# ShotPulled (remote · mcp.shotpulled.com)

Espresso dialing: log a shot, say how it tasted, get one change in your grinder's own clicks.

- Trust score: 85/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `mcp.shotpulled.com`: 85/100 (this document), [markdown](https://verifymcp.io/servers/com-shotpulled-shotpulled/mcp.md), [page](https://verifymcp.io/servers/com-shotpulled-shotpulled/mcp)

## Channel facts

- Endpoint: `https://mcp.shotpulled.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-09-21.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 7053 tokens (~164/item across 43 items; 41 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 68% 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.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 42 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the ShotPulled MCP server?

ShotPulled is a hosted endpoint at https://mcp.shotpulled.com/mcp, so there is nothing to install locally. 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 --transport http com-shotpulled-shotpulled 'https://mcp.shotpulled.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-shotpulled-shotpulled": {
      "url": "https://mcp.shotpulled.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-shotpulled-shotpulled": {
      "type": "http",
      "url": "https://mcp.shotpulled.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-shotpulled-shotpulled]
url = "https://mcp.shotpulled.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-shotpulled-shotpulled": {
      "type": "remote",
      "url": "https://mcp.shotpulled.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-shotpulled-shotpulled --url 'https://mcp.shotpulled.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-shotpulled-shotpulled:
    url: "https://mcp.shotpulled.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-shotpulled-shotpulled": {
      "Transport": "http",
      "Url": "https://mcp.shotpulled.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-shotpulled-shotpulled -t streamable-http -u 'https://mcp.shotpulled.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-shotpulled-shotpulled": {
      "type": "http",
      "url": "https://mcp.shotpulled.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-09-20 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 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.

### 2026-09-17 (score 83, 0)

- [functional regression] Schema quality: 6210 → 7053
- [functional] Server version: 1.1.0 → 1.2.0
- [functional] New tool “update_grinder”
- [functional] New tool “update_machine”
- [functional] New tool “update_scale”
- [functional] New tool “update_water”

### 2026-09-16 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 81, 0)

- [security] New tool “merge_beans”, which the server declares destructive
- [security] Tool “compute_age” rewrote its description, which is the text the model reads
- [security] Tool “list_beans” rewrote its description, which is the text the model reads
- [security] Tool “register_coffee” rewrote its description, which is the text the model reads
- [security] Tool “update_bean” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 142 → 159
- [functional] Server version: 1.0.2 → 1.1.0
- [functional] New tool “register_bag”
- [functional] New tool “update_bag”
- [cosmetic] “compute_age” added an optional parameter “bag_id”
- [cosmetic] “log_shot” added an optional parameter “bag_id”
- [cosmetic] “register_coffee” added an optional parameter “acidity”
- [cosmetic] “register_coffee” added an optional parameter “arabica_pct”
- [cosmetic] “register_coffee” added an optional parameter “body”
- [cosmetic] “register_coffee” added an optional parameter “notes”
- [cosmetic] “register_coffee” added an optional parameter “sweetness”
- [cosmetic] “update_bean” reworded the description of “reason”
- [cosmetic] Tool “list_beans” changed its title: List bags of coffee → List coffees
- [cosmetic] Tool “register_coffee” changed its title: Register a bag of coffee → Register a coffee
- [cosmetic] Tool “update_bean” changed its title: Update a bag of coffee → Update a coffee

### 2026-09-11 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (41)

### `register_grinder` (~212 tokens)

Register a grinder

Register a manual or electric grinder with its dial settings scheme.

Input parameters:

- `archived` (integer): 1 if archived, 0 if active
- `burr_type` (string, required)
- `components_spec` (string): JSON mapping string representing compound adjustment math
- `direction_convention` (string, required)
- `max_value` (number|null): Optional travel max bounds
- `microns_per_step` (number|null): Optional mechanical burr travel microns per nominal step
- `min_value` (number|null): Optional travel min bounds
- `motor_type` (string, required)
- `name` (string, required): The name/model of the grinder, e.g. Kinu M47
- `nominal_step` (number, required): Smallest adjustment increment (e.g. 1 click or 0.1collar units)
- `notes` (string): Additional notes
- `photo` (string): Photo path or URL
- `setting_scheme` (string, required): Collar mark style: single clicks or compound (rotation.number.clicks)

Output parameters:

- `grinder_id` (integer)
- `message` (string)
- `status` (string)

### `set_grinder_position` (~80 tokens)

Set grinder position

Set the current grinder collar position. source="measured" resets verification freshness.

Input parameters:

- `grinder_id` (integer, required)
- `setting_label` (string, required): Verbatim display label, e.g. "1.1.2"
- `source` (string, required): Whether setting is verified ("measured") or guess ("recalled"/"assumed")

Output parameters:

- `grinder_id` (integer)
- `message` (string)
- `position_value` (integer)
- `setting_label` (string)
- `source` (string)
- `status` (string)

### `register_machine` (~258 tokens)

Register an espresso machine

Register an espresso or alternative preparation machine.

