glossary · The process

MCP (Model Context Protocol)

definition

MCP is an open protocol that lets AI clients connect to external servers that provide tools, resources, and context, so the same server works from any client that speaks the protocol.

in one line: The open protocol that plugs ConvOps into your AI tool.

in context

Where does MCP fit?

Keep your tools. Add the process. In ConvOps, one line of config brings the process into the AI tool you already use.

your AI toolClaude, Codex, Cursor
add one linethe server URL
sign inyour workspace
tools appearin the chat
two ways to say it

What is MCP, in plain words?

Same idea at two depths: the plain version, then what the engine actually does.

MCP is how AI tools plug into other systems. Add a server once, and its abilities appear in your chat as if they were built in.

You keep your tool, your model and your subscription.

for engineers

ConvOps is an MCP server whose tools cover tasks, workflows, memory, pools, schedules, metrics, reports and governance.

Works from Claude, Cowork, Codex, Cursor, ChatGPT or any MCP client.

the longer answer

Why does MCP matter?

For users, MCP collapses integration to configuration: adding a server to Claude Code, Cursor, ChatGPT, or any compatible client is a line of config, after which the server's tools appear in the conversation like native abilities.

For products, it inverts the usual architecture. Instead of building an app that embeds an AI, you build a server that plugs into the AI surface people already use. The user keeps their client, their model choice, and their subscription; the server supplies the domain: its data, its actions, its rules.

The protocol was introduced by Anthropic as an open standard in November 2024 and has since been adopted across many AI clients and developer tools. A connection has two roles: the server, which exposes tools, resources and prompts, and the client inside the AI application, which discovers them and passes the model's calls through. Servers run locally over standard input and output, or remotely over HTTP, usually with OAuth sign-in. Because the protocol is shared, a server written once reaches every client that implements it.

in convops

How does MCP work in ConvOps?

ConvOps is built on this inversion: the entire engine (tasks, workflows, memory, pools, schedules, governance) is exposed as an MCP server, which is why the install is one line and there is nothing to migrate.

To connect ConvOps, add https://mcp.convops.app/ to your client. In Claude Code that is one command: claude mcp add --transport http convops https://mcp.convops.app/. On first use the client opens a browser to sign in, and the tools appear in the conversation. ConvOps sells no models: your client keeps its own. The same server entry works from every verified client: Claude Code, Claude including Cowork, OpenAI Codex, ChatGPT, Cursor and OpenCode, so a team can use different tools against one shared process.

questions

What do people ask about MCP?

What is MCP used for?

MCP connects AI applications to external systems through one open standard, and ConvOps uses it to expose its whole engine (tasks, workflows, memory, pools, schedules and governance) as one server. A server exposes tools, resources and prompts, and any compatible client, such as Claude Code, Cursor or ChatGPT, can use them. One server replaces a custom integration per client.

Who created MCP?

Anthropic introduced the Model Context Protocol as an open standard in November 2024. ConvOps is built on it, and the protocol has since been adopted across many AI clients and developer tools, including Claude Code, Codex, Cursor, ChatGPT and OpenCode. Because the protocol is shared, a server written once reaches every client that implements it.

What is the difference between MCP and an API?

ConvOps offers both, which shows the difference. Its REST API is built for scripts and integrations whose developers read the documentation, while its MCP server describes each capability with a name, a description and an input schema, so an AI model can discover and call it itself. MCP servers often call APIs underneath.

Who benefits from MCP besides developers?

Anyone who uses an AI client at work, not only developers. ConvOps relies on MCP so that a finance analyst in ChatGPT, a writer in Claude and an engineer in Claude Code reach the same tasks, workflows and memory without a custom integration, each signing in once from the client they already use.

Do I need to write code to use MCP?

No. With ConvOps, as with most MCP servers, using the protocol is configuration, not code: you add the server's address to your AI client and sign in. For ConvOps that is https://mcp.convops.app/ in the client's MCP settings, or one command in Claude Code, after which its tools appear in the conversation. Code is only needed to build a server of your own.

Does MCP change which AI model I use?

No. MCP connects a client to servers, and the model stays whatever your client uses. ConvOps sells no models, so connecting it leaves your client's model and subscription as they were. The same ConvOps server entry works from every verified client (Claude Code, Claude including Cowork, OpenAI Codex, ChatGPT, Cursor and OpenCode), so a team can mix clients against one shared process.