Skip to content

Planful MCP connector

The Planful connector lets Claude, ChatGPT, Cursor and Microsoft Copilot pull Planful report data, general ledger data and planning models, run data loads and model calculations, all inside each person's own Planful access with every call logged.

  • Connects with an API key
  • Free 14-day trial
  • No credit card
ChatGPT Elaichi connected

Which Planful data loads are still running right now?

Working in Planful with Elaichi

  • List all Planful data load rules
  • List all Planful gl data load rules
  • List all Planful transaction data load rules
Ask anything…
Governance / Audit log Last 24 hours
Planful List all Planful transaction data load rules Emily Carter · ChatGPT · 9:41 AM Done
Planful List all Planful gl data load rules Emily Carter · ChatGPT · 9:41 AM Done
Planful List all Planful data load rules Emily Carter · ChatGPT · 9:41 AM Done
Planful Create a Planful data transfer Megan Brooks · Claude · 9:38 AM Done
Planful Planful data transfers bulk update Ryan Hayes · Cursor · 9:35 AM Done

How to connect Planful to Claude, ChatGPT, Cursor or Microsoft Copilot

Step by step, for each AI app

Planful MCP connector for Claude

  1. 1

    Open Customize, then Connectors.

  2. 2

    Press Add.

  3. 3

    Name it, paste the MCP server URL, then Continue.

    https://api.elaichi.ai/mcp
  4. 4

    Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

Planful MCP connector for Claude Code

  1. 1

    In a terminal, run claude mcp add with the endpoint.

    https://api.elaichi.ai/mcp
  2. 2

    Start Claude Code and run /mcp.

  3. 3

    Pick elaichi, then sign in and approve in the browser.

Terminal

$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp

Use --scope project instead to share it with the repository through .mcp.json.

Planful MCP connector for ChatGPT

  1. 1

    Open Plugins, then press the + button.

  2. 2

    Name it and paste the endpoint into Server URL.

    https://api.elaichi.ai/mcp
  3. 3

    Leave Authentication on OAuth, then tick the risk acknowledgement.

  4. 4

    Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

Planful MCP connector for Cursor

  1. 1

    Open ~/.cursor/mcp.json.

  2. 2

    Add the endpoint under mcpServers.

    https://api.elaichi.ai/mcp
  3. 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.

Planful MCP connector for Microsoft Copilot

  1. 1

    In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.

  2. 2

    Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.

    https://api.elaichi.ai/mcp
  3. 3

    Create a new connection, sign in and approve, then press Add to agent.

  4. 4

    Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Server URL
https://api.elaichi.ai/mcp
Authentication
OAuth 2.0
Type
Dynamic discovery

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

Connect Planful to any MCP client

  1. 1

    Add the endpoint as a remote MCP server.

    https://api.elaichi.ai/mcp
  2. 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.

What teams do with Planful through Elaichi

Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Planful is logged.

  • FP&A

    Check which data loads finished before close

    Ask which Planful data loads are still running and which have completed, then chase the ones that stalled instead of refreshing the status screen all morning.

  • Accounting

    Pull general ledger data for one segment

    Ask for the general ledger data behind a cost center or a business unit segment and get the figures back in plain language, ready to paste into a reconciliation.

  • Controllership

    Kick off a process run and confirm it

    Start a Planful process run as part of the close checklist and have the agent report back when it has been created, so nothing waits on someone remembering to click.

  • Finance systems

    Load a file of actuals into Planful

    Create a data transfer, attach the file and mark it complete from the same chat where you prepared the numbers, using the data load rules already set up in Planful.

  • FP&A

    Rerun a model calculation after an edit

    Append the new member or attribute to a Planful model, start the calculation and check its status without opening the model yourself.

  • Finance leadership

    Export a hierarchy before a reorganization

    Pull an attribute hierarchy or budget entity hierarchy out of Planful so the proposed structure can be reviewed and compared before anyone moves anything.

Try asking

  • “Which Planful data loads are still running right now?”
  • “Show general ledger data for segment 1 this quarter.”
  • “Run the revenue model calculation and check its status.”

See all 47 Planful tools →

What connecting Planful gets you

6 screens from Elaichi, each doing one job for your Planful account.

Elaichi Agent

Ask Elaichi to work across your apps.

Which Planful data loads are still running right now?

Show general ledger data for segment 1 this quarter.

Run the revenue model calculation and check its status.

Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot

The agent

Ask Planful questions in plain language.

Get answers from live data loads, models and report data, not from a stale export.

ElaichiAI apps
Claude ChatGPT Cursor Microsoft Copilot

Copy the endpoint

https://api.elaichi.ai/mcp
Client Connected by Status Last used
Claude
E

Emily Carter

• Connected 4 minutes ago
Cursor
M

Megan Brooks

• Connected 2 hours ago
ChatGPT
R

Ryan Hayes

• Connected Yesterday

AI apps

One Planful endpoint for every MCP client.