Input parameters:

- `archived` (integer): 1 if archived, 0 if active
- `basket_size_grams` (number)
- `boiler_type` (string)
- `built_in_grinder_id` (integer): id of a grinder built into this machine (bean-to-cup / integrated grinder)
- `connected_device` (string): Metadata mapping to smart hardware APIs
- `control_type` (string, required)
- `name` (string, required): Machine name/model, e.g. Dedica EC685
- `notes` (string)
- `photo` (string): Photo path or URL
- `prep_style` (string): Preparation style. One of: espresso, filter, immersion, percolation. Only "espresso" is diagnosed by the dialing engine (G8) — anything else is recorded but never dialed, so do not guess this field.
- `prep_type` (string): Preparation equipment type. One of: espresso_machine, lever_press, moka_pot, aeropress, french_press, v60_dripper, cold_brew. Lower snake_case.
- `tools` (string|null): JSON or comma-separated tools, e.g., paper filters, flow control, metal mesh

Output parameters:

- `machine_id` (integer)
- `message` (string)
- `status` (string)

### `set_equipment_archived` (~67 tokens)

Archive or restore equipment

Archive or restore a grinder, machine, water, or scale.

Input parameters:

- `archived` (integer, required): 1 to archive, 0 to restore
- `id` (integer, required): The ID of the equipment
- `kind` (string, required): The kind of equipment to archive/restore

Output parameters:

- `message` (string)
- `status` (string)

### `update_grinder` (~346 tokens)

Update a grinder

Correct a registered grinder — its name, burrs, collar scheme, nominal step, layout, range or notes. Only the keys you send in fields change; send null to clear an optional field (an empty string also clears a text field, but not a number or a closed list). Required fields can be changed but not cleared. fields may be omitted when only reason is sent. setting_scheme, nominal_step and components_spec describe the collar every recorded grind label is read through: call with dry_run first to see which recorded settings would read as a different position, and tell the user before saving. Saving records the change in the grinder's maintenance history; when a locked recipe's setting moves it also opens an unmeasured calibration epoch (set_maintenance_offset resolves it). The collar's current setting is marked assumed when it reads differently, or cleared when the new collar cannot read it, and measured offsets are converted when a click changes worth. Changing direction_convention is a correction — it moves no number, but every finer/coarser said about this grinder was the wrong way round.

Input parameters:

- `dry_run` (boolean): true: write nothing, and answer with what the edit would do to the settings already recorded (moved[], checked, epoch, position_moved, position_cleared, rescaled_offsets, resigned_offsets, step_ignor…
- `fields` (object)
- `grinder_id` (integer, required): This account's own grinder number, from list_grinders. Never guess one.
- `reason` (string): Optional note, appended to this record's own notes as an ordinary line. Omit it and nothing is written.

Output parameters:

- `changed_keys` (array)
- `checked` (integer|null)
- `direction_flipped` (boolean)
- `dry_run` (boolean)
- `entry_id` (null|integer)
- `epoch` (boolean)
- `grinder_id` (integer)
- `message` (string)
- `moved` (array)
- `moved_count` (integer|null)
- `position_cleared` (boolean)
- `position_moved` (boolean)
- `reads_changed` (boolean)
- `recipe_count` (integer|null)
- `rescaled_offsets` (integer)
- `resigned_offsets` (integer)
- `status` (string)
- `step_ignored` (boolean)
- `unreadable` (integer|null)
- `untranslatable` (integer|null)
- `untranslatable_recipes` (integer|null)

### `update_machine` (~191 tokens)

Update a machine

Correct a registered machine — its name, control type, prep type and style, basket, boiler, accessories or notes. Only the keys you send in fields change; send null to clear an optional field (an empty string also clears a text field, but not a number or a closed list). Required fields can be changed but not cleared. fields may be omitted when only reason is sent. prep_style decides whether shots on this machine are diagnosed at all: only "espresso" is. Programs are edited with register_program, the built-in grinder link is not editable here, and archiving is set_equipment_archived.

Input parameters:

- `fields` (object)
- `machine_id` (integer, required): This account's own machine number, from list_machines. Never guess one.
- `reason` (string): Optional note, appended to this record's own notes as an ordinary line. Omit it and nothing is written.

Output parameters:

- `changed_keys` (array)
- `machine_id` (integer)
- `message` (string)
- `status` (string)

### `update_scale` (~170 tokens)

Update a scale

Correct a registered scale — its type, resolution, capacity, capabilities, build or notes. Only the keys you send in fields change; send null to clear an optional field (an empty string also clears a text field, but not a number or a closed list). Required fields can be changed but not cleared. fields may be omitted when only reason is sent. The three capabilities are 1, 0, or null for "the maker never said"; leave one out rather than sending 0 when nobody knows.

