Definition
Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data through one uniform interface. A system exposes its capabilities once as an MCP server — typed tools, readable resources, prompts — and any MCP-capable client can discover and invoke them, replacing a bespoke integration per assistant with a write-once contract.
Key takeaways
- The Model Context Protocol (MCP) is an open standard letting AI assistants connect to external tools and data uniformly.
- It replaces per-assistant integrations with a write-once server contract that any MCP-capable client can discover and use.
- Its explicit, typed capabilities make it a natural seam for governance — destructive operations can be gated, not auto-run.
- Planoda's MCP server gates external agents through the same propose/approve broker and audit trail as internal ones.
Before a standard existed, every AI assistant needed custom glue for every tool it touched, an N×M integration problem that scaled badly. MCP defines a common contract instead: a server advertises the actions an AI can take, the data it can read, and reusable prompts, and any compliant client connects, discovers what's available, and calls it with validated arguments. The result is interoperability — the same tool serves many assistants, and the same assistant reaches many tools.
Because MCP makes capabilities explicit and typed, it is also a natural seam for governance. The protocol describes what an agent could do; a server is free to decide what it should do, gating destructive operations behind approval rather than executing them on the model's say-so. A well-built MCP server treats dangerous actions as proposals a human or policy confirms.
Planoda ships an MCP server that exposes its tools to external AI assistants and routes their destructive operations through the same propose/approve broker and audit trail as internal agents — so connecting an outside model doesn't open an ungoverned side door.
Related terms
- MCP ServerAn MCP server implements the Model Context Protocol, an open standard that lets AI assistants connect to external tools and data through a uniform interface. Rather than building a bespoke integration per assistant, a tool exposes one MCP server describing its available actions and resources, and any MCP-capable AI can discover and use them safely.
- Tool CallingTool calling is the capability that lets a language model invoke external functions — query a database, search the web, create a record — by emitting a structured request the surrounding system executes. Instead of only producing text, the model can take actions and pull in live data, turning it from a text generator into the reasoning core of an agent.
- Tool registryA tool registry is the single, authoritative catalog of the actions an AI agent may call, with each tool's name, typed arguments, and risk classification declared in one place. It is the source of truth a governance broker consults to decide whether a call is safe to run or must be gated — so capability and destructiveness are properties of the registry, not scattered per-caller decisions.
- Agent broker (propose/approve broker)An agent broker is the runtime component that sits between an AI agent and the actions it wants to take, deciding per call whether to execute inline, require human approval, or refuse. It is where propose/approve governance is actually enforced — the gate is code in the request path, not a guideline in a prompt — so an agent literally cannot run a destructive tool without passing through it.
- AI AgentAn AI agent is a software system that uses a large language model to pursue a goal across multiple steps — reading context, choosing tools, and taking actions — rather than answering a single prompt. In a work platform, agents triage issues, draft updates, and execute multi-step tasks as autonomous teammates, bounded by the permissions and approvals their operators set.