What can you do with this server?

My Finance MCP Server enables Claude to act as an AI bookkeeper for personal finance tracking through natural language interactions. Core capabilities: * Store financial transactions - Upload unstructured documents (receipts, statements, CSVs) and Claude extracts structured data including date, amount, description, and category, persisting to both ChromaDB for vector search and JSON ledger for backup in ~/.my_finance_mcp/ * Semantic search - Query financial history using natural language (e.g., "How much did I spend on groceries last month?") to find relevant transactions across all stored data * List transactions - Browse stored transactions with pagination, optional category filtering, and view transaction indices * Delete transactions - Remove specific entries by index or wipe all data with confirmation * Analyze spending patterns - Ask Claude about portfolio positions, spending trends, allocations, and other financial insights from your data

How do I use My Finance 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., "@My Finance MCP Server how much did I spend on dining out last month?" 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.

My Finance MCP Server

by xinrong-meng

Overview Schema Related Servers Score Discussions

Python

Local

My Finance MCP Server

Bare-bones Model Context Protocol server that lets Claude store personal finance transactions and later query them via semantic search. Transactions are persisted in ChromaDB for vector search plus a JSON ledger for backup.

Run it alongside Claude Desktop and you get an AI bookkeeper that remembers your receipts, statements, and portfolios—then answers natural language questions about spending trends, allocations, or anything else you upload.

Setup

Install

uv sync

Run

uv run my_finance_mcp.py

Configure Claude Desktop

Add to ~/.claude_desktop_config.json:

{
  "mcpServers": {
    "my-finance": {
      "command": "uv",
      "args": [
        "run",
        "--project",
        "/path/to/my_finance",
        "/path/to/my_finance/my_finance_mcp.py"
      ]
    }
  }
}

Related MCP server: Finance MCP Server

Usage

Exposed tools:

store_transactions(transactions) – ingest structured transactions (Claude will extract them from uploaded docs)
query_financial_history(query) – run semantic search across everything stored
list_transactions(limit=20, offset=0, category=None) – page through the JSON ledger to inspect what’s saved and see each transaction’s index
delete_transactions(indices=None, delete_all=False, confirm=False) – delete entries by index or wipe them all (requires confirm=True)

Upload financial data to Claude
Say: "Store this transaction data"
Claude calls the MCP server to save it
Later ask: "How much did I spend on groceries last month?"
Claude searches your historical data via MCP
Use "Show me the stored transactions" or "Delete transaction xx" to invoke the management tools

Example Claude Desktop interaction

User: Remember these portfolio positions for later analysis.
Claude: I'll help you store your portfolio positions from the uploaded CSV file for later analysis. Let me read the file and process the data..
Perfect! I've stored your portfolio positions from November 6, 2025 in your finance system. Here's a summary of what was recorded:...

User: List my stored transactions
Claude: Here are your current stored transactions (4 total):...

User: Delete VXUS - International Stock ETF transaction
Claude: The VXUS - International Stock ETF transaction has been successfully deleted from your stored transactions.

User: List all transactions
Claude: Here are your current stored transactions (3 total):...

Data Storage

~/.my_finance_mcp/financial_data/ - ChromaDB vector database (created automatically)
~/.my_finance_mcp/transactions.json - JSON backup of all transactions

Set the MY_FINANCE_MCP_DIR environment variable before launching Claude if you want to store data in a different directory.

Available Tools

4 tools

delete_transactionsA

Delete transactions from both the JSON ledger and ChromaDB.

Args:
    indices: List of transaction indices (from list_transactions) to delete
    delete_all: Set to true to delete all transactions
    confirm: Must be true to actually perform deletion (safety guard)

Returns:
    Status message describing the deletion result

ParametersJSON Schema

Name	Required	Description	Default
`indices`	No
`delete_all`	No
`confirm`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it's a destructive operation (deleting from two data stores), includes a safety guard (confirm parameter), and describes the return value. However, it doesn't mention potential side effects like data irreversibility or error conditions, leaving some gaps.

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 appropriately sized and front-loaded: the first sentence states the purpose clearly, followed by a structured Args and Returns section. Every sentence earns its place by providing critical information without redundancy, making it efficient and easy to parse.

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 complexity (destructive operation with 3 parameters), no annotations, and an output schema (which handles return values), the description is mostly complete. It covers purpose, parameters, and safety, but could improve by mentioning prerequisites (e.g., needing list_transactions first) or error cases, slightly reducing completeness.

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

Parameters5/5

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

The schema description coverage is 0%, so the description must compensate fully. It does so by clearly explaining all three parameters: indices (list from list_transactions), delete_all (set to true for all), and confirm (safety guard). This adds essential meaning beyond the bare schema, making the parameters understandable and actionable.