Input parameters:

- `fields` (object)
- `reason` (string): Optional note, appended to this record's own notes as an ordinary line. Omit it and nothing is written.
- `scale_id` (integer, required): This account's own scale number, from list_scales. Never guess one.

Output parameters:

- `changed_keys` (array)
- `message` (string)
- `scale_id` (integer)
- `status` (string)

### `update_water` (~136 tokens)

Update a water recipe

Correct a registered water — its name, type, mineral figures or notes. Only the keys you send in fields change; send null to clear an optional field (an empty string also clears a text field, but not a number or a closed list). Required fields can be changed but not cleared. fields may be omitted when only reason is sent.

Input parameters:

- `fields` (object)
- `reason` (string): Optional note, appended to this record's own notes as an ordinary line. Omit it and nothing is written.
- `water_id` (integer, required): This account's own water number, from list_waters. Never guess one.

Output parameters:

- `changed_keys` (array)
- `message` (string)
- `status` (string)
- `water_id` (integer)

### `log_maintenance` (~410 tokens)

Log maintenance

Log a cleaning or maintenance job against a piece of equipment. A task that takes the thing apart opens a calibration epoch, and every recipe locked before it is read through that epoch's offset — so record the offset here if you counted the clicks while reassembling, which is the one moment anybody actually knows it. Read the available tasks, their intervals and their due state from list_grinders.

Input parameters:

- `details` (object): Fields specific to this task. Which ones a task takes is published as details_fields in the task catalog on list_grinders; a burr clean takes none
- `disturbs_zero` (integer): Whether this job disturbed the reference the stored numbers are read against — for a burr clean, whether the burrs actually came out. Defaults to the task's own answer; send 0 for a wipe-down that le…
- `equipment_id` (integer, required): The ID of that piece of equipment
- `equipment_kind` (string, required): Which kind of equipment this job was done on
- `evidence` (string): One line recording what the measurement rested on, e.g. "Counted 6 clicks coarser at reassembly."
- `note` (string): Optional — what you did, and anything that surprised you
- `offset_source` (string): How the offset was arrived at: pull (a reference shot), counted (clicks counted at reassembly), typed (asserted directly)
- `offset_value` (number): The correction, if you measured it now: clicks to ADD to a pre-clean reading to get the same grind today, signed along the collar's own number direction. Omit it and the epoch stays unmeasured, which…
- `performed_at` (string): When it was done (ISO 8601 or YYYY-MM-DD HH:MM:SS, UTC). Defaults to now; backdating is fine
- `task` (string, required): Which maintenance job was performed

Output parameters:

- `entry` (object)
- `entry_id` (integer)
- `message` (string)

### `set_maintenance_offset` (~216 tokens)

Set calibration offset

Record how far a maintenance job moved the reference, on an entry that opened a calibration epoch. Takes an ENTRY, not a piece of equipment: the offset belongs to the event that caused it, which is what lets several of them compose for a recipe locked before all of them. Zero is a legitimate measurement and means "measured, and it had not moved" — omit offset_value entirely to clear it back to unmeasured.

Input parameters:

- `entry_id` (integer, required): The maintenance entry that opened the epoch, from list_grinders
- `evidence` (string): One line recording what it rested on, e.g. "Reference pull 1.38 g/s against 1.74 g/s locked."
- `offset_value` (number): Clicks to ADD to a pre-clean reading to get the same grind today, signed along the collar's own number direction. 0 records "unchanged"; omit to clear the measurement
- `source` (string): How it was arrived at: pull, counted, or typed

Output parameters:

- `entry` (object)
- `message` (string)

### `register_water` (~148 tokens)

Register a water recipe

Register a custom or commercial water formulation.

Input parameters:

- `calcium` (number|null): Calcium concentration in ppm
- `gh` (number|null): General hardness (GH) in ppm
- `kh` (number|null): Karbonate hardness (KH) in ppm
- `magnesium` (number|null): Magnesium concentration in ppm
- `name` (string, required): Water formulation name, e.g. Lotus Light & Bright, Third Wave Water
- `notes` (string): Additional notes
- `sodium` (number|null): Sodium concentration in ppm
- `tds` (number|null): TDS in ppm
- `type` (string): Type, e.g., mineralized, tap, distilled, RO

Output parameters:

- `message` (string)
- `status` (string)
- `water_id` (integer)

### `list_waters` (~74 tokens)

List water recipes

List registered waters for the account. The `id` on each row is the number this account knows that record by, counting from 1 — safe to show, and what other tools expect back.

