Skip to main content
Glama

Startline AI — MCP server, web app & voice API

The serving layer for Startline AI: an AI companion for motorsport event documents. One process gives you an MCP server for AI agents, a phone-first event-day web app, a voice endpoint for Siri, amendment diffs and calendar export — all over a local document vault.

Built after marshalling at a Formula 1 event, where the official app delivers PDFs but can't answer "what time does sign-on close on Saturday?" — and where an amendment is just another PDF that never tells you what changed.

Index search — SQLite FTS5 + BM25 over heading-level chunks with event-jargon synonyms (sign-on = muster, MxM = minute x minute). Instant, deterministic, works with no signal at the track.

Agent search — an MCP server exposing nine typed tools, so an AI assistant can reason across documents and cite pages:

Tool

Purpose

list_events / event_overview

inventory, categories, amendment count

list_docs

filter by event and category

search

full-text with citations

read_doc

fuzzy name match, pages="3-5" slicing

schedule_for

parsed day timeline, with amendment warnings attached

diff_amendment

what an amendment actually changed

amendments / doc_history

version chains

Register it with any MCP client:

{ "mcpServers": { "startline": {
    "command": "uv",
    "args": ["run", "--directory", "/path/to/startline-server", "startline-mcp"]
}}}

Related MCP server: hidrix-tools

Amendment diffs

The feature the official apps don't have. Each amendment is structurally diffed against the schedule it amends — rows matched by normalised text and classified moved / added / removed inside the amendment's time window — then summarised:

"The one-minute signal to the marshalling area is delayed from 17:09 to 17:24, and the reconnaissance lap release from 17:10 to 17:25. A new 20-minute signal checkpoint has been added at 17:15."

Results are cached by content hash, so each amendment costs one model call ever.

Running it

uv sync
uv run startline-mcp        # MCP server (stdio)
uv run startline-serve      # web app + voice API on :8095
uv run startline-caption    # vision-caption maps and diagrams (cached)
uv run startline-faq        # pre-answer common marshal questions (cached)

Point it at a vault with STARTLINE_VAULT=/path/to/vault (default ~/startline-vault). AI features need ANTHROPIC_API_KEY in the environment; without it, index search and the offline answer fallback still work.

Endpoints

Route

What

/

event-day web app — day chips, NOW/NEXT timeline, filter, amendment banner, ask box

/ask?q=

answer engine (used by the web app, Siri and the iOS app)

/api/events, /api/schedule, /api/diff

JSON for clients

/api/docs, /api/file?path=

browse and stream the event's source PDFs/images

/api/faq

pre-answered common questions, grounded in the event's docs

/calendar.ics?day=&q=

RFC 5545 export, optionally filtered

Answers come back in the language the question was asked in — a Vietnamese question gets a Vietnamese answer, while document titles stay in the original.

Voice

SIRI-SETUP.md has the Apple Shortcut recipe (dictate → HTTP → speak) and a launchd plist for running the server permanently. The iOS app below does this natively with an App Intent.

Vision captions

Maps, gate diagrams and notice photos carry no extractable text, so they are invisible to search. startline-caption sends the rendered pages to a vision model, asks it to describe the page and transcribe every label, and caches the result by content hash. Ingest bakes captions into the notes, which makes questions like "how do I get through the zone fence near post 2.5?" answerable from an image.

Repo

Role

startline-vault

ingest pipeline + offline index search

startline-ios

native SwiftUI client

License

MIT

Available Tools

9 tools
amendmentsB

All amendment documents for an event and what they amend.

Args: event: Event code, e.g. 'AUS-GP-2026'.

Inputs: event (required). Returns: result

diff_amendmentA

What an amendment actually changed vs the schedule it amends: moved/added/removed timeline rows plus a short summary. Cached.

Args: name: Slug or title of the amendment document (see amendments()). event: Optional event code to disambiguate.

Inputs: name (required), event. Returns: object

doc_historyB

Version chain for a document: current version, superseded ones, and amendments pointing at it.

Args: name: Slug or title of any version of the document. event: Optional event code to disambiguate.

Inputs: name (required), event. Returns: object

event_overviewA

Summarise one event: categories with doc counts, plus any amendments.

Args: event: Event code, e.g. 'AUS-GP-2026' (see list_events).

Inputs: event (required). Returns: object

list_docsA

List documents, optionally filtered by event and/or category substring.

Args: event: Event code filter, e.g. 'AUS-GP-2026'. category: Substring match on the category path, e.g. 'briefing' or 'supplementary-regulations'. include_superseded: Include documents replaced by newer versions.

Inputs: event, category, include_superseded. Returns: result

list_eventsA

List all events in the vault with document counts.

Inputs: no named parameters. Returns: result

read_docA

Read a document's full text by slug or title (fuzzy matched).

Args: name: Slug or title, e.g. 'marshals event information booklet' or '2026-mxm-event-sat-v1-a6-device'. event: Optional event code to disambiguate. pages: Optional page range like '3-5' or '12' to return only those '## Page N' sections (recommended for long documents).

Inputs: name (required), event, pages. Returns: object

schedule_forA

Timeline for one event day, parsed from the current Minute-x-Minute.

Args: day: 'friday' / 'fri' / 'saturday' / 'sat' / 'sunday' / 'thursday'. event: Event code, e.g. 'AUS-GP-2026'. query: Optional filter — only entries containing this substring, e.g. 'marshal' or 'supercars'.

Inputs: day (required), event (required), query. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: events, documents, search, schedules, amendments, and history. Overlap is minimal and clarified by descriptions (e.g., event_overview vs. list_docs).

    Naming Consistency3/5

    Names mix conventions: list_events, list_docs, read_doc, diff_amendment follow verb_noun, while event_overview, schedule_for, amendments, and doc_history do not. However, all names are still descriptive and readable, so the inconsistency is moderate rather than chaotic.

    Tool Count5/5

    Nine tools is well within the ideal 3–15 range. Each tool serves a clear purpose in the event-documentation domain, and none feel redundant or unnecessary.

    Completeness5/5

    The domain is a read-only knowledge base for motorsport events, and the set covers event listing, document search/read, per-day schedules, amendments, and version history. No obvious workflow dead ends remain; even superseded documents and amendment diffs are handled.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      This MCP server enables AI agents to view PDFs as accessible HTML with bounding-box citations, and provides tools for layout-aware parsing, schema extraction, cross-document Q&A, and PDF rendering.
      27
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.
      42
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      MCP server that gives AI assistants direct access to RaceHooks motorsport analytics and data, enabling management of webhooks, live sessions, simulations, and account usage.
      58
      60 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for Nyxdoc, a document system where humans and external agents collaborate on documents with version history, agent to-dos, and workspace permissions.
      MIT