Which integrations are available for this server?

Provides tools for managing personal finances through Firefly III, including accounts, transactions, budgets, categories, tags, bills, piggy banks, and rules.

How do I use Firefly III MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Firefly III MCP Server Show me my account balances" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Firefly III MCP Server

by horsfallnathan

Overview Schema Source Related Servers Score Discussions Admin

Python

Remote

Firefly III MCP Server

A Model Context Protocol (MCP) server that provides programmatic access to Firefly III personal finance management through Claude Desktop, Cursor IDE, and other MCP-compatible AI assistants.

📚 Documentation

📖 Full Documentation

Related MCP server: Lunch Money MCP Server

Overview

This MCP server enables AI assistants to interact with your Firefly III instance, allowing you to manage your personal finances through natural language conversations. You can:

💰 Manage accounts: List, create, update, and delete asset, expense, revenue, and liability accounts
📊 Handle transactions: Create, retrieve, update, and delete financial transactions
💳 Budget management: Work with budgets, budget limits, and track spending
🏷️ Categorization: Manage transaction categories and tags
💸 Bill tracking: Handle recurring bills and payment monitoring
🐷 Piggy banks: Manage savings goals and track progress
⚙️ Rules & automation: Configure transaction rules and rule groups

Key Features

🤖 AI Integration: Works seamlessly with Claude Desktop, Cursor IDE, and other MCP clients
💡 Comprehensive API: Supports most Firefly III v1 API endpoints
⚡ Flexible modes: Choose between consolidated tools or direct API access
🔒 Type-safe: Full Pydantic model validation for all requests/responses
🎯 Configurable: Enable only the Firefly III entities you need

Quick Example

Once set up, you can interact with your finances naturally:

"Show me my account balances"
"Create a new expense for $25.50 at Coffee Shop from my Checking Account"
"What's my budget status for this month?"
"List all my transactions from last week"
"Create a new savings goal for a vacation with a target of $2000"
"Show me all bills that are due this month"
"Help me create a transaction rule that automatically categorizes Starbucks purchases as 'Coffee'"
"Create a new budget category for 'Home Improvement' with a $500 monthly limit"

Requirements

Python 3.12+
A running Firefly III instance
Firefly III API token (Personal Access Token)

🚀 Quick Setup

Local Installation

Clone and set up the project locally:

# Clone the repository
git clone https://github.com/horsfallnathan/firefly-iii-mcp-server.git firefly-mcp
cd firefly-mcp

# Install with UV (recommended)
uv sync

# Or with pip
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e .

Configuration

Create a .env file in the project root:

# Required: Your Firefly III API URL and token
FIREFLY_API_URL=https://your-firefly-instance.com/api/v1
FIREFLY_API_TOKEN=your_token_here

# Optional: Enable all entities (default: just accounts). Requires `FIREFLY_DIRECT_MODE=true`
# Enabling all entities would lead to about 76 tools being registered and most clients suggest a maximum of 40 tools
FIREFLY_ENABLED_ENTITIES=all

# When false, the server will register consolidated tools for dynamic operation. When true, it will register individual tools for each operation
FIREFLY_DIRECT_MODE=false

FIREFLY_LOG_LEVEL=INFO

🔑 Getting a Firefly III API Token:

Log into your Firefly III instance
Go to Options → Profile → OAuth
Click Create New Token
Give it a descriptive name (e.g., "MCP Server")
Copy the generated token to your .env file

📖 See full configuration guide

🔌 MCP Client Integration

Cursor IDE

Add to your workspace or global settings:

{
  "mcp.servers": {
    "firefly-mcp": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/firefly-mcp", "run", "firefly-mcp"],
      "env": {
        "FIREFLY_API_URL": "https://your-firefly-instance.com/api/v1",
        "FIREFLY_API_TOKEN": "your_token_here",
        "FIREFLY_ENABLED_ENTITIES": "all",
        "FIREFLY_DIRECT_MODE": "false"
      }
    }
  }
}

VSCode

Create an mcp.json file in your project root or workspace:

