io.github.mbrionesalvarez/caddie-mcp
PYPI · CADDIE-MCP
Your Garmin golf data in Claude: GPS shots, strokes gained, club distances, health context
Available components
Last scanned (4 hours ago)
Scores higher than 87% of PyPI servers
Category Health and Science
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 40 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 85 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability83
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1509 tokens (~94/item across 16 items; 13 tools + 3 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 4 Nov 26 0
- Security disclosure: unverified → fail ▼ functional
- 3 Nov 26 −15
- Provenance: unverified → fail ▼ security
- Malware scan: pass → unverified ▼ security
- Security disclosure: fail → unverified ▼ functional
- 2 Nov 26 0
- Provenance: fail → unverified ▼ security
- 31 Oct 26 +1
- Provenance: unverified → fail ▼ security
- Stability: 0.97 → pass security
- 30 Oct 26 −1
- Provenance: fail → unverified ▼ security
- Stability: pass → 0.97 functional
- 24 Oct 26 +1
- Stability: 0.97 → pass security
- 23 Oct 26 −1
- Stability: pass → 0.97 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/caddie-mcp@1.0.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 40 packages
| Packages resolved | 40 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
correlate_health_performance ~171
Does recovery (or weather) affect your golf? Joins each round to its health/conditions data and computes a Pearson correlation. Daily metrics (sleep_score, hrv, readiness...) come from the night/day around the round; round-window metrics (bb_at_tee, avg_hr_during_round, avg_stress_during_ round, temp_c, wind_speed_mph) are measured DURING the round itself. Returns the paired table, r, and an honest interpretation — small samples are flagged loudly. Remember lower is better for score/putts: a NEGATIVE r between sleep_score and score_to_par means better sleep, better golf.
| Name | Type | Req | Description |
|---|---|---|---|
| health_metric | string | – | – |
| last_n_rounds | integer | – | – |
| performance_metric | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
garmin_status ~42
Check connector health: Garmin auth state, last sync, cached data coverage (rounds, shots, GPS %, club %). Call this first in a session.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
get_club_stats ~77
Per-club performance over the last N rounds: measured avg/min/max/ stddev carry distance (excludes putts and penalties), sample size, usage share, lateral miss bias from Garmin's dx offsets, plus Garmin's own average and 'advice' distances for comparison.
| Name | Type | Req | Description |
|---|---|---|---|
| last_n_rounds | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_course_intel ~79
Personal course intelligence for one course (name substring match): per-hole scoring average vs par, hardest and easiest holes, most common tee club per hole, and round history there. Use for strategy questions like 'how should I play X next time?'.
| Name | Type | Req | Description |
|---|---|---|---|
| course | string | yes | – |
| last_n_rounds | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_handicap ~59
WHS-style Handicap Index: best-N-of-20 differentials, which rounds count, and the index trend over time. Needs rounds with tee rating and slope (Garmin records these when a tee box is selected on the watch).
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
get_health_context ~97
Health context for a round or date (YYYY-MM-DD): sleep score and duration the night before, HRV status, Body Battery range, training readiness, average stress, resting HR, steps. With round_id, also returns the round summary so performance and recovery sit side by side. NULL fields mean the watch/feature didn't record — say so, don't guess.
| Name | Type | Req | Description |
|---|---|---|---|
| date | – | – | – |
| round_id | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_performance_stats ~111
PGA-style performance stats over the last N rounds: driving distance/ accuracy + miss direction, GIR and proximity by distance bucket, scrambling and sand saves, putting (make % by feet, 3-putt avoidance), scoring (par 3/4/5 averages, bounce-back, distribution). Optionally pass benchmark_handicap to compare every metric against that handicap level.
| Name | Type | Req | Description |
|---|---|---|---|
| benchmark_handicap | – | – | – |
| category | string | – | – |
| last_n_rounds | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_round ~83
Get one round in depth: header, hole-by-hole scorecard, and optionally every shot. round_id comes from list_rounds. Prefer get_shots (with filters or geojson) when the goal is shot analysis or mapping.
