memory_get_by_id
Retrieve a specific document by its exact ID.
How to use it
memory_get_by_id is exposed by the Junto Memory MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the memory_get_by_id tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Junto Memory
python -m shared_memory --transport stdioOther tools in Junto Memory (39)
Mark a message as received (shortcut for status update).
Add a task, feature request, or tech debt item to the backlog.
Manage API keys and view audit logs. Actions: createkey, revokekey, listkeys, auditlog, authstatus. Requires owner role when auth is enabled.
Bulk archive all documents matching a tag (e.g., end-of-version cleanup).
Get a prompt and unenriched functions to run local enrichment on your machine.
Change a document's status: active, deprecated, superseded, archived. Preserves history.
Shared checklists for launch readiness, deploy steps, etc. Actions: create, get, add, check, delete, list.
Mark a backlog item as done or won't-do, with optional resolution notes.
Read-only queries against registered external databases. Actions: list, schema, query. SQL injection protection built in.
Create or update a versioned spec with owner-only enforcement. Supports semver and history.
Record a summary, files modified, and handoff notes. Releases all locks. Call this when done.
Add deep analysis to a function ref: signature, parameters, side effects, complexity. For librarian use.
Search for functions by purpose or name. Check before implementing to avoid duplication.
See what other agents are currently working on — tasks, files touched, timestamps. Avoid overlap.
Get heartbeat status of agents. Flags agents stale after 5 minutes.
View functions awaiting librarian enrichment.
View current file locks with stale detection (inactive > 30 min).
Get pending messages for your agent. Scoped by project.
Retrieve a spec by name, optionally at a specific historical version.
Manage behavioral rules that all agents receive at session start. Actions: list, set, delete, get. Update once, every agent on every machine picks it up.
Send a heartbeat with your current status (idle, busy, error). Enables stale detection.
Discover registered agents across projects with roles and last activity.
List backlog items with filters: project, status, priority, assignee, milestone.
List all projects with document counts. No session required.
List all specs with optional version history and type filtering.
Atomically lock files for exclusive editing. Supports directory locks. Auto-releases on session end.
Manage projects and agents. Actions: create, get, list, delete, addagent, removeagent, updateagent.
Search the knowledge base by natural language. Returns relevant docs with relevance scores.
Quick shortcut to record a learning, gotcha, or technique for other agents.
Register a function reference with name, file, purpose, and optional gotchas. Triggers librarian enrichment.
Bulk restore previously archived documents by tag.
Search across all projects and shared collections at once.
Send a message to another agent. Supports categories (task, question, blocker, etc.) and threading.
Register a session and receive context: recent learnings, active agents, file locks, pending signals. Call this first.
Store a new document (architecture, API spec, code snippet, interface contract, etc.).
Release specific file locks or all locks held by your session.
Update a backlog item's status, priority, assignee, or description.
Track message lifecycle: pending, delivered, received, completed, failed.
Update your current work status and files touched. Enables overlap detection and dependency signaling.