# Practice Better MCP by usefulapi (remote · practice-better.usefulapi.io)

Read Practice Better clients, sessions, availability, services, packages, invoices and forms.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `practice-better.usefulapi.io`: 64/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-practice-better/practice-better.md), [page](https://verifymcp.io/servers/io-usefulapi-practice-better/practice-better)

## Channel facts

- Endpoint: `https://practice-better.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## 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 2026-10-17.

- **Endpoint Security**: 78/100
  - 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 enforcement could not be verified: the plaintext port redirected somewhere other than https, so enforcement is unproven.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly.
- **Schema Quality & AI Usability**: 78/100
  - 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 2365 tokens (~157/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 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 Practice Better MCP by usefulapi server?

Practice Better MCP by usefulapi is a hosted endpoint at https://practice-better.usefulapi.io/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 io-usefulapi-practice-better 'https://practice-better.usefulapi.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-usefulapi-practice-better": {
      "url": "https://practice-better.usefulapi.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-usefulapi-practice-better": {
      "type": "http",
      "url": "https://practice-better.usefulapi.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-usefulapi-practice-better]
url = "https://practice-better.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-practice-better": {
      "type": "remote",
      "url": "https://practice-better.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-practice-better --url 'https://practice-better.usefulapi.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-practice-better:
    url: "https://practice-better.usefulapi.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-usefulapi-practice-better": {
      "Transport": "http",
      "Url": "https://practice-better.usefulapi.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-usefulapi-practice-better -t streamable-http -u 'https://practice-better.usefulapi.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-usefulapi-practice-better": {
      "type": "http",
      "url": "https://practice-better.usefulapi.io/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.

### 2026-10-17 (score 64, +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.

### 2026-10-14 (score 63, +3)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] The server now declares the “prompts” capability
- [functional] First check of Schema quality: 100
- [functional] New prompt “getting_started”
- [functional] Server version: 1.0.0 → 1.1.0

### 2026-10-13 (score 60, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-12 (score 60)

First indexed and scored.

## MCP tools (15)

### `practice_better_get_account` (~60 tokens)

Get my account

The practitioner (API user) behind this connection: id, name, title, timezone, default currency, role flags and the practice (company) id and name. Settings, integrations and the bio are not returned. GET /consultant/profile.

### `practice_better_list_practitioners` (~53 tokens)

List practitioners

List the practitioners and admin users of the practice, with id, name, role flags and activation status. Use the ids to filter sessions and invoices. GET /company/administration/members.

### `practice_better_list_clients` (~284 tokens)

List clients

List client records, newest first: id, status, name, email, phone, timezone and activity dates. Date of birth, address, insurance and notes are not returned. A page holds at most 100 records. To look up one person by name or email use practice_better_find_clients. GET /consultant/records.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `child_records` (boolean): true = only sub-records (dependants), false = only primary records.
- `has_account` (boolean): true = only clients with an active Practice Better user account.
- `limit` (integer): Results per page, 1-100 (default 25).
- `modified_after` (string): ISO 8601 date-time with a timezone, e.g. 2026-10-01T00:00:00Z.
- `modified_before` (string): ISO 8601 date-time with a timezone, e.g. 2026-10-01T00:00:00Z.
- `status` (array): Only these statuses. pendingcreate = prospective client, created = added client.

### `practice_better_find_clients` (~144 tokens)

Find clients by name or email

Search client records by name, preferred name or email (case-insensitive text match). Practice Better has no search endpoint, so this reads the 500 most recent records (5 pages of 100) and filters them; `complete` says whether every record was checked. Returns at most `max_results` matches with the same fields as practice_better_list_clients. GET /consultant/records.

Input parameters:

- `max_results` (integer): Most matches to return, 1-50 (default 10).
- `query` (string, required): Text to look for in first name, last name, preferred name or email.
- `status` (array): Only these statuses.

### `practice_better_get_client` (~79 tokens)

Get client

One client record by id: status, name, preferred name, pronouns, email, phones, timezone, activity dates and tag ids. Date of birth, address, insurance, emergency contacts, notes and health history are not returned. GET /consultant/records/{recordId}.

Input parameters:

- `record_id` (string, required): Client record id.

### `practice_better_list_sessions` (~269 tokens)

List sessions (appointments)

List sessions (appointments), newest first: date, duration, service, practitioner, client (id and name), status and payment status. Booking notes and session notes are not returned. Filter by date range, practitioner, client record, service or group/1-1. GET /consultant/sessions.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `date_after` (string): Sessions on or after this date-time (ISO 8601 with timezone).
- `date_before` (string): Sessions on or before this date-time (ISO 8601 with timezone).
- `group` (boolean): true = only group sessions, false = only 1-1 sessions.
- `limit` (integer): Results per page, 1-100 (default 25).
- `practitioner_ids` (array): Only sessions of these practitioners (ids from practice_better_list_practitioners).
- `record_ids` (array): Only sessions of these client records.
- `service_ids` (array): Only sessions of these services (ids from practice_better_list_services).

### `practice_better_get_session` (~95 tokens)

Get session

One session (appointment) by id: date, duration, service, practitioner, client (id and name), location and status. Booking notes and session notes are not returned. For a group session pass record_id to see one client's view. GET /consultant/sessions/{sessionId}.

