startline
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@startline what time does qualifying start on Saturday?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Two kinds of search
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 |
| inventory, categories, amendment count |
| filter by event and category |
| full-text with citations |
| fuzzy name match, |
| parsed day timeline, with amendment warnings attached |
| what an amendment actually changed |
| 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 |
| answer engine (used by the web app, Siri and the iOS app) |
| JSON for clients |
| browse and stream the event's source PDFs/images |
| pre-answered common questions, grounded in the event's docs |
| 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.
Related repos
Repo | Role |
startline-vault | ingest pipeline + offline index search |
startline-ios | native SwiftUI client |
License
MIT
Available Tools
9 toolsamendmentsB
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
searchA
Full-text search over every document chunk (FTS5 + BM25 + synonyms).
Best first step for any factual question. Results cite note + page heading; follow up with read_doc for full context.
Args: query: Plain words, e.g. 'sign on saturday' or 'pit lane speed limit'. event: Optional event code filter. category: Optional substring filter on category path. include_superseded: Also search documents replaced by newer versions. limit: Max results (default 8).
Inputs: query (required), event, limit, category, +1 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
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).
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.
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.
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
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for agentverse documentation, generated by doc2mcp.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Related MCP Servers
- AlicenseAqualityDmaintenanceThis 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.27MIT
- AlicenseNot gradedqualityCmaintenanceMCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.42MIT

@racehooks/mcpofficial
AlicenseBqualityBmaintenanceMCP server that gives AI assistants direct access to RaceHooks motorsport analytics and data, enabling management of webhooks, live sessions, simulations, and account usage.5860 npm1MIT- AlicenseNot gradedqualityBmaintenanceMCP server for Nyxdoc, a document system where humans and external agents collaborate on documents with version history, agent to-dos, and workspace permissions.MIT