ADK MCP
About
Documentation and assembly review for @nhtio/adk.
Details
- Author
- Unknown
- Categories
- Developer Tools, Knowledge Base
Jump to
This page is about the thing you give to another agent when you want it to help with ADK without making it guess.
The docs site is for humans. The API reference is for humans. TheAssemblysection is for humans who can read a page, hold three constraints in their head, and come back to the editor with the right shape. Coding agents do not work like that. They need the same knowledge, but they need it in the place where they are already working: inside their tool loop.
Install this MCP server in your coding agent, then ask the agent to use the ADK tools before it writes ADK setup code.
Recommended for teams and shared project config:
The ADK MCP is alocal Model Context Protocol servershipped inside the@nhtio/adknpm package. When an MCP-capable coding agent starts it, the server opens a stdio connection and exposes ADK-specific tools, resources, and prompts.
It carries a packaged documentation corpus built at publish time:
- the hand-written documentation pages;
- the generated TypeDoc API reference;
- the changelog copied into the docs build;
- the ADK assembly Skill and its reference notes.
The important word ispackaged. The MCP server does not scrape the live docs site, does not call a hosted search API, and does not depend on your editor's web access once the npm package has resolved. The docs it serves are the docs that shipped with that version of@nhtio/adk.
If your agent installs@nhtio/adk@1.20260817.0, the MCP server answers from the docs and API reference packaged with@nhtio/adk@1.20260817.0. That is the difference between "look up ADK" and "look up the ADK I am actually using."
Not a second documentation site.The canonical prose still lives here. The MCP is the portable, tool-shaped copy for an agent runtime.
Not a model.It does not reason on its own. Your coding agent chooses when to call it, reads the result, and decides what to do next.
Not a privileged workspace tool.It does not need an ADK project path. It does not write files. It reads its packaged corpus and reviews code you paste or the agent passes to it.
Not a project introspection tool.It will not inspect your repository and infer which ADK version you use. It only knows the package version you launched. That is why pinned MCP config matters.
Not a replacement for understanding the seam.It will remind the agent that storage callbacks are required, that the executor mustack()ornack(), and that history belongs in input middleware. It will not make a vague integration correct by magic.
Every stdio MCP server is a local process. This one is intentionally boring — it serves packaged markdown and simple review tools — but your MCP client is right to ask for trust before starting it.
MCP clients often make local servers look scarier than they are because they are approving a process launch, not reading the server's source code. Here is the shape of this one:
- Network:no network access is required after npm resolves the package.
- Corpus:read-only markdown/JSON packaged with the installed npm package.
- Filesystem:reads its own packaged corpus file; it does not read your project files or home directory.
- Shell:executes no shell commands after your MCP client starts it.
- Tools:deterministic tool list with plain string inputs; no hidden dynamic tool discovery from the network.
The trust prompt is still correct. Startingnpx -y @nhtio/adk@1.20260817.0means your client is launching local code from npm. Pin the version, review the package you install, and keep MCP approval on for anything that can modify your workspace.
The server exposes one resource collection, five tools, and three prompts.
The tool payloads are intentionally small and boring:
Tell your agent: "Use the ADK MCP before you answer." That one sentence usually prevents the two classic mistakes: inventing nonexistent helper APIs and omitting required storage callbacks.
You need an MCP-capable client and a Node runtime new enough to run the package. ADK itself requires Node 18 or newer.
The examples below usenpxbecause it is the common denominator across coding agents. If your environment standardizes onpnpm dlx,yarn dlx, orbunx, use the equivalent command only if your MCP client supports it.
Different agents put MCP configuration in different places, but the server shape is the same everywhere: stdio transport, commandnpx, args-yand the package spec. The examples below use@nhtio/adk@1.20260817.0; replace1.20260817.0with the ADK version in your project.
{ "servers": { "adk": { "type": "stdio", "command": "npx", "args": ["-y", "@nhtio/adk@1.20260817.0"] } } }
claude mcp add --transport stdio adk -- npx -y @nhtio/adk@1.20260817.0
{ "mcpServers": { "adk": { "command": "npx", "args": ["-y", "@nhtio/adk@1.20260817.0"] } } }
{ "mcpServers": { "adk": { "command": "npx", "args": ["-y", "@nhtio/adk@1.20260817.0"] } } }
{ "mcpServers": { "adk": { "command": "npx", "args": ["-y", "@nhtio/adk@1.20260817.0"] } } }
{ "mcpServers": { "adk": { "command": "npx", "args": ["-y", "@nhtio/adk@1.20260817.0"], "disabled": false, "autoApprove": [] } } }
name: ADK MCP version: 0.0.1 schema: v1 mcpServers: - name: ADK docs type: stdio command: npx args: - -y - "@nhtio/adk@1.20260817.0"
- VS Code / GitHub Copilot:use the command palette entry for MCP user or workspace configuration, or commit.vscode/mcp.jsonwhen the team should share the server.
