fieldwork-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fieldwork-mcp Who owes me money?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fieldwork MCP
Ask your pest control business questions in plain English.
Works with Claude, Cursor, Codex, and other AI apps that support MCP.
“How many customers do I have?”
“Who owes me money?”
“How much Alpine did we use this week?”
“Who did the most jobs?”
Your AI asks Fieldwork. You get a clear answer.
Read-only — it can’t change jobs, charge cards, or edit customers.
Site: landing/index.html (Relay home) · landing/fieldwork.html (Ask Fieldwork) · Roadmap: ROADMAP.md
Who this is for
Pest and lawn-care owners who run Fieldwork and want answers without digging through reports.
Related MCP server: BackCrew Housecall Pro MCP Server
Why can’t they just ask Claude or Cursor to set it up?
Often they can — if they’re already in Cursor or Claude Code with this project open, say:
Set up Fieldwork MCP for me. I’ll paste my API key into
.env.
The agent can create the venv, write MCP config, and wire the launcher.
You still need to get the API key yourself (it’s your Fieldwork password-equivalent).
Don’t paste the key into a random chat if you can drop it straight into .env.
When a copy-paste snippet still helps
You’re on the website and don’t have an agent in the folder yet
You’re on Claude Desktop, which doesn’t edit your disk the same way
Someone else is setting up a machine without opening this repo
The endgame (see Roadmap) is a one-line remote URL + login, like LandingFolio — no Terminal, no JSON.
What you can ask
Customers
How many customers do I have?
Do I have a customer named ___?
Money
Who owes me money?
How much did we make this month?
How is business doing?
Product
How much product was used?
What chemicals do we carry?
Schedule, routes & technicians
What’s on the schedule this week?
Who are my technicians?
How are my routes doing?
Who did the most jobs?
Bonus prompt: monday_morning_briefing — one bundled ops snapshot.
Quick start
1. Get your Fieldwork API key
Easiest path (in the Fieldwork app):
Open your user (or an API Integration user)
Open the Integration tab and copy the API Key
Help: Fieldwork APIs
2. Install
git clone https://github.com/daisydaines/fieldwork-mcp.git
cd fieldwork-mcp
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .
cp .env.example .env
# put FIELDWORK_API_KEY=... in .env3. Connect your AI app
Cursor — ~/.cursor/mcp.json:
{
"mcpServers": {
"fieldwork": {
"command": "/ABS/PATH/TO/fieldwork-mcp/scripts/run_mcp.sh"
}
}
}Claude Desktop — same JSON in~/Library/Application Support/Claude/claude_desktop_config.json
Claude Code:
claude mcp add fieldwork -- /ABS/PATH/TO/fieldwork-mcp/scripts/run_mcp.shCodex — add a stdio MCP server pointing at scripts/run_mcp.sh (same idea as Cursor).
Then restart the app and ask: How many customers do I have?
Hosted connect (no Dropbox-style OAuth)
Fieldwork does not offer a third-party OAuth login popup. Closest path:
./scripts/run_mcp_http.sh
# open http://127.0.0.1:8000/connectPaste your API key once. You get a bearer token and a one-line snippet for Claude / Cursor / Codex.
Also serves the Relay landing at /.
URL | What |
| Landing |
| Paste API key → connect token |
| Streamable HTTP MCP ( |
For a shared deploy, set FIELDWORK_VAULT_SECRET (required) and FIELDWORK_PUBLIC_BASE_URL
(e.g. https://mcp.example.com). See Dockerfile. Keep FIELDWORK_MCP_ALLOW_ENV_FALLBACK=0.
Safety
Can do | Cannot do |
Read customers, jobs, invoices, usage | Create or edit customers |
Summarize routes & techs | Cancel or reschedule jobs |
Report product used on jobs | Take payments or change prices |
Tools are annotated readOnlyHint. The HTTP client refuses non-GET requests.
For builders
pip install -e ".[dev]"
pytest
ruff check src tests
./scripts/run_mcp.sh # stdio
./scripts/run_mcp_http.sh # streamable-httpAuth to Fieldwork: api-key header (default).
Unofficial. Not affiliated with Fieldwork / Anstar Products.
License
MIT — see LICENSE.
