This FastMCP-based Todo Server, developed for the Swarmonomicon project, receives todo requests via FastMCP and stores them in MongoDB. It integrates with the Swarmonomicon todo worker, providing a Python-based implementation for task management and distribution. The server offers features like adding todos with priorities and target agents, querying todos with filters and projections, and supports real-time updates via MQTT, making it suitable for AI-driven task automation and collaborative workflows.
Nessuna recensione ancora. Sii il primo a recensire!
Accedi per unirti alla conversazione
Highlight AICreate a task with project, priority, target agent, notes, and metadata.
MongoDB-style filter queries with projection, limit, offset, `since` change detection, and `graph_root` for dependency subgraph traversal.
Patch any fields; metadata is deep-merged. Supports `$push`/`$pull` on array fields (e.g. `metadata.blockers`) for dependency linking.
Remove a task.
Fetch a single task by ID.
Stage for review with optional comment; writes to audit log. Sets status to `review`, not `completed`.
Filter by status: `pending`, `initial`, `in_progress`, `blocked`, `review`, `completed`.
Tokenized multi-word fuzzy text search.
Recent tasks for a specific project.
Capture a lesson with language, topic, and tags.
Fetch by ID.
Patch lesson content or metadata.
Remove a lesson.
Text search across lesson fields.
Regex pattern search.
Browse all lessons, with brief mode for summaries.
List sessions, optionally filtered by project.
Fetch a session by ID.
Start a new AI work session.
Spawn a child session from a parent, linked to a todo.
Fork a session with optional message inheritance.
Full ancestor/descendant trace for a session.
Visual session tree for a project.
Link a todo to a session.
Create an epic goal container (Quest → Chains → Todos). Use instead of `add_todo` for multi-step objectives.
Progress report: % complete, per-chain status, next actions, blockers. Agent orientation tool.
List quests filtered by status/project.
Add an existing todo to a quest chain retroactively (creates chain on demand).
Update quest fields: name, description, status, success_criteria, metadata.
One call: recent todos, lessons, session state, project stats for an agent's working context.
Semantic similarity search across todos and lessons. Returns honest empty when nothing clears the relevance threshold — no regex fallback noise.
Pre-task lessons check: call before starting work, classifies past solutions vs pitfalls.
Persistent agent journal — leave notes readable by other agents for cross-agent coordination.
Retrieve notes from the persistent agent journal.
Audit log queries: filter by type, project, date range.
Enumerate known projects from filesystem.
Topic explanation system: persistent knowledge cards.
Add a topic explanation to the persistent knowledge cards.
Logs an observation with configurable sarcasm. Useful for marking known issues during automated runs.
Inject a Python, JavaScript, or shell function as a live MCP tool at runtime.