Claude, ChatGPT, Cursor and Microsoft Copilot connect over OAuth, with no SDK and no shared API key.

ElaichiTools
Tool Action Description
Create a Planful data transfer Create Transfer data to Planful in a single call against a Data Load Rule (DLR). Returns: DataLoadRuleId, ExcecutionId, ChunksReceived, RecordsReceived, RunAsynchronously, Attempts, TransferResponse, DataLoadRuleConfig, Payload. Requires DataLoadRuleConfig and Payload. Max 40MB per request.
Planful data transfers bulk update Update Transfer Planful data in batches when the load exceeds limits. Returns: DataLoadRuleId, ExcecutionId, ChunksReceived, RecordsReceived, RunAsynchronously, Attempts, TransferResponse, DataLoadRuleConfig, Payload. Requires DataLoadRuleConfig and Payload; complete the load via the IsLoadCompleted header or a null Payload. Max 40MB per request.
Planful data transfers complete Complete When you are about to send the last request, you can either add the IsLoadCompleted parameter in the Header and provide its value as True or you provide the value for the payLoad parameter in the request body as Null . Final batch of a batched transfer: sends IsLoadCompleted=true so Planful closes the load. Returns: DataLoadRuleId, ExcecutionId, ChunksReceived, RecordsReceived, RunAsynchronously, Attempts, TransferResponse, properties. Required: payload, DataLoadRuleName, ColumnDelimiter.
Create a Planful data transferfile Create Transfer one or more CSV or ZIP data files into Planful through a data load rule. Returns: DataLoadRuleId, ExcecutionId, RunAsynchronously, Attempts, TransferResponse, DataLoadRuleConfig, Payload. Required: data_load_rule_name, column_delimiter, file. ZIP files must contain base64-encoded CSV.
List all Planful data load rules List List all data load rules (DLRs) you have access to in Planful. Returns an array of rules, each with DataLoadRuleId, Name, and LoadItem (the DLR type).

Tool catalog

47 Planful tools, no custom code.

Data loads, general ledger data, hierarchies, process runs and model calculations, ready the moment you connect.

ElaichiToolboxes
Name Source template Tools Created

FP&A toolbox

Planful · models and calculations

Planful starter 18 Mar 4, 2026

Accounting toolbox

Planful · general ledger and segment data

— 9 Mar 2, 2026

Controllership toolbox

Planful · process runs and close

— 24 Feb 27, 2026

Finance systems toolbox

Planful · data loads and transfers

Planful starter 6 Feb 19, 2026

Finance leadership toolbox

Planful · report data

— 31 Jan 30, 2026

Business partners toolbox

Planful · budget entity hierarchies

— 12 Jan 22, 2026

Toolboxes

Every finance team gets its own Planful toolbox.

FP&A, accounting and finance systems each see the Planful tools their work needs.

ElaichiConnections
Connection Scope Status Access
PL

Planful (Corporate FP&A)

Connected by Emily Carter

Personal • Active 1 team · 6 members
PL

Planful (Accounting)

Connected by Jake Morgan

Organization • Active 3 teams · 24 members
PL

Planful (Controllership)

Connected by Megan Brooks

Organization • Active 2 teams · 11 members
PL

Planful (Finance systems)

Connected by Tyler Reed

Personal • Needs re-auth 1 team · 3 members
PL

Planful (EMEA finance)

Connected by Ryan Hayes

Personal • Active Not shared
PL

Planful (Americas finance)

Connected by Ashley Parker

Personal • Active 2 teams · 9 members

Shared connections

Share a Planful connection, never the API key.

One person connects Planful, teammates work through it without ever seeing a credential.

ElaichiAudit log
When Who What happened Type

2 minutes ago

Mar 6, 2026, 3:10 PM

E

Emily Carter

[email protected]

Restriction Created Access

8 minutes ago

Mar 6, 2026, 3:04 PM

J

Jake Morgan

[email protected]

Restriction Updated Access

14 minutes ago

Mar 6, 2026, 2:58 PM

M

Megan Brooks

[email protected]

Role Assigned Access

20 minutes ago

Mar 6, 2026, 2:52 PM

T

Tyler Reed

[email protected]

Planful Users Updated MCP

26 minutes ago

Mar 6, 2026, 2:46 PM

R

Ryan Hayes

[email protected]

Planful Data loads Created MCP

32 minutes ago

Mar 6, 2026, 2:40 PM

A

Ashley Parker

[email protected]

Planful Data loads List Toolbox

Audit log

Know who touched Planful, and when.