Input parameters:

- `status` (string): Filter by status: current (unarchived), archived, or all. Defaults to current.

Output parameters:

- `waters` (array)

### `register_scale` (~413 tokens)

Register a scale

Register a brewing scale — the instrument that weighs the dose and the yield.

Input parameters:

- `auto_tare` (integer|null): 1 if it zeroes itself when a vessel is set down, 0 if not, null if unstated
- `auto_timer` (integer|null): 1 if the timer starts on first flow, 0 if not, null if unstated
- `capacity_g` (number|null): Maximum weight in grams. The cup or portafilter counts against it
- `connectivity` (string): How the scale talks to an app or a machine controller
- `depth_mm` (number|null): Platform depth in mm
- `flow_rate_display` (integer|null): 1 if the scale shows live flow rate in g/s, 0 if it does not, null if the maker never said
- `height_mm` (number|null): Overall height in mm — the dimension that decides whether it fits under a group head
- `name` (string, required): Scale name/model, e.g. Acaia Lunar, Timemore Black Mirror Basic 2
- `notes` (string): Additional notes
- `power` (string): How it is powered or recharged
- `resolution_banded` (integer|null): 1 when resolution_g only holds in the lowest weight band and coarsens with load — put the ladder in notes
- `resolution_g` (number|null): Finest published readability in grams. Leave null unless the maker states it
- `scale_type` (string, required): What the scale is built for: espresso (drip-tray footprint), brew (pour-over platform), dual (both modes), connected (app/controller integration), dosing (gravimetric dispensing), training, bench (hi…
- `water_resistance` (string|null): IEC 60529 ingress code as published, e.g. IPX4, IPX6, IP67, or none
- `width_mm` (number|null): Platform width in mm — measure your drip tray

Output parameters:

- `message` (string)
- `scale_id` (integer)
- `status` (string)

### `list_scales` (~74 tokens)

List scales

List registered scales for the account. The `id` on each row is the number this account knows that record by, counting from 1 — safe to show, and what other tools expect back.

Input parameters:

- `status` (string): Filter by status: current (unarchived), archived, or all. Defaults to current.

Output parameters:

- `scales` (array)

### `register_program` (~193 tokens)

Register a machine program

Register a programmed shot button on a machine. A program cuts the shot off either by weight (program_type "volumetric", set target_volume_g) or by time (program_type "timed", set target_time_s). One machine can have a mix of both.

Input parameters:

- `description` (string|null)
- `machine_id` (integer, required)
- `program_number` (integer, required): Program number / button index (e.g. 1 or 2)
- `program_type` (string): Cutoff method: "volumetric" (weight) or "timed" (duration). Defaults to volumetric.
- `target_time_s` (number|null): Target shot duration cutoff in seconds (required for timed programs)
- `target_volume_g` (number|null): Target yield cutoff in grams (required for volumetric programs)
- `volume_source` (string): Confidence in the stored cutoff value, for either type

Output parameters:

- `message` (string)
- `program_id` (integer)
- `status` (string)

### `register_coffee` (~739 tokens)

Register a coffee

Register a coffee that is NOT yet in list_beans, together with its first bag, and make it the active coffee. The coffee is the roaster's product (roaster, origins, variety, process, roast level, roasting type, cupping score, aromatics, roaster notes, rest window); the bag is this purchase (roast date, weight, price, state). For another bag of a coffee already on file call register_bag instead — it keeps the recipes and notes. Returns bean_id and the first bag's bag_id.

Input parameters:

- `acidity` (string): Free text; roasters usually say low, medium or high
- `arabica_pct` (number): Percent arabica, 100 for a pure arabica; the rest robusta
- `archived` (integer): 1 if archived, 0 otherwise
- `aromatics` (string)
- `attachments` (string): JSON or comma-separated list of attachments
- `bag_notes` (string)
- `bag_weight_g` (number): Bag weight in grams
- `bean_mix` (string): E.g. blend details
- `best_by_date` (string): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `body` (string): Free text; roasters usually say low, medium or high
- `buy_date` (string): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `co2e_kg` (number)
- `cost` (number)
- `cupping_points` (number)
- `currency` (string)
- `decaffeinated` (integer): 1 if decaf, 0 if regular
- `dial_category` (string): Dialing behavior class: classic = medium/traditional espresso roasts (chocolate/nut, balanced); dark = genuinely dark/roasty; the light categories cover Nordic and ultra-light styles.
- `ean` (string)
- `favourite` (integer): 1 if favourite, 0 otherwise
- `finished` (integer): 1 if finished, 0 otherwise
- `frozen_at` (string): Calendar day the bag went into the freezer, YYYY-MM-DD — a day, not a timestamp
- `frozen_note` (string)
- `frozen_storage` (string)
- `name` (string, required)
- `notes` (string): The coffee's own description — the roaster's tasting notes, the dialing approach that worked. Per bag notes go in bag_notes.
- `opened_date` (string): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `origin` (string)
- `origins` (array): List of bean origin details
- `process_type` (string, required)
- `qr_code` (string)
- `rating` (integer)
- `rest_window_days_max` (integer)
- `rest_window_days_min` (integer)
- `roast_custom` (string)
- `roast_date` (string, required): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `roast_level` (string, required)
- `roast_range` (string)
- `roaster` (string)
- `roasting_type` (string)
- `state` (string)
- `storage` (string)
- `sweetness` (string): Free text; roasters usually say low, medium or high
- `unfrozen_at` (string): Calendar day the bag came out, YYYY-MM-DD — a day, not a timestamp
- `url` (string)
- `variety` (string)