| Name | Type | Req | Description |
|---|---|---|---|
| include_holes | boolean | – | – |
| include_shots | boolean | – | – |
| round_id | integer | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_shots ~127
Get shot-level data (GPS, club, lie, distance, miss offsets dx/dy). Filter by round_id, holes, club name substring, or shot_type (drive|approach|chip|putt|penalty). format="geojson" returns a FeatureCollection (shot LineStrings + pin Points) ready for Mapbox or Leaflet — ideal for shot maps and dashboards.
| Name | Type | Req | Description |
|---|---|---|---|
| club | – | – | – |
| format | string | – | – |
| holes | – | – | – |
| limit | integer | – | – |
| round_id | – | – | – |
| shot_type | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
get_strokes_gained ~130
Strokes Gained (Broadie method) per round: total plus off-tee / approach / short-game / putting. baseline: "auto" grades each round against the player's own handicap level; or force one of scratch, 5hcp, 10hcp, 15hcp, 20hcp, bogey (scratch = the number seen on TV). estimated_share > 0 means some shots lacked GPS and used inferred lies/distances — hedge conclusions accordingly.
| Name | Type | Req | Description |
|---|---|---|---|
| baseline | string | – | – |
| last_n_rounds | integer | – | – |
| round_id | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
list_rounds ~85
List golf rounds, newest first, as compact summaries (date, course, score, putts, fairways, GIR, ratings). Dates are YYYY-MM-DD; course is a case-insensitive substring match. Use get_round for hole-by-hole detail.
| Name | Type | Req | Description |
|---|---|---|---|
| course | – | – | – |
| end_date | – | – | – |
| limit | integer | – | – |
| start_date | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
query_golf_data ~88
Run a read-only SQL SELECT over the golf database (DuckDB dialect). Tables: rounds, holes, shots, clubs, daily_health. Read the schema://data-dictionary resource for columns, units, and enums. Single statement, SELECT/WITH only, capped at 200 rows — aggregate server-side instead of selecting raw rows when possible.
| Name | Type | Req | Description |
|---|---|---|---|
| sql | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
sync_garmin_data ~226
Pull golf data from Garmin Connect into the local cache, plus daily health (sleep, HRV, Body Battery, stress, readiness) for round dates. Incremental and CHUNKED: each call syncs up to max_rounds new rounds (default 25, newest first, ~2-4 minutes) and reports rounds_remaining. To load a full multi-year history, simply keep calling this tool until rounds_remaining is 0 — tell the user the total and give a brief progress update between batches. Nothing is lost between calls; every batch is permanent. full=True refetches already-cached rounds (least-recently-synced first; pass max_rounds to bound it, otherwise it runs unbounded). include_health=False skips the health pass. (Very large backfills can also run outside chat: `caddie-mcp sync` in a terminal does it in one go.)
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | – |
| include_health | boolean | – | – |
| max_rounds | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the io.github.mbrionesalvarez/caddie-mcp server?
io.github.mbrionesalvarez/caddie-mcp runs locally as a PyPI package, launched with uvx caddie-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · caddie-mcp
claude mcp add mbrionesalvarez-caddie-mcp -- uvx caddie-mcp
What is the io.github.mbrionesalvarez/caddie-mcp server?
io.github.mbrionesalvarez/caddie-mcp is listed in the public MCP registry as io.github.mbrionesalvarez/caddie-mcp. Your Garmin golf data in Claude: GPS shots, strokes gained, club distances, health context. This page covers its PyPI package (caddie-mcp).
Is the io.github.mbrionesalvarez/caddie-mcp server safe to use?
io.github.mbrionesalvarez/caddie-mcp scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.mbrionesalvarez/caddie-mcp server expose?
io.github.mbrionesalvarez/caddie-mcp exposes 13 tools: garmin_status, sync_garmin_data, list_rounds, get_round, get_shots, and 8 more. Their descriptions and schemas cost roughly 1,375 tokens of context every time the server is loaded.
Is the io.github.mbrionesalvarez/caddie-mcp server still maintained?
io.github.mbrionesalvarez/caddie-mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.mbrionesalvarez/caddie-mcp server under?
io.github.mbrionesalvarez/caddie-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.