How do I use web3auth?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@web3auth Search MetaMask Embedded Wallets docs for React quick start" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

web3auth

by honeyvig

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

MetaMask Embedded Wallets MCP Server

Build MetaMask Embedded Wallets integrations faster by giving your AI coding assistant live access to the documentation and deep knowledge of the SDK.

There are two things to set up:

Skill — Teaches your AI assistant how to think about the SDK: architecture, framework quirks, key derivation rules, and common mistakes. No code in the skill; the MCP provides that.
MCP server — Gives your AI assistant real-time access to search docs, fetch examples, and look up SDK types.

MCP Tools

Tool	What it does
`search_docs`	Search documentation and example projects
`get_doc`	Fetch the full content of any doc page
`get_example`	Fetch complete source code of an integration example
`get_sdk_reference`	Fetch SDK types and hooks from the open-source repos
`search_community`	Search the MetaMask Builder Hub for real user issues

Related MCP server: Atlas Docs MCP Server

Skill

The skill teaches your AI assistant the mental model for MetaMask Embedded Wallets. It includes SDK selection logic, key derivation rules, authentication concepts, platform quirks, and common mistakes that aren't obvious from the docs alone.

Tip: For the best experience, use the MCP server alongside the skill so that your LLM can fetch live docs and examples rather than relying on static text.

Universal install (works with 40+ agents)

npx skills add web3auth/skill

The skills CLI by Vercel detects your active AI agent and installs to the right directory automatically — Cursor, Claude Code, Copilot, Kiro, Cline, Codex, Antigravity, and 40+ more.

To install for target a specific agent:

npx skills add web3auth/skill -a cursor     # Cursor only
npx skills add web3auth/skill -a claude-code # Claude Code only

MCP Server Setup

Cursor

The fastest way is one click:

Add MetaMask Embedded Wallets MCP to Cursor

Or install via Cursor Marketplace — search "MetaMask Embedded Wallets".

Or add it manually. Open Cursor Settings → Tools & Integrations → MCP and add:

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io"
    }
  }
}

VS Code (GitHub Copilot)

Install from the Visual Studio Marketplace — search "MetaMask Embedded Wallets", or:

code --install-extension Web3Auth.metamask-embedded-wallets

Or use the one-click install URL:

vscode:mcp/install?{"name":"web3auth","url":"https://mcp.web3auth.io"}

Or add manually to your workspace .vscode/mcp.json:

{
  "servers": {
    "web3auth": {
      "type": "http",
      "url": "https://mcp.web3auth.io"
    }
  }
}

JetBrains (IntelliJ, PyCharm, WebStorm, Android Studio)

Install from the JetBrains Marketplace — search "MetaMask Embedded Wallets".

Or add manually in Settings → Tools → AI Assistant → Model Context Protocol (MCP):

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io",
      "transport": "http"
    }
  }
}

Claude Code CLI

claude mcp add --transport http web3auth https://mcp.web3auth.io

Or add manually to your project's claude.json:

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io"
    }
  }
}

Claude Desktop

Open your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the server to the mcpServers section:

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io"
    }
  }
}

Restart Claude Desktop and ask: "Search MetaMask Embedded Wallets docs for React quick start" to verify the connection.

ChatGPT Desktop

Open ChatGPT Desktop → Settings → Connections and add a new MCP server:

Name: web3auth
URL: https://mcp.web3auth.io

Windsurf

Open Windsurf Settings → MCP and add:

{
  "mcpServers": {
    "web3auth": {
      "serverUrl": "https://mcp.web3auth.io"
    }
  }
}

Or edit ~/.codeium/windsurf/mcp_config.json directly.

Kiro (AWS)

Add to your project's .kiro/settings/mcp.json:

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io"
    }
  }
}

Warp Terminal

In Warp, open Settings → AI → MCP Servers and click Add Server:

Name: web3auth
URL: https://mcp.web3auth.io

Or use Warp's one-click MCP install if available in your version.