- Claude Code:the CLI command above writes the config for you. Add--scope projectif the project should carry a shared.mcp.json.
- Claude Desktop:editclaude_desktop_config.jsonfrom the Developer settings screen, then restart Claude Desktop.
- Cursor:add the JSON to Cursor's MCP configuration for the workspace or user profile.
- Windsurf:edit~/.codeium/windsurf/mcp_config.json, or use the MCP settings UI if available.
- Cline / Roo Code:open the MCP Servers settings from the extension panel and paste the JSON entry undermcpServers.
- Continue:put the YAML block in a file under.continue/mcpServers/, or use Continue's supported JSON import path if you are sharing config with another MCP client.
Uselatestonly when you are experimenting. For shared config, prefer the same package version your project depends on instead of whatever npm resolves as latest that day.
{ "command": "npx", "args": ["-y", "@nhtio/adk@1.20260817.0"] }
Once your client starts the server, the ADK tools should appear next to that client's other MCP tools. Some clients make you explicitly enable the server, approve tool calls, or restart the agent session after editing config.
Use get_adk_assembly_guidance, then cite the specific ADK doc/API section you are relying on before proposing code.
Use the ADK MCP first. Help me assemble the smallest correct @nhtio/adk TurnRunner with explicit storage callbacks, a mock executor, hydration in the input pipeline, and a smoke test.
Use review_adk_assembly on this setup before suggesting changes. Prioritize missing callbacks, executor ack/nack mistakes, message hydration, and tool registry wiring.
Use search_adk_docs and lookup_adk_api to debug this ADK error. Do not invent helper APIs; cite the ADK contract you are relying on.
Use lookup_adk_api for TurnRunnerConfig and explain which callbacks are required for a no-op prototype.
If your client supports MCP prompts as slash commands or prompt templates, use the server prompts directly:
- assemble-adk-agentfor a new integration;
- review-adk-agentfor existing code;
- debug-adk-assemblyfor a failing setup.
If your client supports MCP resources, attachadk://...resources when you want the agent to read a full page instead of a search excerpt.
The MCP is opinionated in the same way ADK is opinionated: it wants the seam to be explicit before code starts moving.
The order matters. Read the assembly contract first, search the specific seam second, write code third. That is slower than guessing for about five minutes and faster than debugging a half-built runner for an afternoon.
Do not let it inventToolRegistry.fromTools. Do not let it put conversation history directly on raw input instead of hydrating through middleware. Do not let it omit persistence callbacks because the prototype "doesn't need storage." If the prototype wants a no-op, it still has to say so out loud.
Use this website when you are learning the model. Use the MCP when another agent is helping you apply it.
That split is deliberate. Humans need the story:How agents work,What ADK is,The Loop, thenAssembly. Agents need a tool surface that says: search here, read this page, check this code, now proceed.
The MCP is that surface. A Skill with legs. A docs site that can ride along in the agent's own loop.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.
Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Remote, no-auth MCP server providing AI-powered codebase context and answers
Official Svelte MCP server, provides docs and suggestions on the generated code.
Structured .aide spec files that give AI agents progressive disclosure into your codebase architecture. 6 MCP tools, 8 slash commands, TUI wizard, multi-IDE support.
Assists AI developers with requirement clarification, module design, and technical architecture.
AmazingMCP — MCP Server for .NET / C# Codebases
An MCP server that gives AI agents deep understanding of C# codebases via Roslyn — type search, dependency graphs, usage analysis, and architecture overviews, all from a live in-memory compilation.
Automatically generates documentation for code repositories by analyzing directory structures and code files using the OpenRouter API.
MCP server that ingests project docs once and lets Claude search by meaning instead of reading everything — saving tokens on large codebases
Enforce consistent C++ style and best practices across your codebase. Analyze naming conventions, memory safety, and const correctness, and get actionable modernization suggestions up to C++23. Accelerate reviews with ready-made prompts and quick access to curated guidelines.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
