FreeAgent MCP server for AI agents

Live

OAUTH 2.0

ACCOUNTING

Accounting & Finance

FreeAgent gives your agent small business accounting: create and send invoices, estimates, and credit notes, record bills and expenses, explain bank transactions, log time on projects, and read profit and loss, balance sheet, and cashflow reports.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
FreeAgent
agent · Acme Q3
Run
Which invoices are overdue, and how much is outstanding?
S
freeagent_invoices_list
121ms
Bookkeeping agent
6 invoices are overdue, totaling £14,820. The oldest, for Harbour Design, is 47 days past due.
Sources: FreeAgent invoices, 6 overdue
freeagent
6 invoices
18:29
Message Claude...

Tools your bookkeeping agent reaches for on FreeAgent, scoped per user.

CALL ANY TOOL
117 tools for accounting in FreeAgent: create, email, and reconcile invoices, estimates, and credit notes, record bills and expenses, explain bank transactions, log timeslips, and read financial reports.
freeagent_accounting_transaction_get
Get accounting transaction
Get one FreeAgent accounting transaction by ID. Returns its date, description, category, nominal code, debit value, source item and foreign currency data. Use freeagent_accounting_transactions_list to find the ID.
Parameters
Name
Type
Required
Description
transaction_id
string
Required
Numeric ID of the accounting transaction: the number at the end of its FreeAgent `url` (for https://api.freeagent.com/v2/accounting/transactions/123 the ID is 123). Get it from freeagent_accounting_transactions_list.
freeagent_accounting_transactions_list
List accounting transactions
freeagent_bank_account_create
Create bank account
freeagent_bank_account_update
Update bank account
freeagent_bank_statement_upload
Upload bank statement
freeagent_bank_transaction_delete
Delete bank transaction
freeagent_bank_transaction_get
Get bank transaction
freeagent_bank_transactions_list
List bank transactions
freeagent_contact_create
Create contact
freeagent_contact_get
Get contact
freeagent_contacts_list
List contacts
freeagent_credit_note_delete
Delete credit note
freeagent_credit_note_mark_as_draft
Credit note mark as draft
freeagent_credit_note_send_email
Credit note send email
freeagent_credit_note_update
Update credit note
freeagent_estimate_mark_as_approved
Estimate mark as approved
freeagent_estimate_pdf_get
Get estimate pdf
freeagent_estimates_list
List estimates
freeagent_expense_create
Create expense
freeagent_invoice_duplicate
Duplicate invoice
freeagent_journal_set_get
Get journal set
freeagent_note_create
Create note
freeagent_note_delete
Delete note
freeagent_note_update
Update note
freeagent_notes_list
List notes
freeagent_price_list_item_update
Update price list item
freeagent_stock_item_get
Get stock item
freeagent_stock_items_list
List stock items
freeagent_timeslip_timer_start
Start timeslip timer
freeagent_timeslip_timer_stop
Stop timeslip timer

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// FreeAgent tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["freeagent"], toolNames: [
    "freeagent_invoices_list",
    "freeagent_invoice_send_email",
    "freeagent_profit_and_loss_summary_get"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find overdue invoices, email each one to its client again, and summarize this month's profit and loss" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["freeagent"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find overdue invoices, email each one to its client again, and summarize this month's profit and loss" }],
  tools,
});

// Execute the tool call with the user's vaulted FreeAgent OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["freeagent"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find overdue invoices, email each one to its client again, and summarize this month's profit and loss" }],
  tools,
});

// Tool call runs with the user's vaulted FreeAgent OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["freeagent"] }, pageSize: 100,
});

const agent = new Agent({
  name: "bookkeeping_agent",
  model: "gemini-2.5-pro",
  instruction: "FreeAgent tools scoped to this user",
  tools,
});

await agent.run("Find overdue invoices, email each one to its client again, and summarize this month's profit and loss");
Try these prompts
Copy any prompt into your agent. Each maps directly to a FreeAgent tool. Click to copy, paste into your agent, done.
Invoicing
Copy the prompt
Copied
Create a draft invoice for Harbour Design for 12 hours of consulting at £95 an hour.
Copy the prompt
Copied
Email the latest invoice for Harbour Design to the client.
Copy the prompt
Copied
Convert the approved website estimate into an invoice.
Bank and expenses
Copy the prompt
Copied
List unexplained transactions in our business current account this month.
Copy the prompt
Copied
Explain this £240 bank payment as Travel.
Copy the prompt
Copied
Record a £36 train fare expense for Sam from yesterday.
Reports and time
Copy the prompt
Copied
Show profit and loss for this accounting year.
Copy the prompt
Copied
What tax deadlines are coming up for the company?
Copy the prompt
Copied
Log 3 hours on the Rebrand project for today.
SEE HOW AUTH WORKS
Each user signs in to FreeAgent once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
FreeAgent
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
FreeAgent
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
FreeAgent
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
FreeAgent
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other accounting and finance connectors.
GTM and RevOps Teams
Revenue forecast commentary
Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.
GTM and RevOps Teams
CRM AI agent
Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.
Test other agents
See the same per-user auth pattern across other accounting and finance connectors.
GTM
Revenue forecast agent
Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared FreeAgent token looks fine in a demo. In production every invoice and journal entry looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
FreeAgent today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access FreeAgent as the user or through a shared service account?
As the user. Each user signs in to FreeAgent once, and Scalekit stores and refreshes their tokens. Invoices, bills, and journal entries the agent creates are attributed to that user in your audit trail, not a shared service account.
Where is the FreeAgent OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in FreeAgent?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the report and list tools without freeagent_invoice_delete, which permanently deletes an invoice, or freeagent_journal_set_create, which posts manual journal entries. Scalekit also enforces scope checks before every API call.
What happens when a user revokes FreeAgent access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Which FreeAgent company does the agent work on?
The company of the FreeAgent user who signs in. freeagent_company_get returns its details, freeagent_user_me_get returns the user who authorized the connection, and freeagent_company_tax_timeline_get lists that company's upcoming tax events, such as VAT returns and corporation tax.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""freeagent"": {
""url"": ""https://mcp.scalekit.com/freeagent"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.freeagent]
url = ""https://mcp.scalekit.com/freeagent""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""freeagent"": {
""url"": ""https://mcp.scalekit.com/freeagent"",
""type"": ""http""
}
}
}