Available Tools
28 toolsfind_customerARead-onlyIdempotent
Answer: "Do I have a customer named ___?", "Find customer Smith"
Search customers by name or other Fieldwork search text.
Inputs: query (required), limit. Returns: result
get_customerARead-onlyIdempotent
Fetch one customer by ID.
Inputs: customer_id (required). Returns: result
get_financial_summaryARead-onlyIdempotent
Financial summary report for a date range (ISO dates, e.g. 2026-01-01).
Inputs: end_date (required), start_date (required), branch_id. Returns: result
get_invoiceARead-onlyIdempotent
Fetch one invoice by ID.
Inputs: invoice_id (required). Returns: result
get_operations_summaryBRead-onlyIdempotent
Operations summary report for a date range (ISO dates, e.g. 2026-01-01).
Inputs: end_date (required), start_date (required), branch_id, service_route_id. Returns: result
get_work_orderBRead-onlyIdempotent
Fetch one work order. plain=True uses Fieldwork's show_plain endpoint.
Inputs: work_order_id (required), plain. Returns: result
get_work_order_service_reportBRead-onlyIdempotent
Fetch the service report for a work order (often includes treatment details).
Inputs: work_order_id (required). Returns: result
health_checkARead-onlyIdempotent
Verify Fieldwork credentials. Run this first if other tools fail.
Calls GET /v3.1/profile. On success returns a small redacted profile summary.
Inputs: no named parameters. Returns: result
how_are_my_routes_doingCRead-onlyIdempotent
Answer: "How are my routes doing?", "Which route is busiest?"
Jobs (and completions) per service route for a date range.
Inputs: days, end_date, start_date. Returns: result
how_is_business_doingARead-onlyIdempotent
Answer: "How is business doing?", "How many jobs did we finish this month?"
Plain-English operations snapshot (jobs completed, cancelled, production value).
Inputs: days, end_date, start_date. Returns: result
how_many_customersARead-onlyIdempotent
Answer: "How many customers do I have?", "What's my customer count?"
Counts every customer in Fieldwork and breaks down by status. Prefer this over search_customers for total-count questions.
Inputs: no named parameters. Returns: result
how_much_moneyBRead-onlyIdempotent
Answer: "How much money did we make?", "What's our revenue this month?"
Financial summary snapshot for a date range.
Inputs: days, end_date, start_date. Returns: result
how_much_product_was_usedARead-onlyIdempotent
Answer: "How much product was used?", "What chemicals did we use this month?"
Totals logged material/chemical usage from completed jobs.
Args: days: Look back this many days ending today (default 30). Ignored if start_date set. start_date: Optional YYYY-MM-DD range start. end_date: Optional YYYY-MM-DD range end (default today). material_name: Optional filter, e.g. "Alpine" or "Taurus".
Inputs: days, end_date, start_date, material_name. Returns: result
list_calendar_work_ordersBRead-onlyIdempotent
List calendar work orders for a date range (YYYY-MM-DD).
Inputs: end_date, start_date, only_workpool, with_workpool. Returns: result
list_customer_notesBRead-onlyIdempotent
List notes on a customer (read-only).
Inputs: customer_id (required), page, per_page, body_contains. Returns: result
list_materialsARead-onlyIdempotent
List materials/chemicals in the Fieldwork catalog (name, EPA #, etc.).
Inputs: no named parameters. Returns: result
list_service_routesBRead-onlyIdempotent
List service routes (technician routes).
Inputs: no named parameters. Returns: result
list_servicesARead-onlyIdempotent
List service types configured in Fieldwork.
Inputs: no named parameters. Returns: result
list_work_order_unit_recordsARead-onlyIdempotent
List unit records for a work order.
This is the main read path for material usage: usages are nested on unit records in Fieldwork's API (there is no standalone material-usages index).
Inputs: work_order_id (required), page, per_page. Returns: result
search_customer_by_phoneARead-onlyIdempotent
Find a customer by phone number.
Inputs: phone (required). Returns: result
search_customersARead-onlyIdempotent
Search Fieldwork customers.
