Spectora API and MCP server Let your AI agent book and chase your inspections.

Schedule inspections, add agreements and read agents and clients in Spectora. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

  • Free 7-day trial, no card
  • Unofficial, not affiliated with Spectora
Spectora logo Spectora Cloud Browser

11 tools Read and write

Request to report

What can you automate in Spectora? Use an AI agent, a workflow or a script.

  • Book inspections from requests

  • Reschedule and notify the client

  • Chase unsigned agreements

  • Add a missing agreement to a job

  • Report which agents sent you work

  • Send the report link once it is published

Official, no scheduling

Does Spectora have an MCP server or an API? Both, and neither one books an inspection.

Spectora has an official MCP server, the AI Connector, and a public API (checked 28 Oct 2026). The connector's 10 tools read agents, clients, inspections, attachments and events for a company admin, and Spectora says it "cannot book, edit, or delete anything". The API also writes client and agent records and uploads attachments, but "can't schedule inspections, make calendar changes, or edit reports". Cotlet runs 11 Spectora tools hosted, 4 of them writes, over MCP for agents and REST for scripts.

  • Both come with every paid Spectora plan at no extra cost. API writes need the standard API plan; the free API plan gives 500 read requests a month and answers 403 to a write.
  • Agreements and sharing the client portal have no endpoint at all. Report content "isn't available to read".
  • Zapier and webhooks need Spectora Advanced ($4 per inspection). Zapier has 4 triggers on new or changed agent and client contacts and no actions.
Spectora AI Connector, the Spectora API and Cotlet compared
What you need AI ConnectorSpectora APICotlet
Read inspections, agents and clients Yes, company admin Yes Yes, as your role sees
Book or reschedule an inspection No No Yes, after your OK
Add an agreement, share the client portal No No Yes, after your OK
Create and update agent and client records No Yes, standard API plan Client inside a new booking
Report link No Not found Link only, no findings
Allowed by Spectora Yes, official Yes, official Uses the web app

Checked 28 Oct 2026. Sources: Spectora: AI Connector (MCP) and API · Spectora Developer: MCP server · Spectora Help: What is the MCP Server? · Spectora Help: Using the Zapier Integration · Spectora API overview and quota · Spectora pricing

Set up once

How does Cotlet connect to Spectora? One account, two ways to connect.

  1. 1Sign in to Spectora

    Use your own account in its Cotlet Cloud Browser.

  2. 2Choose MCP or REST

    Connect your agent or create a Cotlet API key.

  3. 3Run your workflow

    Ask your agent or send an HTTP request.

We never keep your Spectora password, and no booking, reschedule or portal link goes out to a client until you approve it. Who can see your session

Any MCP client

Connect Spectora 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. 1

    Enable Spectora for agents. Make a Cotlet account, log in to Spectora in its Cloud Browser as the user the agent should act as, and press Enable for agents.

  2. 2

    Add the Cotlet address. Give your agent https://cotlet.dev/mcp/v1 as a remote MCP server or custom connector.

  3. 3

    Confirm the connection. Chat apps send you through a Cotlet sign-in. Editors, n8n and scripts use an API key from the console.

https://cotlet.dev/mcp/v1 is one address for all your apps, Spectora among them. You can keep Spectora's own connector next to it for its ready-made reports. Turned Spectora on after connecting? Refresh the connector to see its tools.

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

Claude Code:
claude mcp add --transport http cotlet-spectora \
  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-spectora": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}
Codex
# ~/.codex/config.toml
[mcp_servers.cotlet-spectora]
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: spectora_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: spectora_write
Scripts and HTTP

How to use the Spectora REST API

Create your Cotlet API key

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

Connect Spectora in Cotlet and enable it for agents. Account access: Your own Spectora account (company admin for company-wide lists and settings, inspector for your own jobs).

Make your first Spectora API request

REST
curl https://cotlet.dev/api/v1/spectora/inspections \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read inspections 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": "spectora",
  "tool": "list_inspections",
  "result": {
    "inspections": [
      {
        "inspection_id": "insp_81f3",
        "address": "14 Maple Street, Springfield",
        "starts_at": "2026-11-03T09:00:00",
        "inspector": "Dana Whitt",
        "client": "Priya Nair",
        "services": [
          "Home Inspection"
        ],
        "agreements_signed": false
      }
    ],
    "next_cursor": null
  }
}

Returns inspection_id, address, date and time, inspector, client name, services and the agreement state for each job, in the order Spectora lists them. Follow next_cursor until it is empty.

Canceled inspections are included only when you search for them. The account sees the inspections its role allows.

from: First day, YYYY-MM-DD.

to: Last day, YYYY-MM-DD.

cursor: next_cursor from the previous page.

