The short answer
The Model Context Protocol (MCP) is an open protocol that lets AI applications and agents connect to external tools and data sources through a standard interface. An MCP server exposes tools; an MCP client — such as an AI assistant or IDE — discovers and calls them.
At a glance
- Term
- Model Context Protocol (MCP)
- Also known as
- MCP · MCP server
- Category
- Developers & AI agents
- Where it matters
- AI agents and integrations
Model Context Protocol in practice
MCP replaces one-off integrations with a common contract: a server describes its tools and their inputs, and any compatible client can use them. Remote servers are commonly reached over Streamable HTTP with bearer-token authentication.
Why Model Context Protocol matters
- Agents can use live, specialised data instead of guessing from training data.
- One server works with many clients.
Model Context Protocol in MarketPrior
MarketPrior runs an MCP server at /mcp (Streamable HTTP, Bearer auth) with tools for company search, reports, diligence runs, alerts, the lead trigger feed, contacts and exports. It uses the same scoped API keys, quotas and credits as the REST API.