Skip to main content
Glama

stretch-mcp

An MCP server that gives an operations agent governed access to the systems that run STRETCH Yoga, an independent studio at 180 E. Pender St in Vancouver.

The agent answers "what is going on at the studio today?" from live data, and it can ask to change a booking, but it cannot change one by itself. A person approves every write in chat first.

Why it exists

A studio this size runs on a booking system, a staff scheduler, a shift log and a group chat, and the owner is the integration layer between them. Before this server, each agent skill carried its own API recipes and credentials. This puts one typed, audited tool layer in front of those systems so that any MCP client (Hermes, Claude Code, Claude Desktop) gets the same tools with the same rules.

Related MCP server: ops-platform

Tools

Tool

What it returns

Source

daily_brief

The day's classes and rentals, who is on the desk, coverage gaps for the week, yesterday's sales, shift log notes, writes awaiting approval

all of the below

class_schedule

Classes with teacher, bookings and capacity

Momence API

class_roster

Who is booked and checked in (first name and last initial only)

Momence API

room_rentals

Room rentals and private bookings

Momence API

front_desk_shifts

Who is scheduled on the front desk

iCal feed from the staff scheduler (Rippling)

coverage_gaps

Classes and rentals with nobody assigned to the desk

Momence + scheduler

sales_summary

A day's sales by category and payment method, with the same weekday a week earlier

Momence report API

shift_log

What staff flagged at end of shift: broken things, supplies, incidents

Formbricks

propose_free_booking, propose_cancel_booking

A pending action id. Nothing changes

execute_action

Runs a proposed write only after a person approved it

Matrix + Momence

How writes are approved

agent                     stretch-mcp                    Matrix room            Momence
  | propose_cancel_booking      |                             |                    |
  |---------------------------->| validate against roster     |                    |
  |                             | post "Approval needed A-1f" |                    |
  |                             |---------------------------->|                    |
  |        action id, pending   |                             |  owner reacts ✅   |
  |<----------------------------|                             |                    |
  | execute_action(A-1f)        |                             |                    |
  |---------------------------->| who reacted to that event?  |                    |
  |                             |---------------------------->|                    |
  |                             | approver did: run the write |                    |
  |                             |------------------------------------------------->|
  |             status: done    |                             |                    |
  |<----------------------------|                             |                    |

The design points:

  • The approval check is made against the homeserver, not against anything the agent passes in. The agent holds no token or code that could approve its own proposal.

  • A proposal is validated when it is made (the booking has to be on that class's roster), and the summary a person approves is written by the server, not by the model.

  • Executing is idempotent. A finished action returns its stored result and never runs twice.

  • Proposals expire after 24 hours. A ❌ rejects.

  • With no Matrix settings, proposals are recorded and can never be executed.

Tracing

Every tool call appends one line to audit.jsonl in the state directory: timestamp, tool, arguments, duration and success. Results are not logged, so the trace holds no customer data. Tool failures come back to the agent as {"ok": false, "error": ...} rather than as a stack trace, and daily_brief reports a failed section under unavailable instead of failing as a whole.

Run it

git clone https://github.com/boydthomson/stretch-mcp && cd stretch-mcp
cp .env.example .env    # fill in; nothing secret is committed
uv sync
uv run pytest
uv run stretch-mcp      # stdio

Client config (Hermes config.yaml, same shape for other clients):

mcp_servers:
  stretch:
    command: /path/to/stretch-mcp/.venv/bin/stretch-mcp
    env:
      STRETCH_MCP_ENV: /path/to/stretch-mcp/.env

Layout

stretch_mcp/
  server.py     tool definitions (MCP Python SDK v2)
  momence.py    booking system client
  frontdesk.py  iCal shift feed parser
  coverage.py   pure coverage logic, unit tested
  shiftlog.py   Formbricks responses
  approvals.py  propose / approve / execute state machine
  audit.py      JSONL trace
profile/        the Hermes agent profile that uses this server
tests/

Known limits

  • The gate governs the tool path. An agent that also has a shell on the same host and can read the server's .env could call the booking API directly. The stretch-ops profile in profile/ therefore runs without terminal or file tools. Moving the server to its own host behind HTTP is the next step.

  • Recurring iCal events are not expanded. Rippling publishes one event per shift.

  • Sales totals include tax and come from the report API, which allows 100 runs a day; finished days are cached.

  • There is no evaluation harness yet. The plan is a set of questions with known answers, scored nightly against the trace.

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to retrieve customer, order, ticket, policy, and agreement information, and to prepare or execute state-changing support actions like escalations and follow-ups with confirmation and access control.
      -
    • A
      license
      A
      quality
      C
      maintenance
      Lets an AI assistant read and write business records in plain language, including looking up people, creating and updating tasks, logging time, and pulling utilization reports through a synthetic ops platform or an optional ClickUp adapter.
      8
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables Claude to manage a service business front desk by searching customers, checking real-time availability, creating and canceling appointments without double-booking, and generating revenue reports from actual data.
      9
      MIT
    • A
      license
      C
      quality
      B
      maintenance
      Enables studio owners to connect their own studio API key and query an assistant about availability, bookings, clients, packages, prices and business performance. Ships 150 API-backed tools—65 read/preview operations enabled by default and 85 opt-in mutations requiring confirmation and idempotency keys—plus guided prompts for monthly reviews, finding session times and preparing booking changes.
      65
      MIT