github · pelikhan · Dec 27, 2025 · Dec 27, 2025 · Dec 27, 2025 · Dec 27, 2025
diff --git a/docs/package-lock.json b/docs/package-lock.json
diff --git a/docs/src/content/docs/examples/issue-pr-events/projectops.md b/docs/src/content/docs/examples/issue-pr-events/projectops.md
@@ -136,7 +136,7 @@ Analyze the issue and add it to the organization project board...
 ```
 
 This configuration ensures:
-1. The GitHub MCP toolset can query repository and project information
+1. The GitHub Model Context Protocol (MCP) toolset can query repository and project information
 2. The `update-project` safe output can modify the organization project
 3. Both operations use the same token with appropriate permissions
 

diff --git a/docs/src/content/docs/examples/scheduled/research-planning.md b/docs/src/content/docs/examples/scheduled/research-planning.md
@@ -28,7 +28,7 @@ Maintains and updates project planning issues with current priorities, ensuring
 ### Basic Research
 Searches for information on a given topic, analyzes results, and creates structured summaries with relevant sources. Triggered manually via workflow_dispatch with research topic input. Workflow file: `.github/workflows/research.md`
 
-### MCP Inspector
+### Model Context Protocol (MCP) Inspector
 Analyzes all [MCP](/gh-aw/reference/glossary/#mcp-model-context-protocol) configuration files, extracts server details, and generates comprehensive inventory reports to maintain visibility into available [MCP servers](/gh-aw/reference/glossary/#mcp-server) and their capabilities. Runs weekly on Mondays at 10am UTC, or manually via workflow_dispatch. Workflow file: `.github/workflows/mcp-inspector.md`
 
 > [!WARNING]

diff --git a/docs/src/content/docs/guides/custom-safe-outputs.md b/docs/src/content/docs/guides/custom-safe-outputs.md
@@ -72,7 +72,7 @@ The agent can now call `slack-notify` with a message, and the custom job execute
 
 ## Architecture
 
-Custom safe outputs separate read and write operations: agents use read-only MCP servers with `allowed:` tool lists, while custom jobs handle write operations with secret access after agent completion.
+Custom safe outputs separate read and write operations: agents use read-only Model Context Protocol (MCP) servers with `allowed:` tool lists, while custom jobs handle write operations with secret access after agent completion.
 
 ```text
 ┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐

diff --git a/docs/src/content/docs/guides/getting-started-mcp.md b/docs/src/content/docs/guides/getting-started-mcp.md
@@ -5,7 +5,7 @@ sidebar:
   order: 2
 ---
 
-This guide walks you through integrating MCP servers with GitHub Agentic Workflows, from your first configuration to advanced patterns.
+This guide walks you through integrating Model Context Protocol (MCP) servers with GitHub Agentic Workflows, from your first configuration to advanced patterns.
 
 ## What is MCP?
 

diff --git a/docs/src/content/docs/guides/packaging-imports.md b/docs/src/content/docs/guides/packaging-imports.md
@@ -50,7 +50,7 @@ Remote imports are automatically cached in `.github/aw/imports/` by commit SHA.
 