{
  "servers": {
    "firefly-mcp": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/firefly-mcp", "run", "firefly-mcp"],
      "env": {
        "FIREFLY_API_URL": "https://your-firefly-instance.com/api/v1",
        "FIREFLY_API_TOKEN": "your_token_here",
        "FIREFLY_ENABLED_ENTITIES": "all",
        "FIREFLY_DIRECT_MODE": "false"
      }
    }
  }
}

Operation Modes

Consolidated Mode (Default)

Provides three meta-tools for dynamic operation:

firefly_execute(entity, operation, params) - Execute any Firefly III operation
firefly_list_operations(entity?) - List available operations
firefly_get_schema(entity, operation) - Get parameter schema for operations

Direct Mode

Set FIREFLY_DIRECT_MODE=true to register individual tools for each operation:

account_list(limit?, page?) - List accounts
account_get(id) - Get account details
transaction_create(transactions) - Create transactions
And many more...

🛠️ Development & Testing

Using MCP Inspector

For development and debugging, use the MCP Inspector:

# Install and run MCP Inspector
npx @modelcontextprotocol/inspector uv run firefly-mcp

The MCP Inspector provides a web interface where you can:

🧪 Test all available tools and operations
🔍 Inspect request/response schemas
🐛 Debug server connectivity and authentication
✅ Validate your Firefly III configuration

📖 See full development guide

Running Tests

# Run all tests
make test-all

# Run with coverage
make coverage

# Run specific test types
make test-unit
make test-integration

Local Development

# Development with .env file
make dev

# Direct execution
uv run firefly-mcp
python -m firefly_mcp.main

📋 Environment Variables Reference

Variable	Default	Description
`FIREFLY_API_URL`	`https://firefly.dev.nlocal/api/v1`	Your Firefly III API base URL
`FIREFLY_API_TOKEN`	(required)	Personal Access Token from Firefly III
`FIREFLY_DISABLE_SSL_VERIFY`	`false`	Disable SSL verification for development
`FIREFLY_DIRECT_MODE`	`false`	Enable individual tools for each operation
`FIREFLY_ENABLED_ENTITIES`	`account`	Comma-separated list of entities to enable
`FIREFLY_LOG_LEVEL`	`INFO`	Logging level (DEBUG, INFO, WARNING, ERROR)

🎯 API Compatibility

This MCP server is compatible with Firefly III API v1. It has been tested with:

✅ Firefly III v6.x

🤝 Contributing

Fork the repository
Create a feature branch
Make your changes
Add tests for new functionality
Run the test suite
Submit a pull request

📄 License

This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). See the LICENSE file for details.

Available Tools

5 tools

echoA

Echo a message back to the user

ParametersJSON Schema

Name	Required	Description	Default
`message`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.6/5.0

Behavior4/5

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

The description accurately discloses the tool's behavior (echoing) with no side effects. No annotations exist, so description carries full burden and does so adequately.

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?

The description is a single, efficient sentence that earns its place with no wasted words.

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?

Given the tool's simplicity and the presence of an output schema, the description provides sufficient context for its purpose and behavior.

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

Parameters2/5

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

Schema coverage is 0% and the description does not add meaning beyond the property name 'message'. It fails to compensate for the lack of schema descriptions.

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

Purpose4/5

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

The description clearly states the tool echoes a message back, using a specific verb and resource. However, it does not distinguish from sibling tools, but they are unrelated.

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

Usage Guidelines3/5

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

Usage is implied; no explicit when-to-use or alternatives guidance is provided, but it is straightforward for this simple tool.

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

firefly_executeC

Execute any Firefly III operation dynamically.

Args: entity: Entity type (account, transaction, budget, etc.) operation: Operation name (list, get, create, update, delete, etc.) params: Operation parameters as dictionary

ParametersJSON Schema

Name	Required	Description	Default
`entity`	Yes
`operation`	Yes
`params`	No

TDQS

C2.6/5.0

Behavior1/5

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

No annotations are provided, so the description carries full responsibility for behavioral transparency. It only states that it executes operations dynamically but does not disclose side effects (e.g., whether it creates, updates, or deletes data), error handling behavior, rate limits, or authentication requirements. This is insufficient for an agent to understand the tool's impact.