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 specific action ('Delete transactions') and resources ('from both the JSON ledger and ChromaDB'), distinguishing it from sibling tools like list_transactions (read-only) and store_transactions (create/update). It precisely defines what the tool does beyond just restating the name.

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?

The description implies usage by referencing list_transactions for indices, but does not explicitly state when to use this tool versus alternatives like query_financial_history or store_transactions. It provides some context (e.g., using indices from list_transactions) but lacks clear exclusions or comparative guidance with other tools.

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

list_transactionsA

List stored transactions from the JSON ledger with optional pagination and filtering.

Args:
    limit: Maximum number of transactions to return (default 20)
    offset: Number of transactions to skip from the beginning (default 0)
    category: Optional category filter (case-insensitive)

Returns:
    Dictionary containing total count, pagination info, and transactions with index field

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`offset`	No
`category`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.5/5.0

Behavior3/5

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 mentions pagination and filtering capabilities, which adds useful context beyond basic listing. However, it lacks details on permissions, rate limits, error handling, or whether the operation is read-only (implied by 'List' but not explicitly stated).

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 well-structured with a brief overview followed by clearly labeled 'Args' and 'Returns' sections. Every sentence adds value: the first sentence states purpose and features, and the subsequent sections efficiently document parameters and return values without redundancy.

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 moderate complexity (3 parameters, no annotations, but with output schema), the description is fairly complete. It covers purpose, parameters, and return structure. The output schema exists, so the description doesn't need to detail return values, but it could benefit from more behavioral context like error cases or performance notes.

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?

The schema description coverage is 0%, so the description must compensate. It provides clear semantics for all three parameters (limit, offset, category) in the 'Args' section, explaining their purposes and defaults. This adds significant value beyond the bare schema, though it doesn't cover edge cases like format for 'category'.

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 verb 'List' and resource 'stored transactions from the JSON ledger', making the purpose specific and understandable. It distinguishes from siblings like 'delete_transactions' (deletion) and 'store_transactions' (storage), though it doesn't explicitly differentiate from 'query_financial_history' which might have overlapping functionality.

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 mentions 'optional pagination and filtering', which implies usage for retrieving filtered data, but provides no explicit guidance on when to use this tool versus alternatives like 'query_financial_history'. There are no statements about when-not-to-use or prerequisites, leaving usage context vague.

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

query_financial_historyC

Search through all stored financial data using semantic search.

Args:
    query: Search query string to find relevant transactions

Returns:
    Formatted summary of matching transactions with totals

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

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 mentions 'semantic search' which hints at intelligent matching beyond exact terms, but doesn't explain what 'all stored financial data' encompasses, whether there are rate limits, authentication requirements, or how results are formatted beyond 'formatted summary'. For a search tool with zero annotation coverage, this leaves significant behavioral gaps.

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 appropriately concise with three sentences that each serve a purpose: stating the tool's function, describing the parameter, and explaining the return value. It's front-loaded with the core purpose and avoids unnecessary verbiage.

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 (which handles return values) and only one parameter, the description covers the basics: purpose, parameter role, and return type. However, as a search tool with no annotations, it lacks details on behavioral aspects like search scope, limitations, or error handling, making it minimally adequate but with clear gaps.

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 description coverage is 0%, so the description must compensate. It adds that the 'query' parameter is a 'Search query string to find relevant transactions', which provides basic semantic context beyond the schema's title 'Query'. However, it doesn't elaborate on query syntax, examples, or constraints, leaving the parameter only partially documented.

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 as 'Search through all stored financial data using semantic search' - this specifies the verb (search), resource (financial data), and method (semantic search). However, it doesn't explicitly differentiate from sibling tools like 'list_transactions' which might also retrieve financial data, leaving room for ambiguity about when to use semantic search versus listing.

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 'list_transactions' or 'store_transactions'. It doesn't mention scenarios where semantic search is preferred over other methods, nor does it specify prerequisites or exclusions for usage.

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

store_transactionsA

Parse and store transaction data from uploaded financial documents.

If you receive unstructured financial data (statements, receipts, CSV files, etc.),
extract transactions into the format: [{"date": "YYYY-MM-DD", "amount": number, "description": "string", "category": "string"}]

Args:
    transactions: List of transaction dictionaries, each containing:
        - date: Transaction date (string, format: YYYY-MM-DD)
        - amount: Transaction amount (number, can be negative for expenses)
        - description: Transaction description (string)
        - category: Transaction category (string, optional, e.g. "Food", "Transport", "Bills")

Returns:
    Success message with count of stored transactions

ParametersJSON Schema

Name	Required	Description	Default
`transactions`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.3/5.0

Behavior3/5

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

With no annotations provided, the description carries full burden. It describes the core behavior (parsing and storing transactions) and specifies the expected input format, but doesn't disclose important behavioral traits like authentication requirements, error handling, rate limits, or whether this is a mutating operation (implied by 'store' but not explicitly stated).