Output parameters:

- `bag_id` (integer)
- `bean_id` (integer)
- `message` (string)
- `status` (string)

### `set_active` (~177 tokens)

Set active equipment

Switch the active bean, grinder or machine for this account. The numbers come from list_beans, list_grinders and list_machines. Registering something already makes it active, so use this to switch back to something that exists, not after register_coffee.

Input parameters:

- `bean_id` (integer|null): This account's own bean number, as returned by list_beans. Never guess one; null = leave unchanged
- `grinder_id` (integer|null): This account's own grinder number, as returned by list_grinders. Never guess one; null = leave unchanged
- `machine_id` (integer|null): This account's own machine number, as returned by list_machines. Never guess one; null = leave unchanged
- `program_id` (integer|null): A program number from the active machine's list. null = leave unchanged

Output parameters:

- `message` (string)
- `status` (string)

### `update_bean` (~154 tokens)

Update a coffee

Update a coffee's own fields (roaster, origins, roast level, rest window, notes, rating…). Bag-shaped fields sent here (state, roast_date, bag_weight_g, grams_remaining, cost…) land on the coffee's CURRENT bag — use update_bag when it has more than one. Changing dial_category changes what the engine advises (G5, C10), so say why in the optional note.

Input parameters:

- `bean_id` (integer, required)
- `fields` (object, required)
- `reason` (string): Optional free-text note, appended as an ordinary line to the coffee's notes — or to the current bag's bag_notes when the call changed only bag fields. Omit it and nothing is written.

Output parameters:

- `message` (string)
- `status` (string)

### `get_dial_state` (~27 tokens)

Get current dial state

Retrieve current dialing state, active context, recent shots, recommendations, and locked recipes.

Output parameters:

- `active_coffee` (object)
- `active_grinder` (object)
- `active_machine` (object)
- `active_program` (null)
- `locked_recipe` (object)
- `recent_recommendations` (array)
- `recent_shots` (array)

### `log_shot` (~773 tokens)

Log a shot

Log an espresso or alternative shot/brew attempt. Uses the active context (bean/grinder/machine/program) unless overridden via bean_id/grinder_id/machine_id/program_id — ALWAYS pass bean_id explicitly when the user names a specific coffee, so the shot cannot land on the wrong bag. Backdate with pulled_at when the shot happened earlier. When the user reports taste (bitter, sour, harsh, hollow…), include matching sensory_tags — the diagnosis engine reads tags and metrics, not free-text flavor_notes. When the user tasted the shot and reports it as GOOD/clean (no defects), pass tasted=1 with no sensory_tags — otherwise a tag-less, rating-less shot is filed taste-pending as if never tasted.

Input parameters:

- `bag_id` (integer|null): Which bag of the coffee the shot came from; defaults to its current (open) bag. Bag numbers are on list_beans' bags[]
- `bean_id` (integer|null): Override: log against this bean instead of the active one (null = active)
- `best_brew` (integer): 1 if marked as best brew, 0 otherwise
- `beverage_g` (number): Yield mass excluding cup/vessel weight in grams
- `bloom_time_s` (number): Pre-wetting or bloom duration in seconds
- `data_confidence` (string): measured = weighed/timed live; recalled = from memory; estimated = a best guess (e.g. missed the timer — "~25s")
- `dose_g` (number, required)
- `drink_intent` (string)
- `favourite` (integer): 1 if favourite, 0 otherwise
- `finish_action` (string, required)
- `first_drip_time_s` (number): Time to first drip in seconds
- `flavor_notes` (string)
- `flow_profile` (string): Opaque flow profile data (JSON/TEXT)
- `grinder_id` (integer|null): Override: grinder used, if not the active one (null = active)
- `machine_id` (integer|null): Override: machine used, if not the active one (null = active)
- `method_tools` (string): JSON representation of method tools used (e.g., paper filters, screen)
- `observations` (object)
- `pressure_profile` (string): Pressure profile description or values
- `program_id` (integer|null): Override: machine program used, if not the active one (null = active)
- `pulled_at` (string|null): When the shot was actually pulled (ISO 8601 or "YYYY-MM-DD HH:MM:SS"), for backdated entries. Defaults to now (null = now). When backdating, pass the returned shot_id to diagnose_shot explicitly — th…
- `rating` (integer)
- `sensory_tags` (array)
- `tasted` (integer): 1 = the shot was tasted at log time. The explicit way to record a CLEAN tasting: sensory tags all describe defects, so a good shot has none — without this flag (or a rating) it would be filed taste-p…
- `tds` (number): Total Dissolved Solids percentage (e.g. 9.1 or 1.35)
- `temp_taste` (string)
- `temperature_c` (number): Brew temperature in Celsius
- `time_s` (number, required)
- `verdict` (string)
- `vessel_name` (string): Cup/vessel name
- `vessel_weight_g` (number): Cup/vessel weight in grams
- `water_id` (integer): Optional references to waters formulation
- `yield_g` (number, required)