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

Conciseness4/5

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

The description is concise, with a clear Purpose line followed by an Args section. It avoids verbosity and front-loads the purpose. However, it could be slightly more informative without increasing length significantly, e.g., by referencing sibling tools.

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

Completeness1/5

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

Given the tool's dynamic nature and lack of output schema or annotations, the description is highly incomplete. It does not specify the return format, error messages, or how to discover valid entity-operation combinations. With sibling tools like 'firefly_list_operations' available, it should cross-reference them for completeness.

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

Parameters3/5

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

The schema has 0% description coverage, so the description must compensate. It explains each parameter: entity as a type (e.g., account, transaction), operation as an action (list, get, create, etc.), and params as a dictionary. While this adds some context beyond raw schema, it remains vague with 'etc.' and does not enumerate all valid values, which could lead to incorrect usage.

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

Purpose4/5

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

The description clearly states the tool's purpose: executing Firefly III operations dynamically. It specifies the verb 'execute' and the resource 'Firefly III operation', making it distinct from sibling tools like 'firefly_get_schema' and 'firefly_list_operations' which are about metadata retrieval. However, it lacks specificity about which operations are supported, leaving some ambiguity.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'firefly_list_operations' or 'firefly_get_schema'. It does not mention prerequisites, such as needing to first list operations with 'firefly_list_operations' or that this tool assumes the user knows valid entity-operation pairs.

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

firefly_get_schemaA

Get parameter schema for a specific operation.

Args: entity: Entity type (account, transaction, etc.) operation: Operation name (list, get, etc.)

ParametersJSON Schema

Name	Required	Description	Default
`entity`	Yes
`operation`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.5/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It only says 'Get parameter schema', implying a read operation, but does not disclose behavioral traits such as whether it requires authentication, has rate limits, or any side effects. Minimal information.

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?

The description is extremely concise, with one line for the purpose and two lines for argument descriptions. It is front-loaded and every sentence adds value without redundancy.

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

Completeness3/5

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

Given the simplicity (2 params, no nested objects) and presence of an output schema (not described), the description is adequate but not complete. It does not explain that the output is a schema useful for subsequent calls to firefly_execute, nor does it leverage context from siblings to guide the agent.

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 description coverage is 0%, yet the description adds meaningful explanations for both parameters: 'entity: Entity type (account, transaction, etc.)' and 'operation: Operation name (list, get, etc.)'. This provides context beyond the bare schema titles, though examples could be more exhaustive.

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?

The description clearly states 'Get parameter schema for a specific operation', specifying the verb ('Get') and resource ('parameter schema'). This distinguishes it from siblings like firefly_execute (executes) and firefly_list_operations (lists operations).

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives (e.g., before calling firefly_execute). The description only lists arguments, lacking context like 'Use this to determine required parameters for an operation before executing it.'

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

firefly_list_operationsB

List all available Firefly III operations.

Args: entity: Optional entity filter (account, transaction, etc.)

ParametersJSON Schema

Name	Required	Description	Default
`entity`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.3/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that the tool lists operations with an optional entity filter, but omits details like whether the list is filtered by permissions, the nature of operations (e.g., predefined or user-specific), or any side effects. The description fails to add behavioral context beyond the basic functionality.

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?

The description is extremely concise with two short sentences. The main purpose is front-loaded in the first sentence, and the parameter description follows logically. No unnecessary words are present; every part earns its place.

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

Completeness3/5

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

Given the tool has an output schema (not shown), the description doesn't need to detail return values. The tool is simple with one optional parameter. However, the description lacks details about the entity filter's format and what 'operations' entails, which could leave the agent uncertain about how to use it effectively.

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

Parameters3/5

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

The description adds some meaning to the single parameter 'entity' by mentioning it as an optional filter with examples ('account, transaction, etc.'). However, schema description coverage is 0%, so the description should compensate more. The examples are vague and lack specificity, leaving interpretation open.

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?

The description clearly states the verb 'list' and the resource 'all available Firefly III operations', which directly communicates the tool's function. The optional entity filter adds specificity. The purpose is distinct from sibling tools like firefly_execute (which executes an operation) and firefly_get_schema (which retrieves schemas).