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

Spectora workflows for agents and automations

Spectora workflows you configure
ToolConnect throughExample workflow
n8nHTTP RequestReturns one inspection with its client, agents, services and agreements. Use get_inspection in your configured business report.
MakeHTTP > Make a requestLists upcoming inspections whose agreement the client has not signed. Use list_unsigned_inspections in your configured business report.
Python or Node.jsREST APIReturns the report URL of a published inspection. Use get_report_link in your configured business report.

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

Cotlet reads Spectora; 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.

7 read, 4 write

Spectora API endpoints and MCP tools

Inspections and the schedule4

Bookings and moves trigger the client emails your Automations set up. A new booking needs square feet and year built; when Spectora cannot look them up, the call fails and names what is missing.

  • list_inspections Lists inspections by date range, status, inspector or address. read

    Returns inspection_id, address, date and time, inspector, client name, services and the agreement state for each job, in the order Spectora lists them. Follow next_cursor until it is empty. Canceled inspections are included only when you search for them. The account sees the inspections its role allows.

    MCP callspectora_read → list_inspections

    REST endpointGET https://cotlet.dev/api/v1/spectora/inspections

    Parameters

    Parameters: list_inspections
    NameTypeDescription
    from string string First day, YYYY-MM-DD.
    to string string Last day, YYYY-MM-DD.
    search string string Address or client name, as in the Inspections search.
    inspector string string Inspector name, as shown in Spectora.
    cursor string string next_cursor from the previous page.

    Example response

    {
      "inspections": [
        {
          "inspection_id": "insp_81f3",
          "address": "14 Maple Street, Springfield",
          "starts_at": "2026-11-03T09:00:00",
          "inspector": "Dana Whitt",
          "client": "Priya Nair",
          "services": [
            "Home Inspection"
          ],
          "agreements_signed": false
        }
      ],
      "next_cursor": null
    }
  • get_inspection Returns one inspection with its client, agents, services and agreements. read

    Reads the Inspection Details page. It returns the address, time, services, agreements with their signed state, the client, the buyer's and listing agent, and notes. Report content is not returned, only the link from get_report_link.

    MCP callspectora_read → get_inspection

    REST endpointGET https://cotlet.dev/api/v1/spectora/inspections/{inspection_id}

    Parameters

    Parameters: get_inspection
    NameTypeDescription
    inspection_id string required string Id from list_inspections.

    Example input

    {
      "inspection_id": "inspection_8c41d2"
    }

    Example response

    {
      "inspection_id": "insp_81f3",
      "address": "14 Maple Street, Springfield",
      "starts_at": "2026-11-03T09:00:00",
      "inspector": "Dana Whitt",
      "client": {
        "name": "Priya Nair",
        "email": "priya@example.com"
      },
      "buyer_agent": "Marcus Lee",
      "listing_agent": "Elena Cruz",
      "services": [
        "Home Inspection"
      ],
      "agreements": [
        {
          "name": "Pre-Inspection Agreement",
          "signed": false
        }
      ]
    }
  • create_inspection Creates an inspection in the internal scheduler. writeasks first

    Fills the New Inspection form and saves it. Choosing a service pulls in the templates, agreements and fees set up for it, and Spectora then sends the client the booking email with the sign and pay link as your Automations say. The address needs square feet and year built; when Spectora cannot look them up, the call fails and lists what is missing. A service name Spectora does not have fails at once. By default you confirm each call; you can switch that off for this tool.

    MCP callspectora_write → create_inspection

    REST endpointPOST https://cotlet.dev/api/v1/spectora/inspections

    Parameters

    Parameters: create_inspection
    NameTypeDescription
    address string required string Street address, city and state.
    starts_at string required string Local start time, ISO 8601.
    inspector string string Inspector name; defaults to the signed-in account.
    client_name string required string Client full name.
    client_email string required string Client email.
    services array required array Service names exactly as in Settings > Services.
    listing_agent_email string string Listing agent email.

    Example input

    {
      "address": "address",
      "starts_at": "starts at",
      "client_name": "client name",
      "client_email": "jane@example.com",
      "services": "services"
    }

    Example response

    {
      "inspection_id": "insp_81f3",
      "status": "scheduled",
      "address": "14 Maple Street, Springfield",
      "starts_at": "2026-11-03T09:00:00",
      "agreements": [
        "Pre-Inspection Agreement"
      ]
    }
  • reschedule_inspection Moves an inspection to a new date, time or duration. writeasks first

    Does what Reschedule does on Inspection Details, also for a canceled inspection. Unless you turn notifications off, Spectora sends the reschedule notices, re-queues reminders and updates the agreements to the new date. With Trigger Once on, a second reschedule does not send again. Deleted inspections cannot be rescheduled. By default you confirm each call; you can switch that off for this tool.