 ## Example: Modular Workflow with Imports
 
-Create a shared MCP server configuration in `.github/workflows/shared/mcp/tavily.md`:
+Create a shared Model Context Protocol (MCP) server configuration in `.github/workflows/shared/mcp/tavily.md`:
 
 ```yaml wrap
 ---

diff --git a/docs/src/content/docs/guides/researchplanassign.md b/docs/src/content/docs/guides/researchplanassign.md
@@ -11,7 +11,7 @@ The strategy follows three distinct phases:
 
 ### Phase 1: Research
 
-A research agent (typically scheduled daily or weekly) investigates the repository under a specific angle and generates a comprehensive report. Using advanced MCP tools for deep analysis (static analysis, logging data, semantic search), it examines the codebase from a specific perspective and creates a detailed discussion or issue with findings, recommendations, and supporting data. Cache memory maintains historical context to track trends over time.
+A research agent (typically scheduled daily or weekly) investigates the repository under a specific angle and generates a comprehensive report. Using advanced Model Context Protocol (MCP) tools for deep analysis (static analysis, logging data, semantic search), it examines the codebase from a specific perspective and creates a detailed discussion or issue with findings, recommendations, and supporting data. Cache memory maintains historical context to track trends over time.
 
 ### Phase 2: Plan
 

diff --git a/docs/src/content/docs/guides/security.md b/docs/src/content/docs/guides/security.md
@@ -11,7 +11,7 @@ sidebar:
 Security is foundational -- Agentic Workflows inherits GitHub Actions' sandboxing model, scoped permissions, and auditable execution. The attack surface of agentic automation can be subtle (prompt injection, tool invocation side‑effects, data exfiltration), so we bias toward explicit constraints over implicit trust: least‑privilege tokens, allow‑listed tools, and execution paths that always leave human‑visible artifacts (comments, PRs, logs) instead of silent mutation.
 
 A core reason for building Agentic Workflows as a research demonstrator is to closely track emerging security controls in agentic engines under near‑identical inputs, so differences in behavior and guardrails are comparable. Alongside engine evolution, we are working on our own mechanisms:
-highly restricted substitutions, MCP proxy filtering, and hooks‑based security checks that can veto or require review before effectful steps run.
+highly restricted substitutions, Model Context Protocol (MCP) proxy filtering, and hooks‑based security checks that can veto or require review before effectful steps run.
 
 We aim for strong, declarative guardrails -- clear policies the workflow author can review and version -- rather than opaque heuristics. Lock files are fully reviewable so teams can see exactly what was resolved and executed. This will keep evolving; we would love to hear ideas and critique from the community on additional controls, evaluation methods, and red‑team patterns.
 

diff --git a/docs/src/content/docs/guides/web-search.md b/docs/src/content/docs/guides/web-search.md
@@ -5,7 +5,7 @@ sidebar:
   order: 15
 ---
 
-This guide shows how to add web search to workflows using the Tavily MCP server, an AI-optimized search provider designed for LLM applications. While alternatives exist (Exa, SerpAPI, Brave Search), this guide focuses on Tavily configuration.
+This guide shows how to add web search to workflows using the Tavily Model Context Protocol (MCP) server, an AI-optimized search provider designed for LLM applications. While alternatives exist (Exa, SerpAPI, Brave Search), this guide focuses on Tavily configuration.
 
 ## Tavily Search
 

diff --git a/docs/src/content/docs/introduction/architecture.mdx b/docs/src/content/docs/introduction/architecture.mdx
@@ -7,7 +7,7 @@ sidebar:
 
 import { Aside } from '@astrojs/starlight/components';
 
-GitHub Agentic Workflows implements a defense-in-depth security architecture that protects against prompt injection, rogue MCP servers, and malicious agents. This document provides visual diagrams of the key security mechanisms.
+GitHub Agentic Workflows implements a defense-in-depth security architecture that protects against prompt injection, rogue Model Context Protocol (MCP) servers, and malicious agents. This document provides visual diagrams of the key security mechanisms.
 
 ## Overview
 

diff --git a/docs/src/content/docs/introduction/how-it-works.mdx b/docs/src/content/docs/introduction/how-it-works.mdx
@@ -25,7 +25,7 @@ Analyze this issue and provide helpful triage comments...
 
 Workflows support **GitHub Copilot** (default), **Claude Code**, and **Codex**. Each [engine](/gh-aw/reference/engines/) interprets natural language instructions and executes them using configured tools and permissions.
 
-## Tools and MCPs
+## Tools and Model Context Protocol (MCP)
 
 Workflows use [tools](/gh-aw/reference/tools/) through the **Model Context Protocol (MCP)** — a standardized protocol for connecting AI agents to external tools and services — for GitHub operations, external APIs, file operations, and custom integrations.
 

diff --git a/docs/src/content/docs/reference/compilation-process.md b/docs/src/content/docs/reference/compilation-process.md
@@ -76,7 +76,7 @@ The compilation process generates specialized jobs based on workflow configurati
 |-----|---------|---------|------------------|
 | **pre_activation** | Role checks, stop-after deadlines, skip-if-match, or command triggers | Validates permissions, deadlines, and conditions before AI execution | None (runs first) |
 | **activation** | Always | Prepares workflow context, sanitizes event text, validates lock file freshness | `pre_activation` (if exists) |
-| **agent** | Always | Core job that executes AI agent with configured engine, tools, and MCP servers | `activation` |
+| **agent** | Always | Core job that executes AI agent with configured engine, tools, and Model Context Protocol (MCP) servers | `activation` |
 | **detection** | `safe-outputs.threat-detection:` configured | Scans agent output for security threats before processing | `agent` |
 | **Safe output jobs** | Corresponding `safe-outputs.*:` configured | Process agent output to perform GitHub API operations (create issues/PRs, add comments, upload assets, etc.) | `agent`, `detection` (if exists) |
 | **conclusion** | Always (if safe outputs exist) | Aggregates results and generates workflow summary | All safe output jobs |

diff --git a/docs/src/content/docs/reference/engines.md b/docs/src/content/docs/reference/engines.md
@@ -13,7 +13,7 @@ Claude and Codex engines are available but marked as experimental. They are not
 
 ### GitHub Copilot CLI
 
-GitHub Copilot is the default and recommended AI engine for most workflows. The [GitHub Copilot CLI](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/use-copilot-cli) provides MCP server support and is designed for conversational AI workflows.
+GitHub Copilot is the default and recommended AI engine for most workflows. The [GitHub Copilot CLI](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/use-copilot-cli) provides Model Context Protocol (MCP) server support and is designed for conversational AI workflows.
 