Cline (VS Code)

Add to your Cline MCP settings (Ctrl+Shift+P → "Cline: Open MCP Settings"):

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io",
      "transport": "http"
    }
  }
}

Continue.dev

Add to your Continue config.json (open with Ctrl+Shift+P → "Continue: Open config.json"):

{
  "mcpServers": [
    {
      "name": "web3auth",
      "url": "https://mcp.web3auth.io"
    }
  ]
}

Zed

Add to your Zed settings.json (Cmd+, to open):

{
  "context_servers": {
    "web3auth": {
      "command": {
        "path": "npx",
        "args": ["-y", "mcp-remote", "https://mcp.web3auth.io"]
      }
    }
  }
}

Or install via Zed Extensions — search "MetaMask Embedded Wallets".

Antigravity

Open your MCP configuration file:

macOS/Linux: ~/.config/antigravity/mcp.json
Windows: %APPDATA%\antigravity\mcp.json

Add the server to the mcpServers section:

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io"
    }
  }
}

Antigravity hot-reloads MCP config changes — no restart required.

Xcode (via GitHub Copilot)

Xcode 26.3+ supports MCP via GitHub Copilot. Add the server to your Copilot MCP config or use the VS Code extension setup above (Copilot MCP registry is shared).

Alternatively, configure Xcode's agentic tools to point at https://mcp.web3auth.io directly via Settings → Copilot → MCP Servers.

Eclipse (via GitHub Copilot)

Eclipse with GitHub Copilot supports MCP. Add via Eclipse → Preferences → GitHub Copilot → MCP Servers → Add Server:

Name: web3auth
URL: https://mcp.web3auth.io

Neovim (avante.nvim)

In your Lua config, add via mcphub.nvim:

require("mcphub").setup({
  servers = {
    web3auth = {
      url = "https://mcp.web3auth.io",
      transport = "streamable-http",
    },
  },
})

Or using mcp-remote for compatibility:

require("avante").setup({
  mcp = {
    servers = {
      web3auth = {
        command = "npx",
        args = { "-y", "mcp-remote", "https://mcp.web3auth.io" },
      },
    },
  },
})

Neovim (codecompanion.nvim)

require("codecompanion").setup({
  extensions = {
    mcp = {
      servers = {
        web3auth = {
          command = "npx",
          args = { "-y", "mcp-remote", "https://mcp.web3auth.io" },
        },
      },
    },
  },
})

Amp (Sourcegraph)

Add to your Amp MCP configuration:

{
  "mcpServers": {
    "web3auth": {
      "url": "https://mcp.web3auth.io"
    }
  }
}

Goose

Add to ~/.config/goose/config.yaml:

extensions:
  - name: web3auth
    type: http
    url: https://mcp.web3auth.io

5ire

In 5ire Settings → MCP Servers → Add:

Name: web3auth
URL: https://mcp.web3auth.io

Aider

Aider supports MCP via the LiteLLM bridge. Add to your Aider config:

mcp_servers:
  web3auth:
    command: npx
    args: ["-y", "mcp-remote", "https://mcp.web3auth.io"]

Codex CLI

For Codex CLI or any stdio-only agent, use mcp-remote to bridge the HTTP endpoint:

npm install -g mcp-remote

Then add to ~/.codex/config.toml:

[mcp_servers.web3auth]
command = "npx"
args = ["-y", "mcp-remote", "https://mcp.web3auth.io"]

Or add to your agent's JSON config:

{
  "mcpServers": {
    "web3auth": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.web3auth.io"]
    }
  }
}

Static docs (llms.txt)

If your AI tool doesn't support MCP yet, use the static documentation file instead:

https://docs.metamask.io/llms-full.txt

For tools that support the llms.txt spec and can index docs automatically:

https://docs.metamask.io/llms.txt

Warning: The static file is a snapshot and may not include the latest updates. Use the MCP server when possible for always-current docs.

