Monitoring and observability · MCP server
MCPSpend: MCP server, setup and security
MCPSpend is an open-source MCP server that lets an AI agent track MCP tool spending by tool, project and end customer. Its repository has 66 stars and its last commit is from August 31, 2026 and it is licensed under MIT.
What MCPSpend does
According to its repository: “Real-time cost observability for MCP tool calls: a transparent proxy that attributes spend per tool, project and end customer.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. MCPSpend is listed under Monitoring and observability, a category of 57 servers in the directory, where it ranks #19 by stars.
Topics declared by the repository: ai-agents, ai-observability, claude-desktop, cost-tracking, cursor, llm-cost.
Installing and connecting MCPSpend
Distribution modes declared in the official MCP registry:
- npm package (Node.js, usually started with
npx)
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript. Listed systems: macOS, Windows, Linux.
The registry lists one secret variable to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for MCPSpend:
- Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on May 22, 2026, the andreisirbu91-lab/MCPSpend repository has 66 stars and 3 forks, with 0 open issues. It has more stars than 58% of the servers in the directory. Last change 2 months ago. Version published in the registry: 0.2.1 (May 25, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
MCPSpend is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- Requires an API key or token
Avoid if…
- You do not want to give credentials to an agent
Alternatives
- Netdata81.1K ★
- MCP grafana3.6K ★
- Openstatus9.2K ★
- OneUptime7.8K ★
- Homebutler305 ★
- SolidPing26 ★
Learn more
Frequently asked questions
How do I install MCPSpend?
MCPSpend is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of andreisirbu91-lab/MCPSpend.
Is MCPSpend free?
The code is published under the MIT licence and can be used free of charge. It needs an API key: the service it connects to may be paid.
Is MCPSpend safe?
Points to watch: secrets. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by andreisirbu91-lab on GitHub. Check who maintains it before giving it access.
What are the alternatives to MCPSpend?
In the same category: Netdata, MCP grafana, Openstatus, and OneUptime. Netdata and MCP grafana score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score