# Boardsesh Climbing Logbook (pypi · boardsesh-mcp)

Read-only access to your Boardsesh logbook across Kilter, Tension, MoonBoard and more

- Trust score: 92/100 (high trust)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- pypi · `boardsesh-mcp`: 92/100 (this document), [markdown](https://verifymcp.io/servers/wmmg101-boardsesh-mcp/boardsesh-mcp.md), [page](https://verifymcp.io/servers/wmmg101-boardsesh-mcp/boardsesh-mcp)

## Channel facts

- Registry: `pypi`
- Package: `boardsesh-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to wmmg101/boardsesh-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 24 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2132 tokens (~177/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Boardsesh Climbing Logbook MCP server?

Boardsesh Climbing Logbook runs locally as a PyPI package, launched with uvx boardsesh-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add wmmg101-boardsesh-mcp -- uvx boardsesh-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "wmmg101-boardsesh-mcp": {
      "command": "uvx",
      "args": [
        "boardsesh-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "wmmg101-boardsesh-mcp": {
      "command": "uvx",
      "args": [
        "boardsesh-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add wmmg101-boardsesh-mcp -- uvx boardsesh-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wmmg101-boardsesh-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "boardsesh-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add wmmg101-boardsesh-mcp --command uvx --arg boardsesh-mcp
```

### Hermes

```yaml
mcp_servers:
  wmmg101-boardsesh-mcp:
    command: "uvx"
    args: ["boardsesh-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "wmmg101-boardsesh-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "boardsesh-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add wmmg101-boardsesh-mcp -t stdio -c uvx -a boardsesh-mcp
```

### Other

```json
{
  "mcpServers": {
    "wmmg101-boardsesh-mcp": {
      "command": "uvx",
      "args": [
        "boardsesh-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-15 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 90, +3)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 67. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-06 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 47. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-03 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-30 (score 85, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-28 (score 81, +11)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 70, +2)

- [functional improvement] License: fail → pass
- [functional] Licence: MIT

## MCP tools (12)

### `boardsesh_get_summary` (~82 tokens)

Return a compact overview of the user's whole Boardsesh history, across all boards.

Use first for broad questions ("how is my climbing going?", "summarise my logbook") or
when you need totals: entries, sends, flashes, tries, boards used, angles, date range,
session count, hardest send and flash, and sends per grade.

### `boardsesh_get_ascents` (~239 tokens)

Return the user's logbook entries, newest first, across every board.

Use when the user asks about recent climbs, sends, flashes, attempts, what they did on a
date, or wants raw history. Each entry is one climb at one angle on one board at one time
with the number of tries. Filters: limit (default 25), board, angle, status
('all', 'sends', 'attempts', 'flashes'), start_date/end_date (YYYY-MM-DD).

Input parameters:

- `angle`: Wall angle in degrees (e.g. 20, 40). Omit for all angles.
- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `end_date`: Inclusive end date, YYYY-MM-DD, in the user's timezone.
- `limit`: Maximum number of items to return.
- `start_date`: Inclusive start date, YYYY-MM-DD, in the user's timezone.
- `status`: Filter by outcome. 'sends' includes flashes.

### `boardsesh_get_sessions` (~126 tokens)

Return recent climbing sessions (entries grouped by calendar day), newest first.

Use when the user asks how their last session went, what they climbed on a day, or wants
to compare sessions. Each session lists the boards and angles used, sends, flashes, total
tries, hardest send and every climb logged that day.

Input parameters:

- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `limit`: Maximum number of items to return.

### `boardsesh_get_projects` (~129 tokens)

Return the user's projects: climbs attempted but never sent at that angle.

Use when the user asks what they are working on, unfinished climbs, or what to try again.
A project is per (board, climb, angle), so sending a climb at another angle does not
remove it. Sorted by most recently tried, then most tries.

Input parameters:

- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `limit`: Maximum number of items to return.

### `boardsesh_compare_boards` (~111 tokens)

Compare the user's climbing across every board they have logged on.

Use when the user asks which board they are strongest on, how Kilter compares with
Tension or MoonBoard, or where they climb most. One row per board with sends, flashes,
flash rate, tries, sessions, angles, hardest send in that board's own grades, and
'hardest_boardsesh_grade' / 'median_boardsesh_grade' which are normalised across boards
and therefore the fair comparison.

### `boardsesh_get_grade_pyramid` (~118 tokens)

Return the user's send pyramid: sends per grade, hardest first, with flash rates.

Use when the user asks about their pyramid, grade distribution, flash rate per grade, or
how solid they are at a level. Optional board filter; grades differ between boards, so
prefer filtering to one board when the user names one.

Input parameters:

- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.

### `boardsesh_get_progression` (~131 tokens)

Return climbing progression over time, oldest period first.

Use when the user asks whether they are improving, about trends, or for a month-by-month
or week-by-week view. Each period has sessions, boards used, entries, sends, unique
climbs, flashes, tries and the hardest send.

Input parameters:

- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `period` (string): Bucket size for the progression: calendar month or ISO week.

### `boardsesh_recommend_climbs` (~209 tokens)

Suggest climbs the user has not sent yet, from Boardsesh's recommendations.

Use when the user asks what to try next, wants new climbs, projects at their level, or
something fresh. 'at_level' works from their own send history and excludes climbs they
have already sent. Needs a board configuration, so it uses one of the user's saved
Boardsesh boards.