Every data load, process run and model change is logged with the person who asked for it.

From answering questions to doing the work

A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.

Planful digest

Run 418 · started 2 minutes ago · on behalf of Emily Carter

  1. ✓

    Schedule

    Every weekday at 8:00 AM

    0.2s
  2. ✓

    Fetch data loads

    Planful

    1.4s
  3. ✓

    Group by owner

    Transform

    0.1s
  4. ✓

    Draft the digest

    Agent step

    Ran with 4 tools, returned a structured summary

    6.2s
  5. Approve the digest

    Needs approval

    Assigned to Jake Morgan

    Approve
  6. Post the digest

    Planful

    Queued

Workflows

A schedule starts Planful work end to end.

Data load statuses are fetched, grouped and drafted into a digest a person approves before it posts.

Planful health

Refreshed 4 minutes ago · every 15 minutes · from the data loads collection

Live

Data loads

1,284 ↓ 12%

Models

96 ↓ 8%

Needs attention

3 ↑ 2

Updated this week

412 ↑ 9%

Data loads created

Last 14 days

By team

Share of activity

Corporate FP&A 34%

Accounting 27%

Controllership 21%

Finance systems 18%

Collections and dashboards

Planful health, computed on a schedule.

Data loads created over 14 days and a breakdown by team, with no model in the reporting.

For IT and engineering

Elaichi vs Zapier MCP vs Composio for Planful

All three can connect Planful to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

Elaichi compared with Zapier MCP and Composio for Planful, by what to check
What to check Elaichi Zapier MCP Composio
Where the AI connects One address for the whole organization. https://api.elaichi.ai/mcp A server per member, created at sign-in. An MCP endpoint per team, or an SDK.
Control over Planful tools Allow or restrict single Planful tools, per role or user. App and action restrictions on the account. Role permissions, down to the action.
Record of calls One audit entry per Planful call. A History tab of tool calls. A log of every tool call.
Single sign-on SAML or OIDC, plus SCIM, on Gold. SAML on Enterprise. SAML and OIDC on Enterprise.
Price Free for one person; $15 per user per month on Gold. 2 tasks per successful call. Billed per tool call.

Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.

Longer take: Zapier MCP alternative and when you don't need an MCP gateway.

Planful tools for your AI agents

47 tools are ready to call through Elaichi's MCP endpoint the moment you connect Planful, governed by the same roles, restrictions, and audit log as everything else in Elaichi.

Questions, answered

How do I connect Planful to Claude?

Connect Planful in Elaichi first, where you paste the Planful API key your administrator provides, then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. There is no OAuth application to register in Planful and no client ID or secret to generate. Claude then signs you in through Elaichi, and you are ready to ask about data loads, models and report data.

Does Planful work with ChatGPT and Cursor as well as Claude?

Yes. Once Planful is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Planful once and every client picks it up.

What can an AI agent actually do with my Planful data?

An agent connected to Planful can search report data, list general ledger and segment data, check which data loads are running or finished, start data transfers and process runs, export attribute and budget entity hierarchies, and run or check model calculations. It can also append members and attributes to a model and clear model data when asked. Short, concrete asks such as which Planful data loads are still running work better than long paragraphs.

Does connecting Planful give the AI access to every model and entity?

No. Every call runs inside the Planful access of the person who signed in, so an agent sees the models, entities and reports that person can already see in Planful and nothing more. Elaichi can narrow that access further with restrictions, but it can never widen it beyond what Planful itself allows.

Can my team share one Planful connection?

Yes. One person connects Planful with the API key in Elaichi and shares the connection with a team, and nobody else ever handles the key. Each teammate still signs in to Elaichi as themselves, so every Planful call in the audit log carries their own name.

Can I stop an agent from clearing or changing data in Planful?

Yes. Restrictions in Elaichi work per action, so you can restrict clearing model data, moving hierarchies or starting process runs in Planful for a role or for one person while leaving read access open. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it whatever the prompt says.

What happens to a Planful connection when someone leaves?

Offboarding the person in Elaichi ends their Planful access at once, in every client they used. A shared Planful connection keeps working for everyone else on the team. If you want Planful gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

Does the Planful MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Planful 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, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

Is Elaichi an alternative to Zapier MCP for Planful?

Yes. Both let Claude, ChatGPT or Cursor use Planful. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Planful call.

How is Elaichi different from Composio for Planful?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Planful: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

Put Planful in front of your team

14 days of Black, no credit card. Connect it once and pick what each team can call.

When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.

Add one link to your AI app

The same link for everyone on your team.

https://api.elaichi.ai/mcp
  • ChatGPT
  • Claude
  • Cursor
  • Microsoft Copilot