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 well-structured and appropriately sized. It begins with the core purpose, provides usage context, details the expected format, and explains the return value. Every sentence adds value with no redundant information.

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 complexity (parsing and storing financial data), no annotations, and an output schema present, the description is reasonably complete. It explains the transformation process and return value, though could benefit from more behavioral context about the storage operation itself (e.g., whether it overwrites existing data).

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by providing detailed parameter semantics. It explains the 'transactions' parameter structure, lists all required fields (date, amount, description, category), specifies data types and formats, and provides examples of category values.

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 tool's purpose with specific verbs ('parse and store') and resources ('transaction data from uploaded financial documents'). It distinguishes from siblings by focusing on storage rather than deletion, listing, or querying operations.

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?

The description provides clear context for when to use this tool ('If you receive unstructured financial data...'), but doesn't explicitly mention when not to use it or name specific alternatives among the sibling tools. The guidance is helpful but lacks explicit exclusions.

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.

4 tool updatesv1.0.0Jan 4, 2026
- Addeddelete_transactions
- Addedlist_transactions
- Changedquery_financial_history1 field changed
  - addedInput schema / title
```
Added value: +"query_financial_historyArguments"
```
- Changedstore_transactions1 field changed
  - addedInput schema / title
```
Added value: +"store_transactionsArguments"
```
2 tool updatesNov 7, 2025
- First observedquery_financial_history
- First observedstore_transactions

Install Server

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

TDQS

B3.4/5.0

Disambiguation5/5

Each tool has a distinct and non-overlapping purpose: list_transactions retrieves data, store_transactions adds new data, delete_transactions removes data, and query_financial_history performs semantic search. The descriptions clearly differentiate their functions, with no ambiguity in selection.

Naming Consistency4/5

Three tools follow a consistent verb_noun pattern (list_transactions, store_transactions, delete_transactions), but query_financial_history deviates slightly with a different verb style. The naming is still readable and mostly predictable, with only minor inconsistency.

Tool Count3/5

With only 4 tools, the set feels thin for a finance management server, lacking operations like update_transactions, get_transaction_by_id, or category management. While the tools cover basic CRUD and search, the scope suggests more functionality is needed for comprehensive financial handling.

Completeness2/5

There are significant gaps in the tool surface for a finance domain. The server supports create (store_transactions), read (list_transactions, query_financial_history), and delete (delete_transactions), but lacks update operations (e.g., modify_transaction) and essential features like budget tracking, reporting, or category CRUD, which will limit agent effectiveness.

Maintenance

ActivityInactive

ResponsivenessSyncing

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

Era ContextOAuth
app.era
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
Finance Knowledge & Memory
1
Zenfinance AOAuth
tech.zenfin
Household finance memory, budgets, transactions, and monthly reviews for AI assistants.
Finance
2
Candor Finance BOAuth
money.candor
Personal-finance workspace for AI agents: accounts, spending, budgets, goals, and investments.
Agent Orchestration Finance
101
KachinkOAuth
io.github.ahmadsl
Personal finance tracker — log transactions, view summaries, and browse a dashboard
Finance Note Taking File Systems
2

Related MCP Servers

MCP Agent - AI Expense Tracker
Finance Autonomous Agents App Automation
dev-muhammad
A
license
Not graded
quality
D
maintenance
Enables AI agents to manage personal expenses through natural language conversations. Supports adding, searching, and analyzing transactions with automatic categorization and financial insights.
Updated 10 months ago (2025-10-31 07:48 UTC)
3
MIT
Finance MCP Server
Finance Databases
taylor3lewis
F
license
Not graded
quality
D
maintenance
Enables personal finance tracking through Claude Desktop using natural language to manage income and expenses with persistent SQLite storage. Supports adding and deleting transactions, checking balances, and viewing spending summaries grouped by category or month.
Updated 5 months ago (2026-04-04 01:20 UTC)
-
Finance Tracker MCP Server
Finance Payments & Billing
ID45
A
license
Not graded
quality
D
maintenance
AI-powered personal finance analysis through Claude AI using Plaid integration, enabling natural language queries about transactions, subscriptions, budgets, and spending trends.
Updated 4 months ago (2026-04-29 00:57 UTC)
1
MIT
Expense Tracker MCP Server
Finance Databases
ArProvat
A
license
Not graded
quality
D
maintenance
Enables users to manage personal expenses through natural conversation with Claude, including adding, updating, deleting expenses, and viewing summaries by category or date range.
Updated 5 months ago (2026-04-05 11:39 UTC)
3
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/xinrong-meng/my-finance-mcp'

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