Input parameters:

- `angle`: Wall angle in degrees (e.g. 20, 40). Omit for all angles.
- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `kind` (string): 'at_level' picks climbs around the user's current grade, 'crowd_favorites' popular ones, 'hidden_gems' under-climbed ones, 'fresh' recently set ones.
- `limit`: Maximum number of items to return.

### `boardsesh_find_similar_climbs` (~192 tokens)

Find climbs that use a similar set of holds to a given climb.

Use when the user asks for climbs like one they enjoyed or one they are projecting, or
wants to train a specific movement again. Similarity is hold overlap (0-1); 0.5 and above
feels genuinely related. Pass a climb_uuid from an earlier result.

Input parameters:

- `angle`: Wall angle in degrees (e.g. 20, 40). Omit for all angles.
- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `climb_uuid` (string, required): The climb to match, as a climb_uuid from another tool's output (e.g. a send or project).
- `limit`: Maximum number of items to return.

### `boardsesh_get_hold_heatmap` (~254 tokens)

Return which holds the wall's climbs use, for spotting strengths and weaknesses.

Use when the user asks about weaknesses, hold types they avoid or overuse, or what to
train. Returns per-hold counts (how many climbs use each hold, and whether as hand, foot,
start or finish) plus the average difficulty of climbs using it. Combine with a grade
range to ask "which holds appear in climbs at my next grade". Hold ids are wall positions;
reason about patterns and grade ranges rather than individual ids.

Input parameters:

- `angle`: Wall angle in degrees (e.g. 20, 40). Omit for all angles.
- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `limit`: Maximum number of items to return.
- `max_grade_id`: Only count climbs at or below this difficulty_id.
- `min_grade_id`: Only count climbs at or above this difficulty_id.
- `only_my_projects`: Restrict to climbs the user has attempted but not completed, to see which holds show up in their unfinished projects.

### `boardsesh_search_climbs` (~234 tokens)

Search the board's climb catalogue with filters.

Use when the user wants to find specific climbs: by name, grade range, benchmarks only,
popularity, or excluding ones they have already sent. For "what should I try next" prefer
boardsesh_recommend_climbs, which uses the user's own level.

Input parameters:

- `angle`: Wall angle in degrees (e.g. 20, 40). Omit for all angles.
- `board`: Board type to filter to: kilter, tension, moonboard, decoy, touchstone, soill, grasshopper, woods or spray. Omit for all boards.
- `exclude_sent`: Hide climbs the user has already sent at this angle.
- `limit`: Maximum number of items to return.
- `max_grade_id`: Maximum difficulty_id.
- `min_ascents`: Only climbs with at least this many community ascents.
- `min_grade_id`: Minimum difficulty_id (see boardsesh_get_grades).
- `name`: Match part of a climb name.
- `only_benchmarks`: Only benchmark climbs.

### `boardsesh_get_grades` (~87 tokens)

Return a board's grade scale: difficulty_id to grade label.

Use when you need a difficulty_id for a grade the user named (e.g. to pass min_grade_id
to a search), or to explain what a grade id means. Boards do not share one scale.

Input parameters:

- `board` (string): Board type, e.g. kilter, tension, moonboard.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/wmmg101-boardsesh-mcp/boardsesh-mcp#diagnostics

## Score history

- 2026-10-17: 92
- 2026-10-16: 92
- 2026-10-15: 92
- 2026-10-14: 91
- 2026-10-13: 91
- 2026-10-12: 90
- 2026-10-06: 87
- 2026-10-04: 86
- 2026-10-03: 86
- 2026-10-02: 85
- 2026-10-01: 85
- 2026-09-30: 85
- 2026-09-29: 81
- 2026-09-28: 81
- 2026-09-27: 70
- 2026-09-26: 70
- 2026-09-25: 68
- 2026-09-24: 68
- 2026-09-23: 68
- 2026-09-22: 68

## Common questions

### What is the Boardsesh Climbing Logbook MCP server?

Boardsesh Climbing Logbook is an MCP server listed in the public MCP registry as io.github.wmmg101/boardsesh-mcp. Read-only access to your Boardsesh logbook across Kilter, Tension, MoonBoard and more. This page covers its PyPI package (boardsesh-mcp).

### Is the Boardsesh Climbing Logbook MCP server safe to use?

Boardsesh Climbing Logbook scores 92 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. Its build provenance is signed and verified. 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 Boardsesh Climbing Logbook MCP server expose?

Boardsesh Climbing Logbook exposes 12 tools: boardsesh_get_summary, boardsesh_get_ascents, boardsesh_get_sessions, boardsesh_get_projects, boardsesh_compare_boards, and 7 more. Their descriptions and schemas cost roughly 1,912 tokens of context every time the server is loaded.

### Is the Boardsesh Climbing Logbook MCP server still maintained?

Boardsesh Climbing Logbook is still listed as active in the MCP registry. We last reached this channel on 17 October 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 Boardsesh Climbing Logbook MCP server under?

Boardsesh Climbing Logbook declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/boardsesh-mcp/
- Socket report: https://socket.dev/pypi/package/boardsesh-mcp
- Repository: https://github.com/wmmg101/boardsesh-mcp
- Changelog RSS feed: https://verifymcp.io/servers/wmmg101-boardsesh-mcp/boardsesh-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/wmmg101-boardsesh-mcp/boardsesh-mcp.json
- HTML version of this page: https://verifymcp.io/servers/wmmg101-boardsesh-mcp/boardsesh-mcp