--- title: "AI agent and MCP glossary: 30 terms - actionlake" description: "Plain definitions of MCP, MCP servers and gateways, tool calling, agent permissions, approvals, audit logs, spending caps and more, each with sources." canonical: https://actionlake.com/glossary updated: 2026-10-26 --- Glossary # AI agent and MCP glossary Short, sourced definitions of the terms that come up when you connect AI agents to business systems: the Model Context Protocol and its parts, how agents call tools, and the controls that keep them in bounds. Each entry starts with a one-sentence definition, then explains how it works, what goes wrong, and how actionlake handles it. Sources were checked on 22 October 2026. 30 terms Updated 24 October 2026 ## A - [Action lake Platform and integration An action lake is a governed layer between AI agents and business systems where every action an agent may take is defined, every action it takes is authorised and priced, and every action it took is recorded, independent of the model, framework or vendor.](https://actionlake.com/glossary/action-lake) - [Agent intent Control and proof Agent intent is the one-sentence reason an AI agent states for an action, recorded with the action itself, so anyone reading the record later can tell what the agent was trying to do and judge whether the action fitted that purpose.](https://actionlake.com/glossary/agent-intent) - [Agent plan (saved procedure) Platform and integration An agent plan is a saved, versioned procedure of actions, cross-system joins, loops, waits and approval steps that an AI agent writes once and that then runs the same way on demand or on a schedule, without the model re-deciding every step.](https://actionlake.com/glossary/agent-plan) - [Agent spending caps and budgets Control and proof An agent spending cap is a hard limit on how much a single AI agent credential may spend or call in a period, checked before each request is sent, so that a looping or misbehaving agent stops at the limit instead of after it.](https://actionlake.com/glossary/agent-spending-cap) - [Agentic workflow AI agents An agentic workflow is a multi-step process in which a language model plans or performs some of the steps with tools, ranging from fixed code paths that call a model at set points to open-ended agents that choose every step.](https://actionlake.com/glossary/agentic-workflow) - [AI agent AI agents An AI agent is software in which a language model decides its own next steps and tool calls in a loop, using results from its environment, until a goal is met or a stopping condition is reached.](https://actionlake.com/glossary/ai-agent) - [AI agent audit log Control and proof An AI agent audit log is a record of every action an agent took: which credential ran it, what it did, in which system, with what outcome and cost, and why, kept so a person can reconstruct and verify events later.](https://actionlake.com/glossary/agent-audit-log) - [AI agent permissions (least privilege) Control and proof AI agent permissions are the rules that decide which systems, actions and data an agent's credential may reach, and least privilege for agents means granting only the actions a task needs and enforcing that limit outside the model.](https://actionlake.com/glossary/ai-agent-permissions) ## C - [Canonical verbs Platform and integration A canonical verb is one standard name for the same operation across every system that supports it, written domain.object.operation, such as service.ticket.create, so an agent learns an action once and can run it against any connected system.](https://actionlake.com/glossary/canonical-verb) - [Credential vault (secret isolation for AI agents) Control and proof A credential vault for AI agents stores the API keys and OAuth tokens for business systems encrypted outside the agent, and uses them on the agent's behalf only at the moment of each call, so the model, its prompt and its logs never contain a vendor secret.](https://actionlake.com/glossary/credential-vault) - [Cross-system join Platform and integration A cross-system join combines records from two or more separate systems that refer to the same real-world thing, such as one customer in an accounting ledger and a ticket desk, and returns a single combined answer.](https://actionlake.com/glossary/cross-system-join) ## D - [Dedicated egress IP Platform and integration A dedicated egress IP is one static public IP address reserved for a single customer, from which all of that customer's outbound requests to vendor APIs and databases leave, so the vendor or a firewall can allow-list it.](https://actionlake.com/glossary/dedicated-egress-ip) - [Dry run (for agent actions) Control and proof A dry run checks whether an agent's action would succeed, whether it is allowed and what it would cost, by validating the inputs, permissions and connection without sending anything to the vendor.](https://actionlake.com/glossary/dry-run) ## H - [Human-in-the-loop approval Control and proof Human-in-the-loop approval is a control that pauses an AI agent's action until a named person approves or rejects it, so high-impact or irreversible actions never run on the model's judgement alone.](https://actionlake.com/glossary/human-in-the-loop-approval) ## I - [Idempotency key Platform and integration An idempotency key is a unique value attached