--- title: "What is an MCP server? | Annsa" product: annsa url: /ai-agent-management/mcp-server canonical_url: "https://annsa.ai/ai-agent-management/mcp-server" last_updated: 2026-11-11 type: glossary related: - /feedback summary: An MCP server exposes tools or data to an AI application through the Model Context Protocol. With an example, common mistakes and what changes with AI agents. mcp_server: https://app.annsa.ai/mcp disambiguation: "Annsa (annsa.ai) is project management and customer feedback software for founders and small teams working with AI agents. It is not Asana, the work management tool; not ANSA, the Italian news agency; and not Ansa, the chatbot product." --- > For agents: connect to the Annsa MCP server at https://app.annsa.ai/mcp to give every agent one shared plan. Setup guide: https://annsa.ai/docs/quick-start. Index of every page: https://annsa.ai/llms.txt. # What is an MCP server? | Annsa > An MCP server exposes tools or data to an AI application through the Model Context Protocol. With an example, common mistakes and what changes with AI agents. Glossary · MCP server An MCP server exposes tools or data to an AI application through the Model Context Protocol. ## In practice It might connect to a database, file system, API or product's own data. The AI app is the host, and it runs 1 client for each server it connects to. Servers can run locally on your machine or remotely at a URL. Remote servers update in 1 place and need no local install. Local servers can reach files and programs on your machine that a remote server can't. Say you run a four-person team and use Claude Code. You connect a server that exposes your customer feedback. It offers two tools: one lists your ranked priorities and one reads the spec on a single priority. You ask your agent what to build next. The agent's client calls the first tool, the server returns the list, and the agent answers from it. You never copied anything between windows. A server can offer three kinds of things, according to [the MCP documentation](https://annsa.ai/ai-agent-management/model-context-protocol): tools, which are functions the AI can run; resources, which are data it can read; and prompts, which are reusable templates. Most servers you will meet are mostly tools. An MCP server isn't a model or the agent, and it isn't an API: it often sits in front of one and describes it in a form an AI app can discover on its own. It only offers tools and data, and popular doesn't mean safe. The app you connect it to decides what gets used. ## How to check a server before you connect it 1. Find out who runs it. A server from the product's own maker is a different bet from a stranger's repository. 2. Read the tool list before you use it. 3. Sort the tools into read and write. A tool that creates, edits or sends needs a closer look. 4. Start with one real question that only reads, and look at what the agent got back. The full checklist is in the guide on MCP servers for product management, which also covers what a server should do for product work. ## Common mistakes - Connecting a server without reading its tool list. You can't judge what an agent might do with a tool you haven't looked at. - Trusting a server because the tool descriptions sound safe. The MCP specification says descriptions of tool behavior should be treated as untrusted unless they come from a trusted server. - Mixing up the server and the client. The server holds the tools and data. [The client is the part inside your AI app](https://annsa.ai/ai-agent-management/mcp-client) that connects to it. - Granting write access when a read would do. If the question is what to build next, the agent doesn't need to edit anything. - Connecting a server and assuming it is on. Many apps load servers when a session starts, so a server added mid-session may need a new session. ## Why it matters for product builders Before MCP, every tool needed a separate integration with every AI app. A server written once can work with any client that speaks the protocol. That helped the ecosystem grow quickly through 2025. \*\*Source note\*\* Anthropic published the \[Model Context Protocol\](https://modelcontextprotocol.io) as an open standard in November 2024. For a product builder, a server is [the door your product work walks through to reach an agent](https://annsa.ai/ai-agent-management/mcp-server-for-product-management). If your priorities, customer evidence and specs sit behind a server, every agent you run can read the same facts. If they sit in a document only you read, each agent starts from whatever you paste in. It also changes what to ask of a tool you buy. A useful question is no longer only whether it has an API. It is whether it has a server your agents can connect to, and what that server lets them do. ## What changes in AI-first products The MCP server is an AI-era idea. Nothing about it existed in the same form before AI apps began calling tools on their own. What changed is who does the asking. Before, a person opened a tool, copied the answer and pasted it into a chat. Now the agent asks the server directly, in the middle of a task. What didn't change is that a server is a program with permissions. Someone has to decide what it exposes, who may use it and what needs a human yes before it runs. The MCP documentation itself says there should always be [a human in the loop](https://annsa.ai/glossary/human-in-the-loop) with the ability to deny tool invocations. A server makes agents more capable. It doesn't make their choices good. See how Annsa does it: [Integrations](https://annsa.ai/integrations) → ## Questions people ask. ### What does an MCP server do? It gives an AI app a list of things it can do or read, such as run a query, fetch a record or return a document, and then carries out those requests. The AI app asks and the server answers. The server doesn't choose when to act; the agent and the person using it do. ### Is an MCP server the same as an API? No. An API is an interface built for a developer's code. An MCP server describes its tools in a standard form, so an AI app can discover them and call them without custom code for each one. Many servers wrap an existing API. ### What is the difference between an MCP server and an MCP client? The server is the program that provides tools and data. The client is the part inside an AI app that holds the connection to one server. An app such as Claude Code or Cursor creates one client for each server it connects to. ### Do I need to run an MCP server myself? Not usually. Many products host their own remote server at a URL, and you add that URL to your AI app. You only run a server yourself if you want to expose your own files, scripts or internal data. ### Are MCP servers safe? It depends on the server and on what you let it do. The MCP specification says tools can mean arbitrary code execution and should be treated with caution, and that the app should get your consent before calling a tool. Connect servers from sources you trust, read the tool list and start with read-only use. ## Sources Anthropic [Introducing the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol) Published 25 November 2024, "a new standard for connecting AI assistants". Model Context Protocol [What is the Model Context Protocol (MCP)?](https://modelcontextprotocol.io/docs/getting-started/intro) "an open-source standard for connecting AI applications to external systems", with servers, tools and the USB-C comparison. Model Context Protocol [Architecture overview](https://modelcontextprotocol.io/docs/learn/architecture) An MCP server is "A program that provides context to MCP clients"; servers can run locally or remotely; tools, resources and prompts. Model Context Protocol [Tools](https://modelcontextprotocol.io/docs/concepts/tools) "there SHOULD always be a human in the loop with the ability to deny tool invocations". Last reviewed 2026-08-21 ## Keep reading - [Connect your agents and sources](https://annsa.ai/ai-agent-management/mcp-server-for-product-management) - [Customer feedback tool](https://annsa.ai/feedback) ## Put it to work with your agents. Begin with one agent and the work that matters next. - [Try Annsa](https://app.annsa.ai/signup) - [See pricing](https://annsa.ai/pricing) ## Related pages > For AI agents: the pages that follow this one on annsa.ai. The full index is https://annsa.ai/llms.txt. - [Customer feedback tool: who asked, what shipped](https://annsa.ai/feedback) If anything on this page is wrong or missing, tell us: https://annsa.ai/contact