Start building

Once the skill and MCP are set up, ask your AI assistant directly. Good starting prompts:

"Add MetaMask Embedded Wallets to my React app with Google login."
"Set up social login wallets in my Next.js app using Wagmi."
"Integrate embedded wallets in my Flutter app."
"Why are my users getting different wallet addresses after I changed the login method?"

Tip: Use planning mode (where available) for your initial prompt. Review the plan before generating code — this catches architecture mistakes early and avoids config errors that would change wallet addresses in production.

Distribution

This repo ships artifacts for every major developer platform:

Platform	Type	Location
Cursor Marketplace	Plugin	`.cursor-plugin/` + `mcp.json`
VS Code Marketplace	Extension	`plugins/vscode/`
JetBrains Marketplace	Plugin	`plugins/jetbrains/`
Zed Extensions	Extension	`plugins/zed/`
Claude Agent SDK	Plugin	`plugins/claude/`
Raycast Store	Extension	`plugins/raycast/`
ChatGPT GPT Store	Custom GPT	`openai/`
Official MCP Registry	`server.json`	`server.json`
Glama	`glama.json`	`glama.json`
Smithery	Server card	`app/.well-known/mcp/server-card.json/route.ts`
Vercel skills.sh	Skill	`Web3Auth/skill`
agentskill.sh	Skill	`Web3Auth/skill`

Environment Variables

Variable	Required	Description
`GITHUB_TOKEN`	Yes (hosted) / recommended (local)	GitHub personal access token. Required on the Vercel deployment (`mcp.web3auth.io`) — `get_example` and `get_sdk_reference` call the GitHub API heavily; without a token the shared IP hits the 60 req/hr unauthenticated limit quickly. Optional for local stdio use.
`DISCOURSE_API_KEY`	No	Discourse API key for `search_community` (optional; public search works without it)
`DISCOURSE_API_USERNAME`	No	Discourse API username when using `DISCOURSE_API_KEY`

Development

npm install
npm run build
npm test           # Handler smoke tests (mocked fetch)
npm start          # Run via stdio
npm run dev        # Watch mode

Updating Content

What changed	Where to update
SDK architecture, platform quirks, key derivation, workflow	Web3Auth/skill (`SKILL.md`)
New example repository or scan root (e.g. new platform)	`src/content/example-catalog.ts`
New SDK repository or discovery rules (e.g. new platform)	`src/content/sdk-catalog.ts`
New tool or parameter changes	`src/tools/register.ts`
Example folders / SDK file layout within existing repos	Nothing (discovered live from GitHub, cached 4h)
Doc page content	Nothing (fetched live via Algolia / llms.txt / GitHub)

License

MIT

Available Tools

5 tools

get_docB

Read-onlyIdempotent

Fetch the full content of a MetaMask Embedded Wallets documentation page by URL. Sources: Algolia, llms.txt, GitHub MDX.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	A docs.metamask.io URL, e.g. https://docs.metamask.io/embedded-wallets/sdk/react/

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds behavioral context by listing sources (Algolia, llms.txt, GitHub MDX) and specifying 'full content', but it does not disclose return format or potential errors. This is a moderate addition, consistent with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that clearly communicates the core function and includes useful source information without any fluff. It is appropriately concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter and no output schema, the description adequately covers the main purpose and inputs. It lacks details like return format or error handling, but these are minor for a straightforward fetch operation and are not essential given the simplicity and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes the 'url' parameter with an example, and the description merely repeats 'by URL'. With 100% schema coverage, the baseline is 3, and no additional parameter meaning is provided beyond what the schema already offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Fetch'), resource ('documentation page'), and method ('by URL'), making the tool's purpose obvious. However, it does not explicitly differentiate from sibling tools like search_docs or get_example, so it misses the full 5-point criteria.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is provided on when to use this tool versus alternatives. The description implies usage when a URL is available, but it does not mention search_docs or other siblings, nor any exclusions or prerequisites beyond having a URL.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_exampleA

Read-onlyIdempotent

Fetch complete source code of a Web3Auth integration example from GitHub.