 ```yaml wrap
 engine: copilot

diff --git a/docs/src/content/docs/reference/environment-variables.md b/docs/src/content/docs/reference/environment-variables.md
@@ -20,7 +20,7 @@ GitHub Agentic Workflows supports environment variables in 13 distinct contexts:
 | **Container** | `container.env` | Container runtime | Container settings |
 | **Services** | `services.<id>.env` | Service containers | Database credentials |
 | **Sandbox Agent** | `sandbox.agent.env` | Sandbox runtime | Sandbox configuration |
-| **Sandbox MCP** | `sandbox.mcp.env` | MCP gateway | MCP debugging |
+| **Sandbox MCP** | `sandbox.mcp.env` | Model Context Protocol (MCP) gateway | MCP debugging |
 | **MCP Tools** | `tools.<name>.env` | MCP server process | MCP server secrets |
 | **Safe Inputs** | `safe-inputs.<name>.env` | Safe-input execution | Tool-specific tokens |
 | **Safe Outputs Global** | `safe-outputs.env` | All safe-output jobs | Shared safe-output config |

diff --git a/docs/src/content/docs/reference/frontmatter-full.md b/docs/src/content/docs/reference/frontmatter-full.md
@@ -824,7 +824,7 @@ network:
     # '*.example.com' and ecosystem names like 'python', 'node')
 
 # Sandbox configuration for AI engines. Controls agent sandbox (AWF or Sandbox
-# Runtime) and MCP gateway.
+# Runtime) and Model Context Protocol (MCP) gateway.
 # (optional)
 # This field supports multiple formats (oneOf):
 

diff --git a/docs/src/content/docs/reference/frontmatter.md b/docs/src/content/docs/reference/frontmatter.md
@@ -24,7 +24,7 @@ tools:
 
 The frontmatter combines standard GitHub Actions properties (`on`, `permissions`, `run-name`, `runs-on`, `timeout-minutes`, `concurrency`, `env`, `environment`, `container`, `services`, `if`, `steps`, `cache`) with GitHub Agentic Workflows-specific elements (`description`, `source`, `github-token`, `imports`, `engine`, `strict`, `roles`, `features`, `safe-inputs`, `safe-outputs`, `network`, `tools`).
 
-Tool configurations (such as `bash`, `edit`, `github`, `web-fetch`, `web-search`, `playwright`, `cache-memory`, and custom MCP servers) are specified under the `tools:` key. Custom inline tools can be defined with the `safe-inputs:` key. See [Tools](/gh-aw/reference/tools/) and [Safe Inputs](/gh-aw/reference/safe-inputs/) for complete documentation.
+Tool configurations (such as `bash`, `edit`, `github`, `web-fetch`, `web-search`, `playwright`, `cache-memory`, and custom Model Context Protocol (MCP) servers) are specified under the `tools:` key. Custom inline tools can be defined with the `safe-inputs:` key. See [Tools](/gh-aw/reference/tools/) and [Safe Inputs](/gh-aw/reference/safe-inputs/) for complete documentation.
 