    MCP callspectora_write → reschedule_inspection

    REST endpointPOST https://cotlet.dev/api/v1/spectora/inspections/{inspection_id}/reschedule

    Parameters

    Parameters: reschedule_inspection
    NameTypeDescription
    inspection_id string required string Id from list_inspections.
    starts_at string required string New local start time, ISO 8601.
    duration_hours number number New length in hours.
    disable_notifications boolean boolean Turn off all notifications before moving, as in the Internal box.

    Example input

    {
      "inspection_id": "insp_81f3",
      "starts_at": "2026-11-07T09:00:00",
      "duration_hours": 3
    }

    Example response

    {
      "inspection_id": "insp_81f3",
      "starts_at": "2026-11-07T09:00:00",
      "duration_hours": 3,
      "notifications_sent": true
    }

Agreements, portal and reports4

Agreement names must match your Services & Fees. The portal link shows the client's invoice, agreements and final report, so share it only with people who may see all three.

  • list_unsigned_inspections Lists upcoming inspections whose agreement the client has not signed. read

    Reads the same unsigned-jobs view Spectora has in its business reports. Each row has the inspection_id, client, date and the names of the agreements still unsigned, soonest inspection first. It reports agreements only.

    MCP callspectora_read → list_unsigned_inspections

    REST endpointGET https://cotlet.dev/api/v1/spectora/unsigned-inspections

    Parameters

    Parameters: list_unsigned_inspections
    NameTypeDescription
    from string string First day, YYYY-MM-DD.
    to string string Last day, YYYY-MM-DD.

    Example response

    {
      "inspections": [
        {
          "inspection_id": "insp_81f3",
          "client": "Priya Nair",
          "starts_at": "2026-11-03T09:00:00",
          "unsigned_agreements": [
            "Pre-Inspection Agreement"
          ]
        }
      ]
    }
  • add_agreement Adds an agreement from your Services & Fees to an existing inspection. writeasks first

    Uses Add Agreement in the Agreements box of Inspection Details. The agreement shows as unsigned until the client signs it in the Client Portal. A name that is not in the dropdown fails and lists the available agreements. By default you confirm each call; you can switch that off for this tool.

    MCP callspectora_write → add_agreement

    REST endpointPOST https://cotlet.dev/api/v1/spectora/inspections/{inspection_id}/agreements

    Parameters

    Parameters: add_agreement
    NameTypeDescription
    inspection_id string required string Id from list_inspections.
    agreement string required string Agreement name exactly as in the dropdown.

    Example input

    {
      "inspection_id": "inspection_8c41d2",
      "agreement": "agreement"
    }

    Example response

    {
      "inspection_id": "insp_81f3",
      "agreement": "Pest Agreement",
      "signed": false
    }
  • share_inspection_details Sends the client portal link of an inspection to an email address. writeasks first

    Uses Share Details. The recipient gets the client portal link, which shows what the client sees: the invoice, the agreements and the final report. Send it only to people who may see all of that. By default you confirm each call; you can switch that off for this tool.

    MCP callspectora_write → share_inspection_details

    REST endpointPOST https://cotlet.dev/api/v1/spectora/inspections/{inspection_id}/details/share

    Parameters

    Parameters: share_inspection_details
    NameTypeDescription
    inspection_id string required string Id from list_inspections.
    email string required string Recipient email.

    Example input

    {
      "inspection_id": "inspection_8c41d2",
      "email": "jane@example.com"
    }

    Example response

    {
      "inspection_id": "insp_81f3",
      "shared_with": "priya@example.com",
      "sent": true
    }

Agents and clients3

Read only. Detailed agent profiles are a Spectora Advanced feature, so some agent fields stay empty on the base plan.

  • list_agents Lists agent contacts with their company and number of inspections. read

    Returns agent_id, name, company, email, phone and the count of your inspections that agent is on. Agents come in the order of the Agents list. Follow next_cursor to the end.

    MCP callspectora_read → list_agents

    REST endpointGET https://cotlet.dev/api/v1/spectora/agents

    Parameters

    Parameters: list_agents
    NameTypeDescription
    search string string Name, company or email.
    cursor string string next_cursor from the previous page.