Output parameters:

- `message` (string)
- `shot_id` (integer)
- `status` (string)

### `lock_recipe` (~41 tokens)

Lock a recipe

Lock a successful shot as the reference dialing recipe for this equipment profile.

Input parameters:

- `drink_intent` (string, required)
- `from_shot_id` (integer, required)

Output parameters:

- `message` (string)
- `status` (string)

### `delete_shot` (~73 tokens)

Delete a shot

Delete a logged shot from history. Restores the bean's remaining weight (which is derived from logged doses). Hard delete — there is no undo. To fix a mistake on an otherwise-valid shot, prefer update_shot over delete-and-relog.

Input parameters:

- `shot_id` (integer, required): ID of the shot to delete

Output parameters:

- `deleted_shot_id` (integer)
- `message` (string)
- `status` (string)

### `update_shot` (~131 tokens)

Update a shot

Correct fields on an already-logged shot in place — no need to delete and re-log. Use for fixing a wrong dose/yield/time or grind label, re-filing a shot onto the right bean (bean_id), backfilling rating/tasting notes, or fixing the timestamp (pulled_at). Changing grind_label re-derives the numeric grind position from the shot's grinder; changing yield/time/dose/tds keeps flow rate and extraction yield consistent automatically.

Input parameters:

- `fields` (object, required): Only the fields to change
- `shot_id` (integer, required): ID of the shot to correct

Output parameters:

- `message` (string)
- `shot_id` (integer)
- `status` (string)
- `updated_fields` (array)

### `list_recipes` (~98 tokens)

List locked recipes

List recipes (all or filtered by equipment and status). The `id` on each row is the number this account knows that record by, counting from 1 — safe to show, and what other tools expect back.

Input parameters:

- `bean_id` (integer)
- `grinder_id` (integer)
- `machine_id` (integer)
- `status` (string): Filter by status: current, archived, or all. Defaults to current.

Output parameters:

- `recipes` (array)

### `get_stats` (~42 tokens)

Get statistics

Get compact flat usage stats for a grinder, machine, or bean.

Input parameters:

- `id` (integer, required): The entity ID
- `scope` (string, required): The stats scope

Output parameters:

- `beans_consumed` (integer)
- `brews` (integer)
- `effective_age` (integer)
- `grams_consumed` (integer)
- `grams_ground` (integer)
- `grams_remaining` (integer)
- `last_bean` (string)
- `last_grind_setting` (string)
- `last_used` (string)

### `list_grinders` (~74 tokens)

List grinders

List grinders registered for the account, with status filter. The `id` on each row is the number this account knows that record by, counting from 1 — safe to show, and what other tools expect back.

Input parameters:

- `status` (string): Filter by status: current, archived, or all. Defaults to current.

Output parameters:

- `grinders` (array)

### `list_machines` (~74 tokens)

List espresso machines

List machines registered for the account, with status filter. The `id` on each row is the number this account knows that record by, counting from 1 — safe to show, and what other tools expect back.

Input parameters:

- `status` (string): Filter by status: current, archived, or all. Defaults to current.

Output parameters:

- `machines` (array)

### `list_beans` (~127 tokens)

List coffees

List the coffees registered for the account, with status filter. Each coffee carries its bags[] (every purchase, with its own freshness and grams left) and current_bag_id; the row's top-level roast_date, state, grams_remaining and age fields are the current bag's. The `id` on each row is the number this account knows that coffee by, counting from 1 — safe to show, and what other tools expect back; bag ids are a separate series.

Input parameters:

- `status` (string): Filter by status: current, archived, or all. Defaults to current.

Output parameters:

- `beans` (array)

### `grinder_math` (~47 tokens)

Grinder math

Determine steps/clicks difference and directions between setting labels (C3).