 ### Trigger Events (`on:`)
 

diff --git a/docs/src/content/docs/reference/imports.md b/docs/src/content/docs/reference/imports.md
@@ -96,7 +96,7 @@ Only one agent file can be imported per workflow. See [Custom Agent Files](/gh-a
 
 Imported files can define `tools:`, `mcp-servers:`, `services:`, and `safe-outputs:` frontmatter (other fields trigger warnings). Agent files can also define `name` and `description`. These fields are merged with the main workflow's configuration.
 
-### Tools and MCP Servers
+### Tools and Model Context Protocol (MCP) Servers
 
 ```aw wrap
 # Base workflow

diff --git a/docs/src/content/docs/reference/permissions.md b/docs/src/content/docs/reference/permissions.md
@@ -102,7 +102,7 @@ Run `gh aw compile workflow.md` to validate permissions. Common errors include u
 Some tools require specific permissions to function:
 
 - **`agentic-workflows`**: Requires `actions: read` to access workflow logs and run data
-- **GitHub MCP toolsets**: See [Tools](/gh-aw/reference/tools/) for GitHub API permission requirements
+- **GitHub Model Context Protocol (MCP) toolsets**: See [Tools](/gh-aw/reference/tools/) for GitHub API permission requirements
 
 The compiler validates these requirements and provides clear error messages when permissions are missing.
 

diff --git a/docs/src/content/docs/reference/safe-outputs.md b/docs/src/content/docs/reference/safe-outputs.md
@@ -53,7 +53,7 @@ Custom safe output types: [Custom Safe Output Jobs](/gh-aw/guides/custom-safe-ou
 
 ### Custom Safe Output Jobs (`jobs:`)
 
-Create custom post-processing jobs registered as MCP tools. Support standard GitHub Actions properties and auto-access agent output via `$GH_AW_AGENT_OUTPUT`. See [Custom Safe Output Jobs](/gh-aw/guides/custom-safe-outputs/).
+Create custom post-processing jobs registered as Model Context Protocol (MCP) tools. Support standard GitHub Actions properties and auto-access agent output via `$GH_AW_AGENT_OUTPUT`. See [Custom Safe Output Jobs](/gh-aw/guides/custom-safe-outputs/).
 
 ### Issue Creation (`create-issue:`)
 

diff --git a/docs/src/content/docs/reference/sandbox.md b/docs/src/content/docs/reference/sandbox.md
@@ -8,7 +8,7 @@ sidebar:
 The `sandbox` field configures sandbox environments for AI engines, providing two main capabilities:
 
 1. **Agent Sandbox** - Controls the agent runtime security (AWF or Sandbox Runtime)
-2. **MCP Gateway** - Routes MCP server calls through a unified HTTP gateway
+2. **Model Context Protocol (MCP) Gateway** - Routes MCP server calls through a unified HTTP gateway
 
 ## Configuration
 

diff --git a/docs/src/content/docs/reference/tokens.md b/docs/src/content/docs/reference/tokens.md
@@ -18,7 +18,7 @@ For GitHub Agentic Workflows, you only need to create a few **optional** secrets
 | Copilot workflows (CLI, engine, agent tasks, etc.)   | `COPILOT_GITHUB_TOKEN`                 | Needs Copilot Requests permission and repo access. |
 | Assigning agents/bots to issues or pull requests     | `GH_AW_AGENT_TOKEN`                    | Used by `assign-to-agent` and Copilot assignee/reviewer flows. |
 | Any GitHub Projects v2 operations                    | `GH_AW_PROJECT_GITHUB_TOKEN`           | **Required** for `update-project`. Default `GITHUB_TOKEN` cannot access Projects v2 API. |
-| Isolating MCP server permissions (advanced optional) | `GH_AW_GITHUB_MCP_SERVER_TOKEN`        | Only if you want MCP to use a different token than other jobs. |
+| Isolating Model Context Protocol (MCP) server permissions (advanced optional) | `GH_AW_GITHUB_MCP_SERVER_TOKEN`        | Only if you want MCP to use a different token than other jobs. |
 
 Create these as **repository secrets in *your* repo**. The easiest way is to use the GitHub Agentic Workflows CLI:
 

diff --git a/docs/src/content/docs/reference/tools.md b/docs/src/content/docs/reference/tools.md
@@ -48,7 +48,7 @@ tools:
   web-search:  # Search the web (engine-dependent)
 ```
 