    Example response

    {
      "agents": [
        {
          "agent_id": "agt_204",
          "name": "Marcus Lee",
          "company": "Hillside Realty",
          "email": "marcus@example.com",
          "inspections": 11
        }
      ],
      "next_cursor": null
    }
  • get_agent Returns one agent with the inspections they are on. read

    Returns the agent profile and their inspections, newest first. Detailed agent profiles and agent reports are a Spectora Advanced feature, so fields only filled there come back empty on the base plan.

    MCP callspectora_read → get_agent

    REST endpointGET https://cotlet.dev/api/v1/spectora/agents/{agent_id}

    Parameters

    Parameters: get_agent
    NameTypeDescription
    agent_id string required string Id from list_agents.

    Example input

    {
      "agent_id": "agent_8c41d2"
    }

    Example response

    {
      "agent_id": "agt_204",
      "name": "Marcus Lee",
      "company": "Hillside Realty",
      "email": "marcus@example.com",
      "inspections": [
        {
          "inspection_id": "insp_81f3",
          "starts_at": "2026-11-03T09:00:00"
        }
      ]
    }
  • list_clients Lists client contacts and the inspections they are on. read

    Returns client_id, name, email, phone and the addresses of their inspections. Follow next_cursor to the end of the list.

    MCP callspectora_read → list_clients

    REST endpointGET https://cotlet.dev/api/v1/spectora/clients

    Parameters

    Parameters: list_clients
    NameTypeDescription
    search string string Name, email or address.
    cursor string string next_cursor from the previous page.

    Example response

    {
      "clients": [
        {
          "client_id": "cli_552",
          "name": "Priya Nair",
          "email": "priya@example.com",
          "inspections": [
            "14 Maple Street, Springfield"
          ]
        }
      ],
      "next_cursor": null
    }
Encrypted, revocable

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

  • What we store

    Your logged-in Spectora profile, AES-256-GCM, in Finland. Not your password.

  • What your agent gets

    The 11 Spectora tools. No cookie, no login.

  • What the session sees

    What your Spectora role sees: jobs, clients, agents, fees.

  • What no tool touches

    Payments, payouts, report editing, templates, settings and deleting.

  • If Spectora logs you out

    Your agent gets a sign-in link for you. We never log in for you.

  • How to cut access

    Disable for agents, reset the browser or delete the key. The next call stops.

Our site has A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results). No SOC 2 report or third-party pentest so far.

Account risk

Is it against Spectora's terms? Account safety Their terms ban automated tools without written permission.

"use bots, scrapers, crawlers, automated tools, or excessive requests to access, collect, or extract data from the Content without Spectora's express written permission"
Spectora Terms of Use, section 10 (c), last updated 6 Aug 2026

Section 6 also lets Spectora close an account "for any reason". Cotlet acts in the Spectora web app as you, and Spectora can still count that as an automated tool. Spectora's own connector and API are the routes it allows, so use them for anything they cover. We found no public case of a Spectora account closed for automation (checked 28 Oct 2026).

How we keep your account looking like you

  • Your own Spectora login, entered by you
  • One Cloud Browser with its own IP and cookies
  • Bookings, moves, agreements and portal links wait for your OK
  • No tool deletes an inspection, a client or an agent
  • If Spectora objects, we pause the Spectora tools for everyone within 24 h

Every booking and move emails a client and often an agent. Book a busy morning's requests one by one, not as a burst, and keep reads to what the job needs.

Tested every 12 h

What happens when Spectora changes? We repair the tool; your prompts keep working.

between tests of the Spectora tools
12 h
between tests of bookings and emails a client would get
24 h
for a call to a Spectora tool paused for repair
$0

If Spectora redesigns the New Inspection form or renames a field, the repair is ours. status.cotlet.dev checks the site, console and API every 3 minutes.

4 tools ask first

Approvals, undo and mistakes Clients get no email until you say so.

  1. 01 Reads the request Address, client, date, services and the agent.
  2. 02 Checks the calendar Lists that day's jobs so nothing double-books.
  3. 03 Waits for your OK The booking shows up in your Cotlet console first.
  4. 04 Reports the job Inspection id, time and the agreements it pulled in.
Which Spectora actions can be undone
ActionUndo
Book an inspectionCancel it in Spectora; the booking email is already out
RescheduleMove it back; a second notice goes out unless you turn notifications off
Add an agreementNo undo tool; change the job by hand in Spectora
Share the portal linkNo, the email is out

All 4 write tools ask first, because each one can email a client or an agent. The 7 reads run at once. Switch the wait off per tool for a scheduled run.

Reschedule can turn notifications off before the move, as the Internal box on Inspection Details does.

