timeline-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_timeline_eventsB | Extract timeline-relevant events from a list of conversation messages. Parses time expressions and detects event types like surgery, stitch removal, symptom start, medication start/stop, and follow-up visits. |
| build_timeline_stateB | Create a normalized timeline state from extracted events. Aggregates events, resolves duplicates, computes derived fields like days_since_surgery, and determines the current recovery phase. |
| summarize_timeline_contextC | Generate a short timeline-aware summary for insertion into an LLM system prompt or tool context. |
| days_since_eventC | Return the number of days since a named timeline event (e.g., surgery_date). |
| upsert_message_into_timelineB | Incrementally update a running timeline with one new message. Extracts events, merges into existing state, and recomputes derived fields. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Most tools are clearly separated by their role in the pipeline: extraction, state building, summarization, and querying. There is minor overlap between build_timeline_state and upsert_message_into_timeline since both aggregate events and recompute derived fields, but the incremental vs bulk distinction is clear enough.
The naming mostly follows a verb_noun pattern: extract_timeline_events, build_timeline_state, summarize_timeline_context, upsert_message_into_timeline. The exception is days_since_event, which is not a verb-led action name and breaks the pattern slightly.
Five tools is well-scoped for a focused timeline-management server. Each tool covers a distinct stage of the workflow without redundancy or excessive granularity.
The core lifecycle is covered: extraction, state construction, incremental updates, summarization, and queries. Minor gaps include lack of an explicit reset/clear operation or a way to remove individual events, but these are not critical for the intended use case.