Knowify MCP Server

Jobs, bids, invoices and job costing in Knowify.

Server MCP Terhosting

npx add-mcp 'https://cotlet.dev/mcp/v1/knowify'

Terpasang ke Claude Code, Codex, Cursor, dan lainnya

Dokumentasi

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

Knowify API and MCP server: Let your AI agent do the billing in Knowify.

Knowify has an official MCP server, the AI Connector, and no public API (checked 27 Oct 2026). The connector answers questions about jobs, WIP, billing and labor for admins on Advanced and Enterprise; it creates and sends nothing. Cotlet runs 15 Knowify tools hosted, 9 of them writes, over MCP for agents and REST for scripts.

Jobs, bids, invoices and job costing in Knowify. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Knowify. Knowify is a trademark of its owner. If Knowify's own integrations cover what you need, use them first.

What can you automate in Knowify?

  • Draft progress invoices by percent complete
  • Add change orders and bill them
  • Send proposals out for e-signature
  • Flag phases running over budget
  • Record client checks against invoices
  • Log crew hours on a job phase

Does Knowify have an MCP server or an API?

  • The AI Connector is "available for users with admin permissions in Knowify only", in Claude, Grok and a ChatGPT plugin. Core ($99 a month billed yearly) has no connector and no Zapier.
  • Zapier has 13 actions, such as Create Contract Job, Create Client and Update Phase. None creates an invoice, proposal, change order, payment or time entry.
  • Knowify's in-app Assistant, a beta for some admins (help center, 20 Oct 2026), edits jobs, change orders and time, but "can't draft or send the invoice" and sends nothing to clients.
What you needAI ConnectorZapierCotlet
Works on Core and for non-admin usersAdvanced, admins onlyAdvanced and upYes, any plan and role
Job cost, WIP and invoicesYes, as answersSearches, no costsYes, as data
Create jobs and clientsNoYesYes
Progress invoices, change orders, paymentsNoNo actionYes, after your OK
Send a proposal or invoice to a clientNoNo actionYes, after your OK

Checked 27 Oct 2026. Sources: Getting started with the Knowify AI Connector, Knowify AI Connector, Knowify triggers and actions on Zapier, Knowify integrations, Knowify pricing, Knowify Assistant [beta]

How does Cotlet connect to Knowify?

  1. Sign in to Knowify. Use your own account in its Cotlet Cloud Browser.
  2. Choose MCP or REST. Connect your agent or create a Cotlet API key.
  3. Run your workflow. Ask your agent or send an HTTP request.

We never keep your Knowify password, and no proposal, invoice or payment record goes through until you approve it.

Connect Knowify to your agent or workflow

Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.

  1. Enable Knowify for agents. Open a Cotlet account, sign in to Knowify in its Cloud Browser with the user the agent should work as, then press Enable for agents.
  2. Add the Cotlet address. Put https://cotlet.dev/mcp/v1 into your agent as a remote MCP server or custom connector.
  3. Approve the link. Chat apps ask you to sign in to Cotlet once. Editors, n8n and scripts send an API key from the console.

https://cotlet.dev/mcp/v1 carries Knowify next to your other apps; you can keep Knowify's own AI Connector in the same agent for questions. Users count toward your Knowify plan ($29 a month each past the included ones), so most offices sign in as the bookkeeper or project manager who does the billing. Refresh the connector after enabling Knowify so the tools load.

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:
claude mcp add --transport http cotlet-knowify \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Cursor:

// ~/.cursor/mcp.json
{
  "mcpServers": {
    "cotlet-knowify": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet-knowify]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"

n8n:

MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: knowify_read

Make, Zapier:

Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: knowify_write

How to use the Knowify REST API

Create your Cotlet API key

Create a Cotlet API key with access to Knowify and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect Knowify in Cotlet and enable it for agents. Account access: Your own Knowify account (admin permissions for costs and invoicing).

Make your first Knowify API request

REST:

curl https://cotlet.dev/api/v1/knowify/jobs \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read jobs and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "knowify",
  "tool": "list_jobs",
  "result": {
    "jobs": [
      {
        "job_id": "418203",
        "name": "Maple St Remodel",
        "client": "Dana Whitfield",
        "status": "active",
        "contract_style": "fixed_price",
        "revenue": 42400,
        "cost": 22500,
        "profit": 19900
      },
      {
        "job_id": "418410",
        "name": "Riverside Dental Office",
        "client": "Riverside Dental",
        "status": "lead",
        "contract_style": "fixed_price",
        "revenue": 0,
        "cost": 0,
        "profit": 0
      }
    ]
  }
}

Returns contract jobs with client, status, revenue, cost and profit. Without a status filter it returns all open jobs, newest first.

