Skip to main content
Glama
OxygenBubbles

FreeAgent MCP Server

freeagent_create_expense

Claim back personal card or cash purchases by creating an expense in FreeAgent. Provide vendor, date, amount, description, and optional category; attach receipt or link matching bank transaction.

Instructions

Create an expense in FreeAgent — for purchases on a personal card or cash that need claiming back. Provide vendor, date, amount, description and category. If categoryUrl is omitted, auto-selects from vendor mapping. Optionally pass bankAccountId to auto-match and explain a corresponding bank transaction (e.g. if the same purchase also appears on a company card).

RECEIPTS: Before asking the user for a file, search connected email tools (Gmail, Outlook/M365) for a matching invoice. Use vendor name, amount and date as search terms. Download the PDF and pass it as fileBase64 + fileName. Also check local sources (Downloads folder, etc.) if the user has mentioned them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vendorYesVendor / merchant name (e.g. 'IONOS Cloud')
datedOnYesExpense date YYYY-MM-DD
projectNoFreeAgent project URL (e.g. '/v2/projects/123') to tag the expense against, so it can be rebilled or reported per client. Use freeagent_list_projects to find it.
currencyNoISO 4217 currency code (default GBP)GBP
fileNameNoFile name for the receipt (e.g. 'receipt.pdf')
vatAmountNoVAT amount as string (e.g. '3.80')
fileBase64NoBase64-encoded receipt file (PDF, PNG, JPEG, etc.)
categoryUrlNoFreeAgent category URL (e.g. '/v2/categories/285'). Auto-selected from vendor if omitted.
contentTypeNoMIME type (e.g. 'application/pdf'). Inferred from fileName if omitted.
descriptionYesExpense description (e.g. 'Monthly cloud hosting')
grossAmountYesGross amount as string (e.g. '22.80')
bankAccountIdNoIf supplied, search this bank account for a matching unexplained transaction (same amount, date ±4 days) and link the expense to it.
Install Server

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since annotations only mark readOnly/idempotent/destructive hints, the description carries the burden here. It discloses auto-selection of category from vendor, optional bank-transaction matching via bankAccountId, and the required receipt-search workflow. It stops short of explaining the full side-effect of linking/explaining the bank transaction, which prevents a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two structured paragraphs with no filler. The core purpose is frontloaded, the optional bank-account matching is clearly explained, and the RECEIPTS section is practical workflow guidance rather than redundant paraphrasing of the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 12 parameters and no output schema, the description covers the main invocation intent, optional behaviors, and the required receipt-presearch step. It lacks an explicit note on what the tool returns after success, but that is not critical for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters, giving a baseline of 3. The description enriches beyond the schema by tying parameters to real scenarios: personal card purchases, company-card overlap, and the vendor-and-date matching for bankAccountId. These additions help the agent select which parameters matter in context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States precisely 'Create an expense in FreeAgent' and narrows the use case to 'purchases on a personal card or cash that need claiming back'. This clearly distinguishes it from the mileage-expense sibling and tells the agent exactly what resource is being created.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete scenario for when this tool applies and even instructs the agent about receipt-related workflow before invocation. It does not explicitly mention alternatives such as freeagent_create_mileage_expense, so the agent is left to infer which sibling handles mileage claims.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/OxygenBubbles/freeagent-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server