ConvOps
Book a demo Start free
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. One line of config. The process shows up inside 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 with 98 tools: tasks, workflows, memory, pools, schedules 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 runs 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 standard. 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. It has since been adopted across many AI clients and developer tools.

What is the difference between MCP and an API?

An API is built for programs whose developers read its documentation. MCP describes capabilities so an AI model can discover and call them itself, with names, descriptions and input schemas. MCP servers often call APIs underneath.

related

What does MCP connect to?

Attended executionYou drive the AI. The engine supplies the steps.Agentic workflowA process the AI runs step by step, checked by an engine.Dual attributionEvery change records the agent and the signed-in person, separately.
Connect your clientAttended executionMCP serverSkills vs MCP vs workflows
your next step

Teach it once. Then let it run.

on your ownStart freeConnect your AI tool in one line. Nothing to install.with your teamBook a demoWe show ConvOps on your team's real work.keep readingDual attributionEvery change records the agent and the signed-in person, separately.