Search matches job name, client name, address or tag. Use job_id from each item in the other tools.

limit: 1 to 100. Default: 25.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

Knowify workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestCost to date vs budget for the job and each phase, from Plan & Track. Use get_job_cost in your configured operations sheet.
MakeHTTP > Make a requestInvoices with job, client, amount, balance due and date. Use list_invoices in your configured operations sheet.
Python or Node.jsREST APITime entries from Review Time: person, job, phase, hours, billable and approval state. Use list_time_entries in your configured operations sheet.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads Knowify; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Knowify API endpoints and MCP tools

Jobs and job cost

Contract jobs with revenue, cost and profit, and cost to date against budget per phase from Plan & Track. With Advanced Permissions on, costs show only to admins and users with Unlimited Approval Authority.

  • List jobs (list_jobs, read): Contract jobs with client, contract status, revenue, cost and profitability.
  • Get job (get_job, read): One job: client, jobsite address, contract style, contract lines, change orders and phases.
  • Get job cost (get_job_cost, read): Cost to date vs budget for the job and each phase, from Plan & Track.

Clients, bids and proposals

A new job starts as a lead and turns to bidding when the proposal is saved. Only the e-signature email reaches the client, so only it asks first.

  • List clients (list_clients, read): Clients with contact email, phone and address.
  • Create client (create_client, write): Add a client to your client list.
  • Create job (create_job, write): New contract job. It starts as a lead until a proposal is saved.
  • Save proposal (save_proposal, write): Save the draft proposal (bid) of a job. The job moves to bidding. Nothing is sent.
  • Send proposal for signature (send_proposal_for_signature, write, asks first): Email the proposal to the client for e-signature. The job turns active when they sign.

Change orders and invoices

Change orders exist only on fixed price jobs and must be active to bill. A job keeps one invoicing style, percent or amount, from its first invoice on.

  • Add change order (add_change_order, write): Add a change order to a fixed price job, as a draft or active so it can be invoiced.
  • List invoices (list_invoices, read): Invoices with job, client, amount, balance due and date.
  • Create invoice (create_invoice, write, asks first): Invoice an active job by percent of progress or dollar amount per line, as a draft or finalized.
  • Send invoice (send_invoice, write, asks first): Email a finalized invoice to the client.
  • Record payment (record_payment, write, asks first): Record a full or partial client payment on an invoice.

Time

Hours go on a phase with labor enabled and land in Review Time for approval, as when a foreman enters them.

  • List time entries (list_time_entries, read): Time entries from Review Time: person, job, phase, hours, billable and approval state.
  • Log time (log_time, write): Enter hours on a job phase in the Time Tracker and submit them for review.

Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/knowify-api-mcp-server#tools

Who can see my Knowify session, and how do I revoke it?

  • What we store. The signed-in Knowify browser profile, AES-256-GCM encrypted, in Finland. No password.
  • What your agent gets. The 15 Knowify tools. Never the session cookie.
  • What the session sees. What your Knowify user sees: jobs, costs your permissions allow, invoices, time.
  • What no tool touches. Online card or ACH charges, QuickBooks records, payroll and deletes.
  • If Knowify signs you out. You sign in again in the Cloud Browser. We never type your password.
  • How to cut access. Disable for agents, reset the browser, or remove that user in Knowify.

Our site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).

Approvals, undo and mistakes

  1. Reads the contract. get_job: lines, change orders, contract style.
  2. Checks the math. Percents against earlier invoices; it stops before billing over the contract.
  3. Waits for your OK. The draft invoice shows up in your Cotlet console first.
  4. Finalizes and sends. On a second OK, to the client or the AP address you name.
ActionUndo
Create a client or jobEdit or delete it in Knowify
Save a proposalEdit it while the job is in Bidding
Make a change order activeOnly after deleting every invoice that includes it
Create an invoiceDelete the draft; a finalized one may have synced to QuickBooks
Send a proposal or invoiceNo, the client has the email
Log timeEdit or reject it in Review Time

4 of 15 tools ask first: send_proposal_for_signature, create_invoice, send_invoice and record_payment, the ones a client or your books feel. Reads, new clients and jobs, proposal drafts, change orders and time run at once. Switch the wait off per tool for a scheduled run.

AIA invoices cannot be saved as drafts in Knowify, so the draft step applies to percent and amount billing only.