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives or when not to use it. It doesn't mention prerequisites, exclusions, or comparative context despite having sibling tools that could benefit from such clarification.

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

get_versionB

Get the version of the Firefly MCP server

ParametersJSON Schema

Name	Required	Description	Default
`random_string`	No		dummy

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3/5.0

Behavior2/5

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

No annotations are provided, and the description only states 'get the version', implying a read operation. It does not disclose any behavioral traits such as idempotency, cost, or side effects, leaving the agent to assume minimal behavior.

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?

The description is a single concise sentence with 10 words, containing no redundant information. It is front-loaded with the key action and resource.

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

Completeness3/5

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

The tool is simple (get version) and has an output schema, so the description does not need to explain return values. However, the lack of parameter documentation makes it incomplete for an agent that may need to understand the optional parameter.

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

Parameters1/5

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

The input schema has one optional parameter 'random_string' with a default, but the description does not mention this parameter or explain its purpose. With 0% schema description coverage, the agent has no guidance on how to use the parameter.

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?

The description 'Get the version of the Firefly MCP server' clearly states the action (get) and the resource (version of Firefly MCP server). It distinguishes itself from sibling tools like echo or firefly_execute, which serve different purposes.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or contextual cues for usage.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

5 tool updatesv0.1.0Jun 10, 2026
- First observedecho
- First observedfirefly_execute
- First observedfirefly_get_schema
- First observedfirefly_list_operations
- First observedget_version

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0

Disambiguation4/5

Tools have distinct purposes: echo for testing, get_version for server info, and the firefly_ tools for dynamic API access. However, firefly_execute is a broad catch-all that could be confused with many specific operations, but its name clearly indicates dynamic execution.

Naming Consistency3/5

Three tools follow a consistent firefly_ prefix pattern, but echo and get_version break this convention. This inconsistency could confuse agents expecting uniform naming.

Tool Count5/5

Five tools is well-scoped for a dynamic API wrapper. The single executor tool reduces the need for many individual endpoints, making the set compact and manageable.

Completeness5/5

The dynamic firefly_execute tool can perform any Firefly III operation, ensuring full coverage. Supporting meta-tools for schema and operation listing compensate for the lack of explicit endpoints.

Maintenance

ActivityInactive

ResponsivenessUnresponsive

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
237
wimmOAuth
my.wimm
Personal finance for AI agents — onboard, import statements, categorize & budget over MCP.
Finance Data Platforms
2
ManiloOAuth
app.manilo
Log, query, and edit expenses, budgets, and accounts in Manilo from any MCP-compatible AI assistant.
Finance App Automation
1
Mercado PagoOAuth
com.mercadopago.mcp
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Finance E-commerce & Retail App Automation
2

Related MCP Servers

YNAB MCP Server
Finance Agent Orchestration
calebl
A
license
A
quality
D
maintenance
A Model Context Protocol server that enables AI-powered interaction with YNAB (You Need A Budget) data, allowing users to query their budgets through conversational interfaces.
Updated 8 months ago (2026-01-03 21:37 UTC)
16
38
141
MIT
Lunch Money MCP Server
Finance Customer Data Platforms
MatiasL13
A
license
Not graded
quality
C
maintenance
A Model Context Protocol server that allows AI assistants to interact with Lunch Money accounts, enabling management of transactions, categories, budgets, and other financial data through natural language commands.
Updated a year ago (2025-07-05 04:13 UTC)
MIT
Firefly III MCP Server
Finance
etnperlong
A
license
Not graded
quality
C
maintenance
Enables AI assistants to manage Firefly III personal finance accounts and transactions through the Model Context Protocol.
Updated a year ago (2025-06-12 15:31 UTC)
29
84
MIT
@daften/fireflyiii-mcp
Rizz22
A
license
Not graded
quality
C
maintenance
Connects any MCP-compatible AI assistant to your Firefly III personal finance instance, enabling natural language queries about your finances.
Updated 17 days ago (2026-08-22 12:13 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/horsfallnathan/firefly-iii-mcp-server'

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