MCP call
{
  "name": "reschedule_inspection",
  "arguments": {
    "inspection_id": "insp_81f3",
    "starts_at": "2026-11-07T09:00:00",
    "duration_hours": 3
  }
}
REST
curl -X POST https://cotlet.dev/api/v1/spectora/inspections/insp_81f3/reschedule \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"starts_at":"2026-11-07T09:00:00","duration_hours":3}'
Response
{
  "inspection_id": "insp_81f3",
  "starts_at": "2026-11-07T09:00:00",
  "duration_hours": 3,
  "notifications_sent": true
}

Cron jobs and scripts call the same tools over REST at /api/v1/spectora, with one key and one price. A booking with a service name Spectora does not have fails at once and costs nothing. The tools table gives each tool's REST path.

Pay per call

How much does the Spectora MCP server cost?

About $17 a monthfor an inspection company booking about 25 jobs a month, 3,000 credits. Spectora still bills your plan as before.

A month of Spectora jobs for a small inspection company, in credits
JobCallsCredits
Book an inspection from a request2 × 25500
Reschedule and notify the client2 × 5100
Chase unsigned agreements, weekly4 × 4160
Add a missing pest agreement, weekly4 × 4160
Agent referral report, weekly2 × 480
Report link for a published inspection2 × 25500
Cloud Browser, 30 days1,500
Total3,000
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • No Spectora Advanced or API plan needed

The month is our example of a one or two inspector company; Spectora publishes no jobs-per-account figure. Spectora itself costs $109 a month for the first inspector. Dollars at the $29 pack rate.

Cotlet credit packs: price, credits and calls at 10 credits each
Credits Price, one time Calls at 10 credits Per 1,000 credits
5,000 $29 500 $5.80
15,000 $79 1,500 $5.27
32,000 $149 3,200 $4.66
60,000 $249 6,000 $4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header.

Other options

Spectora MCP server on GitHub, Zapier or hosted: which to use Spectora's own connector, and nothing else yet.

Other Spectora tools on GitHub and elsewhere, checked 28 Oct 2026
OptionWhat it doesWhere it stops
Spectora AI ConnectorOfficial MCP at connect.spectora.com, 10 read tools and 14 ready-made reports such as Lapsed Agent Reactivation.Reads only, company admin only.
ZapierSends new and changed agent and client contacts to a CRM.Spectora Advanced only, no inspections, no actions.
InspectorHub/OpenInspectionOpen-source inspection software that aims at parity with Spectora, 11 stars, active.A replacement: you move your business off Spectora.
api-evangelist/spectoraA third-party profile of the public API.Description only, no server.

We found no Spectora MCP server on GitHub. For reports and questions about your business, Spectora's free connector is the simpler pick. For syncing contacts into a CRM, the API or Zapier. For booking, moving jobs and chasing agreements from an agent, Cotlet.

EU company, since 2019

Who runs Cotlet A company you can look up.

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

Spectora API and MCP: questions

How do I get access?

Sign up free at https://cotlet.dev, find Spectora under Integrations in the console and log in to Spectora in its Cloud Browser. The trial starts with your first app and asks for no card.

How do I connect Spectora to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Spectora 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 Spectora account through Cotlet, in their phone apps too.

What can ChatGPT do in Spectora?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Spectora: book an inspection from a request; reschedule an inspection and tell the client; chase unsigned agreements. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need an admin account or Spectora Advanced?

No Advanced plan is needed for the tools here, but your role counts. The official connector needs company admin (Spectora, checked 28 Oct 2026). Cotlet works in your own session, so it sees what your role sees. Agent profiles and agent reports are Advanced features, so those fields can be empty on the base plan.

What happens to the emails Spectora sends clients?

They go out as your Automations say. Creating and rescheduling an inspection triggers the booking and reschedule notices, which is why those calls wait for your OK by default. Reschedule can turn notifications off first, as the Internal box does.

Should I use Spectora's AI Connector instead?

For questions, yes: it is free with a paid Spectora plan and comes with ready-made reports. It cannot book, edit or delete anything. Use Cotlet for the jobs that change the schedule or reach a client, and keep both connected if you like.

Does Spectora have webhooks?

Yes, for Spectora Advanced users, set up at developer.spectora.com. Webhook calls do not count toward the API quota. Cotlet does not use them; run your agent on a schedule, for example a daily list_unsigned_inspections pass.

Is the MCP server different from the REST API?

Only the way in differs. Both carry the same 11 tools, inputs and answers, with one API key and one price. Agents use MCP; scripts and HTTP steps use REST.

Is Cotlet affiliated with Spectora?

No. Cotlet is independent and not affiliated with Spectora.

Can I use the Spectora 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 agent access to Spectora.

Free 7-day trial with 2,000 credits, no card needed.