ParametersJSON Schema

Name	Required	Description
`name`	No	Example name, e.g. 'React Quick Start' or 'Android Firebase'
`chain`	No	Filter by blockchain family
`category`	No	Filter by category
`platform`	No	Filter by platform
`auth_method`	No	Filter by auth method, e.g. 'auth0', 'firebase', 'google', 'grouped'

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, openWorld, and idempotent hints, so the description carries a lower burden. It adds useful context that the source code comes from GitHub and is 'complete', but does not disclose potential response size or external dependency behaviors beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler words. It immediately states the action and the object, meeting conciseness and structural requirements perfectly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no required parameters and no output schema, the description could clarify whether at least one filter is needed or if name alone suffices to fetch an example. However, the schema itself provides comprehensive parameter documentation, and the tool's purpose is straightforward.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all parameters, each with clear examples and enum definitions. The description does not add additional meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Fetch') and resource ('complete source code of a Web3Auth integration example from GitHub'), clearly distinguishing it from sibling tools like get_doc, get_sdk_reference, and search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies usage for retrieving example source code, and the sibling names provide context for alternatives. However, it does not explicitly state when to use this vs. other tools or mention any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_sdk_referenceA

Read-onlyIdempotent

Fetch SDK source code (types, interfaces, hooks) from open-source Web3Auth repos.

ParametersJSON Schema

Name	Required	Description	Default
`focus`	No	What kind of source to focus on. 'types' = interfaces/types (default, most useful). 'hooks' = React hooks / Vue composables. 'errors' = error types. 'main-class' = SDK implementation. 'all' = everything.	types
`module`	No	Specific SDK module to fetch, e.g. 'core-types', 'react-hooks', 'modal-types', 'main-class'. Omit to get default type definitions. Call without module first to see available modules.
`platform`	Yes	Target platform SDK to fetch source for

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds context that the source comes from open-source repositories, implying public access and no authentication. It also lists example content facets (types, interfaces, hooks). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single concise sentence that front-loads the action ('Fetch SDK source code') and specifies the resource and domain. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only retrieval tool with a detailed schema and three safety hints, the description adequately captures the tool's purpose. No output schema exists, so return format is not required. The description is complete for an agent to decide when to use it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: all three parameters (platform, focus, module) have descriptions with enums and a default. The tool description itself does not add parameter-specific information, so it relies on the schema. With high schema coverage, a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses 'Fetch SDK source code' with a specific resource and domain ('open-source Web3Auth repos'). It clearly distinguishes from sibling tools like get_doc and get_example by focusing on source code rather than documentation or examples.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for retrieving SDK source code, contrasting with siblings for docs/examples. However, it does not explicitly name alternatives or provide exclusion criteria. The module parameter guidance ('Call without module first') offers internal usage help but not inter-tool guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_communityA

Read-onlyIdempotent

Search or fetch posts from the MetaMask Embedded Wallets community forum (builder.metamask.io).

ParametersJSON Schema

Name	Required	Description	Default
`query`	No	Search query, e.g. 'popup blocked safari', 'JWT error', 'Android unstable connection'
`topic_id`	No	Discourse topic ID to fetch the full discussion thread

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe read operation. The description adds minimal context (the forum URL) but does not elaborate on pagination, result structure, or whether query and topic_id can be combined.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the tool's purpose without redundant details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple read-only nature, good annotations, and complete schema, the description is sufficient. It lacks details on result formatting or parameter interaction, but these are not critical for a search/fetch tool with no required parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with detailed descriptions for both query and topic_id. The description's 'Search or fetch posts' reflects these parameters but adds no additional semantic meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Search or fetch posts') and the specific resource ('MetaMask Embedded Wallets community forum'), which distinguishes it from sibling tools like search_docs that target documentation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes it clear that this tool is for community forum posts, implying when to use it. However, it does not explicitly state exclusions or alternatives, such as 'for documentation use search_docs'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_docsA

Read-onlyIdempotent

Search MetaMask Embedded Wallets documentation (Algolia) and example projects. Returns doc page links with snippets and matching examples.

