personal’ or ‘work’). When set, the tool rejects source_files whose path does not match the scope’s configured prefixes.
handoff
Export Handoff Context ·read-only · non-destructive · idempotent · closed-world
Export handoff context as structured JSON for switching between AI providers.
Returns a JSON payload with active commitments, recent decisions, open blockers,
and metadata — designed to carry accountability context across tools.
Returns: str
Source: backend/src/engram/mcp/tools/context.py
Parameters
Optional life context filter (‘personal’ or ‘work’), or “all” for everything
Optional project name filter
Filter by memory types (default: commitment, decision, blocker)
Include recent decisions and other non-active handoff items from the last N hours (default: 24). Active commitments and blockers are unbounded.
Include resolved items (default: false)
#4801 Work Context candidate-restriction. When a collection (possibly empty), the handoff is narrowed to exactly those memory ids — the native lens that
use_context delegate mode passes. The restriction is intersected with the viewer’s visibility predicate, so it can only narrow, never widen. None (default) applies no restriction. An empty collection resolves to an empty handoff.reindex
Reindex Indexed Content ·writes · destructive · idempotent · open-world
Re-index markdown files from CONTENT_ROOT into the document vector store.
Refreshes content_chunks returned by search; does not touch memories.
Returns: str
Source: backend/src/engram/mcp/tools/context.py
Parameters
Optional specific file or directory to reindex (relative to CONTENT_ROOT). If not provided, reindexes everything.