Input parameters:

- `record_id` (string): Group sessions only: the client record id.
- `session_id` (string, required): Session id.

### `practice_better_get_availability` (~183 tokens)

Get available time slots

Open booking slots of one practitioner for one service, starting on the given day: start, end and duration of each slot. It follows the practitioner's booking settings. Needs a practitioner id and a service id. GET /consultant/availability/slots.

Input parameters:

- `day` (string, required): The day to start from, ISO 8601 date-time with timezone, e.g. 2026-10-12T00:00:00Z.
- `location_id` (string): Only slots at this location.
- `package_id` (string): Only slots usable with this client package.
- `practitioner_id` (string, required): Practitioner id (practice_better_list_practitioners).
- `service_id` (string, required): Service id (practice_better_list_services).
- `type` (string): Session type: face (in person), phone or virtual.

### `practice_better_list_services` (~148 tokens)

List services

List the services (appointment types) the practice offers: id, name, duration, group or 1-1, session types and SKU. GET /consultant/services.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `limit` (integer): Results per page, 1-100 (default 25).
- `team_for` (string): Whose items: self (default), all (all team members) or other (team members except you).

### `practice_better_list_packages` (~112 tokens)

List packages

List the package definitions (bundles of sessions or programs) the practice sells: id, name and SKU. GET /consultant/packages.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `limit` (integer): Results per page, 1-100 (default 25).

### `practice_better_list_tags` (~109 tokens)

List tags

List the tags the practice uses to organize clients: id and name. A client record carries tag ids. GET /tags.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `limit` (integer): Results per page, 1-100 (default 25).

### `practice_better_list_invoices` (~217 tokens)

List invoices

List client invoices, newest first: number, date, totals, amount due and paid, payment status, client (id and name) and practitioner. Payment history and line items are not in the list; use practice_better_get_invoice. GET /consultant/payments/invoices.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `invoice_date_after` (string): Invoice date on or after this date-time.
- `invoice_date_before` (string): Invoice date on or before this date-time.
- `limit` (integer): Results per page, 1-100 (default 25).
- `payment_status` (array): Only invoices with these payment statuses.
- `practitioner_ids` (array): Only invoices of these practitioners.
- `record_ids` (array): Only invoices of these client records.

### `practice_better_get_invoice` (~65 tokens)

Get invoice

One invoice by id with its line items (date, quantity, amount, tax) and totals. Descriptions, payment history and billing contact are not returned. GET /consultant/payments/invoices/{invoiceId}.

Input parameters:

- `invoice_id` (string, required): Invoice id.

### `practice_better_list_forms` (~141 tokens)

List forms

List the form templates of the practice (intake forms, questionnaires, consent forms): id and name only. GET /consultant/forms.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `limit` (integer): Results per page, 1-100 (default 25).
- `team_for` (string): Whose items: self (default), all (all team members) or other (team members except you).

### `practice_better_list_form_requests` (~203 tokens)

List form requests

List forms sent to clients, newest first: which form, which client (id), practitioner, and whether it was started or completed, with dates. The answers are never returned. GET /consultant/formrequests.

Input parameters:

- `after_id` (string): Cursor for lists in ascending order: return items after this id. Normally use before_id.
- `before_id` (string): Cursor: pass next_page.before_id of the previous reply to get the next page (lists are newest first).
- `completed` (boolean): true = only completed requests, false = only incomplete ones.
- `created_after` (string): Created on or after this date-time.
- `created_before` (string): Created on or before this date-time.
- `limit` (integer): Results per page, 1-100 (default 25).
- `practitioner_ids` (array): Only requests of these practitioners.
- `record_ids` (array): Only requests for these client records.

## Diagnostics

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

## Score history

- 2026-10-17: 64
- 2026-10-16: 63
- 2026-10-15: 63
- 2026-10-14: 63
- 2026-10-13: 60
- 2026-10-12: 60

## Common questions

### What is the Practice Better MCP by usefulapi server?

Practice Better MCP by usefulapi is listed in the public MCP registry as io.usefulapi/practice-better. Read Practice Better clients, sessions, availability, services, packages, invoices and forms. This page covers its hosted endpoint (https://practice-better.usefulapi.io/mcp).

### Is the Practice Better MCP by usefulapi server safe to use?

Practice Better MCP by usefulapi scores 64 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 Practice Better MCP by usefulapi server expose?

Practice Better MCP by usefulapi exposes 15 tools: practice_better_get_account, practice_better_list_practitioners, practice_better_list_clients, practice_better_find_clients, practice_better_get_client, and 10 more. Their descriptions and schemas cost roughly 2,162 tokens of context every time the server is loaded.

### Does the Practice Better MCP by usefulapi server require authentication?

Yes. Practice Better MCP by usefulapi 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 Practice Better MCP by usefulapi server still maintained?

Practice Better MCP by usefulapi 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.

## Links

- Remote endpoint: https://practice-better.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Website: https://usefulapi.io/practice-better/
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-practice-better/practice-better.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-practice-better/practice-better.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-practice-better/practice-better