MCP call:

{
  "name": "create_invoice",
  "arguments": {
    "job_id": "418203",
    "method": "percent",
    "lines": {
      "line-1": 40,
      "line-2": 40,
      "co-1": 100
    },
    "finalize": false
  }
}

REST:

curl -X POST https://cotlet.dev/api/v1/knowify/jobs/418203/invoices \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"method":"percent","lines":{"line-1":40,"line-2":40,"co-1":100},"finalize":false}'

Response:

{
  "invoice_id": "90517",
  "job_id": "418203",
  "status": "draft",
  "amount": 18400,
  "balance_due": 18400,
  "date": "2026-10-10"
}

A script or a month-end job calls the same tools over REST at /api/v1/knowify, one key, one price. A call Knowify refuses, such as invoicing a job whose contract is not active yet, costs nothing. The tools table gives the REST path of each tool.

How much does the Knowify MCP server cost?

About $24 a month for a trade contractor with about 15 active jobs, 4,120 credits. Your Knowify plan is billed as before.

JobCallsCredits
Monday report of phases over budget19 × 4760
Month-end progress invoices, 12 jobs5 × 12600
Change orders from the field2 × 6120
Bid to proposal out for signature5 × 8400
Record client checks2 × 15300
Foreman time, each workday2 × 22440
Cloud Browser, 30 days1,500
Total4,120
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • Works on Core, no Advanced upgrade needed

Knowify publishes no jobs per account; its reviewers are mostly firms of 2 to 50 people, so the job mix is our example. Core to Advanced alone is $230 a month billed yearly (knowify.com/pricing, 27 Oct 2026). Dollars at the $29 pack rate.

Knowify MCP server: official connector, Zapier or hosted

OptionWhat it doesWhere it stops
Knowify AI ConnectorOfficial MCP server at assistant.knowify.com: margins, WIP, over and underbilling, AR and AP aging, expired subcontractor documents.Answers only. Admins on Advanced or Enterprise.
Knowify AssistantAgent inside the Knowify web app: creates jobs, change orders and phases, edits and approves time.Beta for some admins. No invoices, no emails to clients, no outside agent or schedule.
Zapier MCP13 actions and 12 searches as MCP tools: jobs, clients, bills, tasks, phases.Advanced and up. No proposals, change orders, invoices, payments or time.
GitHubNo Knowify MCP server or API client found (gh search, 27 Oct 2026).Nothing to self-host: there is no public API to build one on.

If you are an admin on Advanced and want answers about WIP and margins, Knowify's own connector is free with your plan; use it. When the agent should build the pay request, send the bid or post the check, or you are on Core, that is the part Cotlet covers.

Also listed on: Odel, mcpbeat

Who runs Cotlet

Cotlet belongs to Take Group sp. z o.o., a software company registered in Poland, EU (VAT PL6342984273), in business since 2019. Its founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Write to contact@cotlet.dev about the Knowify tools.

Knowify API and MCP: questions

How do I get access?

Sign up free at https://cotlet.dev, open Knowify under Integrations in the console and sign in to Knowify in its Cloud Browser. The trial starts when you sign up; no card is asked.

How do I connect Knowify to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Knowify once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Knowify account through Cotlet, in their phone apps too.

What can ChatGPT do in Knowify?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Knowify: weekly report of job phases over budget; create a job and send the proposal for e-signature; add a change order and invoice it. You ask in plain words, and anything that reaches other people waits for your OK first.

Can my agent send an invoice without my OK?

Yes, once you switch confirmation off for send_invoice. By default each email to a client and each payment record waits for your OK. Knowify's own AI Connector is read-only for now (checked 11 Oct 2026).

Do I need admin permissions in Knowify?

Cotlet works in your own Knowify account with the permissions it already has. Knowify's AI Connector needs admin permissions to connect.

Does Knowify have webhooks?

No documented ones. Events such as New Invoice Payment, Change Order Made Active and Time Entry Approved exist only as Zapier triggers on Advanced and up. Otherwise run your agent on a schedule, for example a list_invoices pass each morning.

Can I use the AI Connector and Cotlet together?

Yes. Connect both to the same agent: Knowify's connector for questions about WIP and margins, Cotlet for invoices, proposals, change orders, payments and time.

Is the MCP server different from the REST API?

Only in how you call it. Both carry the same 15 tools, inputs and answers, under one API key and one price. Agents use MCP; scripts and HTTP steps use REST.

Is Cotlet affiliated with Knowify?

No. Cotlet is independent and not affiliated with Knowify, Inc.

Can I use the Knowify API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.