Input parameters:

- `from_label` (string, required)
- `grinder_id` (integer, required)
- `to_label` (string, required)

Output parameters:

- `burr_gap_travel_microns` (integer)
- `direction` (string)
- `relative_coarseness_note` (string)
- `step_unit` (string)
- `steps` (integer)

### `compute_age` (~73 tokens)

Compute coffee age

Compute a bag's age in days off roast and its resting/staling verdict — the coffee's current bag by default, or the bag named.

Input parameters:

- `bag_id` (integer|null): A bag of that coffee (from list_beans' bags[]); null = its current bag
- `bean_id` (integer, required)

Output parameters:

- `age_days` (integer)
- `bag_id` (integer)
- `bean_id` (integer)
- `days_off_roast` (integer)
- `days_since_opened` (null)
- `effective_age_days` (integer)
- `frozen_days_excluded` (integer)
- `grams_remaining` (null)
- `rest_window` (string)
- `roast_date` (string)
- `verdict` (string)
- `warnings` (array)

### `diagnose_shot` (~149 tokens)

Diagnose a shot

Evaluate shot metrics to provide ranked hypotheses (C6) and warn on flip-flops (G2) or fatigue (G6). Resolves the SHOT's own bean — age computed at the shot's pulled_at — never the active profile, and echoes it as bean_context, so diagnosing an older or differently-filed shot is always safe. The engine reads metrics and sensory tags — NOT free-text notes — so make sure taste feedback is recorded as sensory_tags on the shot (via log_shot or update_shot) before diagnosing; otherwise an in-range shot that tastes bad will come back "balanced".

Input parameters:

- `shot_id` (integer): Optional shot ID; defaults to last pulled shot.

Output parameters:

- `bean_context` (object)
- `category` (string)
- `facts` (array)
- `hypotheses` (array)
- `kb_version` (string)
- `one_variable_only` (boolean)
- `warnings` (array)

### `suggest_next_step` (~28 tokens)

Suggest the next step

Retrieve the single next experiment step from the reasoning engine.

Input parameters:

- `bean_id` (integer, required)

Output parameters:

- `category` (string)
- `next_step` (string)
- `warnings` (array)

### `log_recommendation` (~72 tokens)

Log a recommendation

Log a recommended dialing change to allow contradiction/oscillation checking (G2).

Input parameters:

- `based_on_shot` (integer)
- `cited_rules` (array)
- `confidence` (string, required)
- `direction` (string, required)
- `lever` (string, required)
- `rationale` (string, required)

Output parameters:

- `message` (string)
- `status` (string)

### `get_rule` (~47 tokens)

Get a dialing rule

Retrieve the detailed text of a specific rule from the knowledge base by its rule ID.

Input parameters:

- `rule_id` (string, required): The ID of the rule to fetch, e.g. CAT.DARK

Output parameters:

- `rule_id` (string)
- `text` (string)

### `get_kb_version` (~19 tokens)

Get knowledge base version

Retrieve the current version of the knowledge base.

Output parameters:

- `kb_version` (string)

### `kb_changelog` (~23 tokens)

Knowledge base changelog

Retrieve the changelog showing updates and version differences for the knowledge base.

Output parameters:

- `changelog` (string)

### `diagnose_preview` (~305 tokens)

Preview a diagnosis

Sandbox-only diagnosis, writes nothing (no verdict, no recommendation-trail entry). Two modes: pass shot_id to dry-run a LOGGED shot (optionally overriding its sensory_tags — the "what would this read as?" preview; the shot's own bean and its age at pulled_at are used), or pass the full metric set (bean_id, grinder_id, machine_id, grind_label, dose_g, yield_g, time_s, source) for a hypothetical shot. Identical output shape to diagnose_shot, including bean_context.

Input parameters:

- `bean_id` (integer): Coffee bean ID (must belong to this account)
- `dose_g` (number): Dose in grams
- `grind_label` (string): Grinder setting label, e.g. "1.1.3"
- `grinder_id` (integer): Grinder ID (must belong to this account)
- `machine_id` (integer): Machine ID (must belong to this account)
- `sensory_tags` (array): Sensory observations, e.g. ["sour","bitter"]. With shot_id: replaces the stored tags for this preview (omit to use stored; [] = none).
- `shot_id` (integer): Preview a logged shot by ID (dry-run; ignores the metric params below)
- `source` (string): Grinder position source — affects G1 warning (raw mode only)
- `time_s` (number): Extraction time in seconds
- `yield_g` (number): Yield in grams

Output parameters:

- `bean_context` (object)
- `category` (string)
- `facts` (array)
- `hypotheses` (array)
- `kb_version` (string)
- `one_variable_only` (boolean)
- `warnings` (array)

### `list_shots` (~92 tokens)

List shots

List shot history with support for pagination and filtering. Every shot carries a derived taste_pending flag (1 = logged with no sensory tags, no rating, and no tasted flip — the tasting is still owed and can be backfilled with update_shot).

