What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in November 2024, for connecting AI applications to external tools and data sources, such as a CRM, database or file store, through a common interface.Load more
Also known as: MCP.
Glossary · 01 BuildModel Context Protocol (MCP), in practice
Before MCP, every connection between an AI model and another system had to be built separately. MCP defines a standard way for an application to expose tools and data to a model, so one integration can be used by any compatible AI client.
For go-to-market teams, MCP matters in two ways. Internally, it lets AI assistants read from and act on systems such as the CRM, enrichment tools and analytics, which makes research, data clean-up and reporting faster. Externally, a SaaS product that offers an MCP server can be used directly from inside AI assistants.
Connecting a model to live systems carries risk. Permissions, data access and which actions an assistant can take without a person approving them need to be set deliberately.
How Surge45 builds it
MCP is set up in Build, alongside RevOps and your data tools. Where it helps, we connect AI assistants to your CRM and data tools through MCP for research, enrichment checks and reporting, with read-only access by default and human approval for any change to records.
Read next
GTM engineering
GTM engineering is building the systems that run a company's go-to-market: data, enrichment, scoring, outbound sequencing, routing and CRM workflows, engineered so pipeline is created by a repeatable process rather than individual effort.
llms.txt
llms.txt is a proposed plain-text file placed at a website's root that summarises the site for large language models and links to its key pages. It is a proposal, not an adopted standard.
Data enrichment
Data enrichment is adding missing information to account and contact records, such as company size, industry, technology used, job title, verified email and phone number, from external data providers.
RevOps
RevOps (revenue operations) brings the operations of marketing, sales and customer success under one function, with shared systems, data, processes and reporting, so the whole revenue process is run and measured as one.