Args: query: Free-text search (name, email, account bits — whatever Fieldwork indexes). page: Page number (default 1). per_page: Page size (default 25; keep modest). start_date: Optional YYYY-MM-DD (or MM/DD/YYYY) lower bound. end_date: Optional YYYY-MM-DD (or MM/DD/YYYY) upper bound. customer_status: Optional status filter. postal_code: Optional postal/ZIP filter. updated_after: Optional updated-after date (YYYY-MM-DD or ISO-8601).
Inputs: page, query, end_date, per_page, +4 more. Returns: result
search_invoicesCRead-onlyIdempotent
Search invoices.
Inputs: page, query, per_page, customer_id, +1 more. Returns: result
search_work_ordersARead-onlyIdempotent
Search work orders / service appointments.
Prefer passing start_date and end_date (YYYY-MM-DD) to keep results small.
Inputs: page, query, end_date, per_page, +3 more. Returns: result
what_products_do_we_carryARead-onlyIdempotent
Answer: "What products do we carry?", "What chemicals are in our catalog?"
Lists materials/products configured in Fieldwork.
Inputs: no named parameters. Returns: result
whats_on_the_scheduleBRead-onlyIdempotent
Answer: "What's on the schedule?", "How many jobs this week?"
Work-order overview for a date range (default 7 days).
Inputs: days, end_date, start_date. Returns: result
who_are_my_techniciansARead-onlyIdempotent
Answer: "Who are my technicians?", "Who's on my team?", "What routes do I have?"
Lists technicians, office users, and service routes (no secrets).
Inputs: no named parameters. Returns: result
who_did_the_most_jobsARead-onlyIdempotent
Answer: "Who did the most jobs?", "Who's my top technician?"
Ranks technicians/routes by completed jobs for a date range.
Inputs: days, end_date, start_date. Returns: result
who_owes_me_moneyARead-onlyIdempotent
Answer: "Who owes me money?", "What invoices are unpaid?", "How's my AR?"
Totals open invoice balances and lists top customers by amount due.
Inputs: top_n. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 28 tools
Many tools appear to serve the same purpose, such as what_products_do_we_carry and list_materials, how_much_money and get_financial_summary, and whats_on_the_schedule and list_calendar_work_orders. The natural-language question tools overlap heavily with the structured API tools, creating ambiguity about which to use. An agent would struggle to pick the right tool consistently.
The tool names mix full-sentence questions (how_many_customers, who_owes_me_money) with standard verb_noun patterns (get_invoice, list_materials, search_customers). There is no consistent convention; even similar actions use different verbs such as find_customer vs search_customers. This inconsistency makes it harder to predict tool names.
With 28 tools, the server exceeds the 25-tool threshold for 'too many' and includes many near-duplicate question-answering and structured-data tools. The count feels inflated by redundancy rather than justified by distinct functionality.
The server provides broad read-only coverage across customers, work orders, invoices, materials, routes, technicians, and summaries. It lacks any create/update/delete operations, which may be acceptable for an analytics assistant, but there are minor gaps such as no all-invoices list endpoint and no single-technician fetch.
Maintenance
Related MCP Connectors
Ask your Quickbase apps in plain language. Read-only by default; writes need human approval.
Ask your AI about your Airbnb and VRBO listings, bookings, guest messages and reviews. Read-only.
Ask your accounts-receivable portfolio anything. Read-only, scoped to your account.
Ask about Loop Voice AI calls, texts, campaigns and revenue. Read-only, OAuth sign-in.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceProvides structured, read-mostly access to small-business back-office data including customers, invoices, and account notes, allowing Claude to query overdue invoices, revenue summaries, and more.MIT
- AlicenseBqualityDmaintenanceConnects AI assistants to Housecall Pro to look up and manage customers, jobs, invoices, and more through natural language. Operates in read-only mode by default with optional write capabilities.301MIT
- AlicenseAqualityDmaintenanceEnables AI assistants like Claude to read and optionally write data in FieldRoutes (formerly PestRoutes) using plain English, with read-only mode by default and granular safety profiles.39MIT
- AlicenseBqualityDmaintenanceRead-only MCP server that lets Claude, ChatGPT, or Cursor answer pest-business questions from your GorillaDesk account in plain English—looks up customers, invoices, schedules, and technicians without creating or changing data.19MIT