Input parameters:

- `filters` (object)
- `limit` (integer): Number of records to return (1-500)
- `offset` (integer): Offset for pagination

Output parameters:

- `shots` (array)
- `total` (integer)

### `register_bag` (~320 tokens)

Register a bag

Register another bag of a coffee that is already in list_beans — the same roaster's product, bought again. It keeps the coffee's recipes, notes and history; only the purchase facts (roast date, weight, price, state) are new. Does not change the active coffee. Returns a bag_id: bag numbers are their own series, separate from bean numbers. For a coffee that is not in list_beans yet, call register_coffee instead.

Input parameters:

- `bag_notes` (string): Notes about THIS bag (a batch note, where it was bought). The coffee's own description lives on the coffee, in notes.
- `bag_weight_g` (number): Bag weight in grams
- `bean_id` (integer, required): This account's own coffee number, from list_beans. Never guess one.
- `best_by_date` (string): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `buy_date` (string): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `cost` (number)
- `currency` (string)
- `ean` (string)
- `opened_date` (string): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `qr_code` (string)
- `roast_date` (string, required): Calendar day in YYYY-MM-DD format — a day, not a timestamp
- `state` (string): Defaults to sealed; the first log_shot against it opens it
- `storage` (string)

Output parameters:

- `bag_id` (integer)
- `bean_id` (integer)
- `message` (string)
- `status` (string)

### `update_bag` (~146 tokens)

Update a bag

Change bag-level facts on one bag of a coffee: open, seal, freeze, thaw or finish it, correct its roast date, weight, grams left or price. Bag numbers come from the bags[] on list_beans (or current_bag_id). For the coffee itself — roaster, origin, roast level, rest window, notes — use update_bean.

Input parameters:

- `bag_id` (integer, required): This account's own bag number, from list_beans' bags[]. Never guess one.
- `fields` (object, required)
- `reason` (string): Optional free-text note, appended to this bag's notes as an ordinary line. Omit it and nothing is written.

Output parameters:

- `message` (string)
- `status` (string)

### `merge_beans` (~175 tokens)

Merge two coffees

Fold one coffee into another when the same coffee was registered twice. Every bag, shot, recipe and recommendation of from_bean_id moves to into_bean_id; the active coffee follows if it was the one merged away; origins move only if the target has none. Where both hold a locked recipe for the same grinder, machine, program and drink, the newer lock wins and the older is deleted. The source coffee is archived, never deleted. Irreversible — confirm both numbers with the user first (list_beans shows them).

Input parameters:

- `from_bean_id` (integer, required): The duplicate: the coffee number that will be emptied and archived
- `into_bean_id` (integer, required): The coffee number that keeps everything
- `reason` (string): Optional note, recorded on the surviving coffee's notes with the merge

Output parameters:

- `active_followed` (boolean)
- `into_bean_id` (integer)
- `message` (string)
- `moved` (object)
- `replaced_recipes` (integer)
- `status` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-shotpulled-shotpulled/mcp#diagnostics

## Score history

- 2026-09-21: 85
- 2026-09-20: 85
- 2026-09-19: 84
- 2026-09-18: 84
- 2026-09-17: 83
- 2026-09-16: 83
- 2026-09-15: 82
- 2026-09-14: 82
- 2026-09-13: 81
- 2026-09-12: 81
- 2026-09-11: 81
- 2026-09-10: 80
- 2026-09-09: 80
- 2026-09-08: 79
- 2026-09-07: 79
- 2026-09-06: 78
- 2026-09-05: 78
- 2026-09-04: 77

## Common questions

### What is the ShotPulled MCP server?

ShotPulled is an MCP server listed in the public MCP registry as com.shotpulled/shotpulled. Espresso dialing: log a shot, say how it tasted, get one change in your grinder's own clicks. This page covers its hosted endpoint (https://mcp.shotpulled.com/mcp).

### Is the ShotPulled MCP server safe to use?

ShotPulled scores 85 out of 100 on VerifyMCP. 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 ShotPulled MCP server expose?

ShotPulled exposes 41 tools: register_grinder, set_grinder_position, register_machine, set_equipment_archived, update_grinder, and 36 more. Their descriptions and schemas cost roughly 7,014 tokens of context every time the server is loaded.

### Does the ShotPulled MCP server require authentication?

Yes. ShotPulled asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the ShotPulled MCP server still maintained?

ShotPulled is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.shotpulled.com/mcp
- Website: https://shotpulled.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-shotpulled-shotpulled/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-shotpulled-shotpulled/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-shotpulled-shotpulled/mcp