to a write request so that if the same request is delivered twice, after a timeout or a retry, the server performs it once and returns the stored result for the repeat.](https://actionlake.com/glossary/idempotency-key) ## M - [MCP client Model Context Protocol An MCP client is the component inside an AI application that holds one connection to one MCP server, fetches that server's tool list and passes the model's tool calls to it.](https://actionlake.com/glossary/mcp-client) - [MCP gateway Model Context Protocol An MCP gateway is a single MCP endpoint that sits between AI agents and many systems, holding the credentials and enforcing permissions, limits and logging on every tool call that passes through it.](https://actionlake.com/glossary/mcp-gateway) - [MCP server Model Context Protocol An MCP server is a program that offers tools, resources and prompts to AI applications over the Model Context Protocol, usually by wrapping one system's API, such as a ticket desk or an accounting ledger.](https://actionlake.com/glossary/mcp-server) - [MCP tool Model Context Protocol An MCP tool is a named function that an MCP server offers to AI models, described by a name, a plain-language description and a JSON Schema for its input, and invoked with a tools/call request.](https://actionlake.com/glossary/mcp-tool) - [Model Context Protocol (MCP) Model Context Protocol The Model Context Protocol (MCP) is an open standard that lets an AI application connect to external systems and discover and call their tools, read their resources and use their prompts through one JSON-RPC message format.](https://actionlake.com/glossary/mcp) ## O - [OAuth for MCP (dynamic client registration) Model Context Protocol OAuth for MCP is the authorisation flow the MCP specification defines for remote servers, in which an MCP client discovers the server's authorisation server, registers itself, sends the person to sign in and consent, and then calls the server with a short-lived, audience-bound access token.](https://actionlake.com/glossary/oauth-dynamic-client-registration) ## P - [Prompt injection (tool-use risk) Control and proof Prompt injection is an attack in which text that a language model reads, typed by a user or hidden in a web page, email, document or tool result, changes the model's behaviour, and in a tool-using agent it can turn into real actions.](https://actionlake.com/glossary/prompt-injection) ## R - [Rate limiting for AI agents Control and proof Rate limiting for AI agents controls how many requests an agent can make in a time window, both to the platform it calls and to each vendor API behind it, so a fast or looping agent cannot exhaust a shared quota or trigger lockouts.](https://actionlake.com/glossary/rate-limiting-for-agents) - [Remote MCP server Model Context Protocol A remote MCP server runs on the internet rather than on your computer, and AI clients reach it over HTTPS using the Streamable HTTP transport, usually after an OAuth sign-in.](https://actionlake.com/glossary/remote-mcp-server) ## S - [Streamable HTTP transport Model Context Protocol Streamable HTTP is the standard MCP transport for remote servers: the client sends each JSON-RPC message as an HTTP POST to one endpoint, and the server answers with a JSON object or a Server-Sent Events stream.](https://actionlake.com/glossary/streamable-http) ## T - [Tamper-evident ledger (hash chain) Control and proof A tamper-evident ledger is an append-only record in which each entry stores a cryptographic hash of its own contents together with the previous entry's hash, so any later edit, deletion or reordering breaks every hash after it and becomes detectable.](https://actionlake.com/glossary/tamper-evident-ledger) - [Tool calling (function calling) AI agents Tool calling, also called function calling, is a language model's ability to answer with a structured request to run a named function with arguments, which the application executes before handing the result back to the model.](https://actionlake.com/glossary/tool-calling) - [Tool overload Model Context Protocol Tool overload is the loss of accuracy and context space that happens when an AI model is given more tool definitions than it can reliably choose between; Anthropic's documentation says Claude's tool selection degrades once more than 30 to 50 tools are available.](https://actionlake.com/glossary/tool-overload) ## U - [Unified API vs MCP Platform and integration A unified API normalises many vendors in one category behind a single common schema for developers to code against, while MCP is a protocol that lets an AI model discover and call each system's own tools at run time; the two solve different problems and are often combined.](https://actionlake.com/glossary/unified-api-vs-mcp) - [Upstream call Platform and integration An upstream call is one HTTP request that actionlake sent to a vendor's API on your behalf and that returned a definitive, attributable response; it is the unit actionlake meters and bills.](https://actionlake.com/glossary/upstream-call) ## Connect an agent. Start free. [Start free](https://actionlake.com/console?start=sandbox) [Read the quickstart](https://actionlake.com/docs/quickstart) 100,000 calls free every month. No card. Hard caps on every key. --- Source: https://actionlake.com/glossary More: https://actionlake.com/llms.txt