Product Development
Forecast MCP connector
The Forecast connector brings Forecast clients, company contacts, departments, exchange rates, labels and custom fields to Claude, ChatGPT, Cursor and the Elaichi Agent, so each person can read and update them inside their own Forecast access.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Forecast to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Forecast once
-
Open Connections, choose Add connection, and pick Forecast.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Forecast API key. One person generates a token in Forecast and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Forecast MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Forecast MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Forecast MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Forecast to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Forecast through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Account Management
Set up a new client before kickoff
Create the client in Forecast, add its company contacts and apply the right labels in one ask, so the record is ready before the first project is planned.
-
Finance
Keep exchange rates current every month
Update the exchange rates Forecast uses for multi-currency projects when the month closes, and check which rates exist without opening the settings pages.
-
Operations
Clean up company contacts in bulk
Fix titles, emails and ownership across dozens of Forecast company contacts at once, and remove the ones that have gone stale.
-
Project Management
Fill in custom fields on phases and tasks
Set the custom field values on phases, tasks and time registrations after a planning session, so reports filter correctly later.
-
Delivery
Answer client questions from live records
Ask which Forecast clients belong to a department, pull up a single client by name, and get the answer from what is in Forecast right now.
-
Leadership
Review departments and permission profiles
See how departments and permission profiles are laid out in Forecast before a reorganization, without asking an administrator to export anything.
Try asking
- “Create a client called Northwind and add its two contacts”
- “Update the EUR to USD exchange rate to 1.08”
- “Which Forecast clients belong to the Copenhagen department?”
AI tools
Forecast tools for your AI agents
324 tools are ready to call through Elaichi's MCP endpoint the moment you connect Forecast, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
Showing 267 of 324 Forecast tools here. Connect Forecast and call search_tools or tools/list over the MCP endpoint for the complete set.
See it in Elaichi
What connecting Forecast gets you
6 screens from the product, each doing one job for your Forecast account.
The agent
Ask about Forecast clients in plain language.
Type a question and get answers from live Forecast clients, contacts and departments.
- clients
- contacts
- departments
- exchange rates
Ask Elaichi to work across your apps.
Create a client called Northwind and add its two contacts
Update the EUR to USD exchange rate to 1.08
Which Forecast clients belong to the Copenhagen department?
Also runs in Claude, ChatGPT or Cursor
MCP clients
One Forecast endpoint for every AI client.
Claude, ChatGPT and Cursor connect over OAuth, with no SDK and no shared API key.
Copy the endpoint
Tool catalog
324 Forecast tools, no code to write.
Clients, contacts, departments, exchange rates, labels and custom fields, covered from day one.
- List all Forecast clients
- Get single Forecast client by ID
- Create a Forecast client
- Update a Forecast client by ID
Toolboxes
Each team gets its own Forecast toolbox.
Finance works with exchange rates while account managers handle clients and contacts.
- Account Management
- Finance
- Project Management
- Operations
Shared connections
Share one Forecast connection without sharing keys.
One person connects the API key, teammates work through it and never see it.
- Agency EMEA
- Finance
- Delivery
- Account Management
Audit log
Every Forecast change has a name attached.
See when a client was created, who did it, and which record changed.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts Forecast work end to end.
New clients are fetched, grouped, drafted into a digest, approved, then posted to Forecast.
Forecast digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch clients
Forecast
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Forecast
Queued
Collections and dashboards
Forecast health numbers, computed without a model.
Four metrics, 14 days of clients created and a team breakdown, refreshed on schedule.
Forecast health
Refreshed 4 minutes ago · every 15 minutes · from the clients collection
Clients
1,284 ↓ 12%
Contacts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Clients created
Last 14 days
By team
Share of activity
Agency EMEA 34%
Finance 27%
Delivery 21%
Account Management 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Forecast to Claude?
Connect Forecast in Elaichi first: paste a Forecast API key when asked, and Elaichi does the rest. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Sign in with your Elaichi account and Forecast is available in your next chat.
Does Forecast work with ChatGPT and Cursor as well as Claude?
Yes. Once Forecast is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Forecast once and every client picks it up.
What can an AI agent actually do with my Forecast data?
An agent can list your Forecast clients, open a single client, create or update one, and add, update or remove company contacts in bulk. It can also update exchange rates, set custom fields on phases, tasks and time registrations, and look up departments, labels and permission profiles. Short concrete asks such as "create a client called Northwind" work better than long paragraphs.
Does connecting Forecast give the AI access to everything in my Forecast account?
No. Every call to Forecast runs as the person who signed in, so the agent can only see and change what that person's Forecast permission profile already allows. Elaichi can narrow that further with roles and restrictions, but it can never widen it beyond what Forecast itself grants.
Can I stop an agent from deleting or changing things in Forecast?
Yes. Restrictions in Elaichi apply per action, so you can allow reading Forecast clients while blocking deletes, or allow contact updates while blocking anything to do with exchange rates. A restricted action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt can reach it.
What happens to a Forecast connection when someone leaves?
Offboarding the person in Elaichi ends their access to Forecast through every client at once. A shared Forecast connection keeps working for everyone else on the team. If you want Forecast gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.
Does the Forecast MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Forecast is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Put Forecast in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.