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.
A
- Action lakePlatform and integrationAn 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.
- Agent intentControl and proofAgent 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.
- Agent plan (saved procedure)Platform and integrationAn 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.
- Agent spending caps and budgetsControl and proofAn 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.
- Agentic workflowAI agentsAn 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.
- AI agentAI agentsAn 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.
- AI agent audit logControl and proofAn 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.
- AI agent permissions (least privilege)Control and proofAI 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.
C
- Canonical verbsPlatform and integrationA 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.
- Credential vault (secret isolation for AI agents)Control and proofA 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.
- Cross-system joinPlatform and integrationA 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.
D
- Dedicated egress IPPlatform and integrationA 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.
- Dry run (for agent actions)Control and proofA 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.
H
I
M
- MCP clientModel Context ProtocolAn 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.
- MCP gatewayModel Context ProtocolAn 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.
- MCP serverModel Context ProtocolAn 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.
- MCP toolModel Context ProtocolAn 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.
- Model Context Protocol (MCP)Model Context ProtocolThe 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.
O
P
R
- Rate limiting for AI agentsControl and proofRate 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.
- Remote MCP serverModel Context ProtocolA 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.
S
T
- Tamper-evident ledger (hash chain)Control and proofA 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.
- Tool calling (function calling)AI agentsTool 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.
- Tool overloadModel Context ProtocolTool 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.
U
- Unified API vs MCPPlatform and integrationA 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.
- Upstream callPlatform and integrationAn 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.
Connect an agent. Start free.
100,000 calls free every month. No card. Hard caps on every key.