-**Note:** Some engines require third-party MCP servers for web search. See [Using Web Search](/gh-aw/guides/web-search/).
+**Note:** Some engines require third-party Model Context Protocol (MCP) servers for web search. See [Using Web Search](/gh-aw/guides/web-search/).
 
 ## GitHub Tools (`github:`)
 

diff --git a/docs/src/content/docs/setup/cli.md b/docs/src/content/docs/setup/cli.md
@@ -200,7 +200,7 @@ Commands are organized by workflow lifecycle: creating, building, testing, monit
 Initialize your repository for agentic workflows.
 
 ```bash wrap
-gh aw init         # Configure .gitattributes, Copilot instructions (MCP enabled by default)
+gh aw init         # Configure .gitattributes, Copilot instructions (Model Context Protocol (MCP) enabled by default)
 gh aw init --no-mcp # Skip MCP server integration
 ```
 

diff --git a/docs/src/content/docs/setup/mcp-server.md b/docs/src/content/docs/setup/mcp-server.md
@@ -12,7 +12,7 @@ Start the server:
 gh aw mcp-server
 ```
 
-Or configure for any MCP host:
+Or configure for any Model Context Protocol (MCP) host:
 ```yaml wrap
 command: gh
 args: [aw, mcp-server]

diff --git a/docs/src/content/docs/troubleshooting/common-issues.md b/docs/src/content/docs/troubleshooting/common-issues.md
@@ -75,7 +75,7 @@ tools:
 ```
 
 :::tip[Migrate to Toolsets]
-If you're using the `allowed:` pattern with GitHub tools, consider migrating to `toolsets:` for better maintainability. Tool names may change between MCP server versions, but toolsets provide a stable API. See [Migration from Allowed to Toolsets](/gh-aw/guides/mcps/#migration-from-allowed-to-toolsets).
+If you're using the `allowed:` pattern with GitHub tools, consider migrating to `toolsets:` for better maintainability. Tool names may change between Model Context Protocol (MCP) server versions, but toolsets provide a stable API. See [Migration from Allowed to Toolsets](/gh-aw/guides/mcps/#migration-from-allowed-to-toolsets).
 :::
 
 ### Toolset Missing Expected Tools

diff --git a/docs/src/content/docs/troubleshooting/errors.md b/docs/src/content/docs/troubleshooting/errors.md
@@ -314,7 +314,7 @@ workflow file '[path]' already exists. Use --force to overwrite
 
 ## Safe Output Errors
 
-### Failed to Parse Existing MCP Config
+### Failed to Parse Existing Model Context Protocol (MCP) Config
 
 **Error Message:**
 

diff --git a/examples/README.md b/examples/README.md
@@ -11,13 +11,13 @@ For examples of network configuration with package registries and CDNs:
 
 See the [Network Configuration Guide](../docs/src/content/docs/guides/network-configuration.md) for more information.
 
-## MCP Gateway Examples
+## Model Context Protocol (MCP) Gateway Examples
 
 This directory also contains MCP Gateway configuration files for the `mcp-gateway` command.
 
 ## What is MCP Gateway?
 
-The MCP Gateway is a proxy server that connects to multiple MCP (Model Context Protocol) servers and exposes all their tools through a single HTTP endpoint. This allows clients to access tools from multiple MCP servers without managing individual connections.
+The MCP Gateway is a proxy server that connects to multiple Model Context Protocol (MCP) servers and exposes all their tools through a single HTTP endpoint. This allows clients to access tools from multiple MCP servers without managing individual connections.
 
 ## Example Configurations