ParametersJSON Schema

Name	Required	Description
`chain`	No	Filter examples by blockchain family
`query`	Yes	What you are looking for -- e.g. 'React custom auth', 'Android deep linking', 'JWT grouped connections'
`category`	No	Filter examples by category
`platform`	No	Filter examples by platform

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, openWorld, and idempotent hints, so the safety profile is covered. The description adds useful behavioral context by naming the Algolia backend and specifying that results include links, snippets, and matching examples, which goes beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact two-sentence structure, front-loaded with the action and resource, and every sentence adds value. There is no redundant or extraneous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, rich parameter schema, and strong annotations, the description sufficiently conveys purpose and output. It does not mention result limits or pagination, but for a search tool with no output schema, stating that it returns links with snippets and matching examples is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage with descriptions for all four parameters, including detailed enums for chain, category, and platform. The description itself does not add further parameter-specific semantics, so the baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Search') and clearly identifies the resource ('MetaMask Embedded Wallets documentation (Algolia) and example projects'). It also states the return value ('doc page links with snippets and matching examples'), which distinguishes it from sibling retrieval tools like get_doc and get_example.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for searching across docs and example projects, giving clear context for when to use it. However, it does not explicitly mention alternatives or exclusions, leaving room for a stronger differentiation from siblings like search_community.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

5 tool updatesv2.0.0Sep 23, 2026
- First observedget_doc
- First observedget_example
- First observedget_sdk_reference
- First observedsearch_community
- First observedsearch_docs

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored 2026-09-23 15:45 across 5 tools

Disambiguation5/5

Each tool has a distinct purpose: searching docs, fetching doc pages, retrieving examples, fetching SDK source, and searching the community forum. Even the two code-fetching tools are clearly differentiated by target.

Naming Consistency5/5

All tool names follow a consistent lowercase verb_noun pattern (search_* and get_*). The minor singular/plural variation between get_doc and search_docs is negligible.

Tool Count5/5

Five tools is well-scoped for a documentation and developer-support knowledge server. Each tool fills a clear role without redundancy or bloat.

Completeness5/5

The tool surface covers the full knowledge workflow: discover via search, read full docs, inspect examples, examine SDK source, and check community discussions. No significant gaps are apparent for this domain.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

MetaMask Embedded Wallets (Web3Auth) MCP A
io.github.Web3Auth
Helps AI coding agents integrate MetaMask Embedded Wallets (Web3Auth) SDKs.
Blockchain Web3 & Decentralized Tech Developer Tools
524
ref-tools-ref-tools-mcpOAuth
ai.smithery
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Documentation Access Developer Tools Code Analysis
21,177
llmref A
org.llmref
Versioned documentation registry and semantic search for AI tools and coding assistants.
Documentation Access Search Developer Tools
42
developer-toolkit-mcp A
io.github.mjaskolski
The documentation, as a tool your agent can call: 950+ AI-dev guides. Search + fetch tools.
AI & Machine Learning Search
21

Related MCP Servers

dfns-mcp
Blockchain Documentation Access Search
jhubbardsf
A
license
Not graded
quality
C
maintenance
Provides AI agents with access to DFNS documentation, API reference, and SDK code through full-text search and type intelligence.
Updated 7 months ago (2026-02-08 23:37 UTC)
19 npm
MIT
Atlas Docs MCP Server
CartographAI
A
license
A
quality
D
maintenance
Provides AI assistants with up-to-date documentation for popular libraries and frameworks, enabling them to generate more accurate code using less common or newly released libraries.
Updated a year ago (2025-04-22 06:43 UTC)
5
13 npm
36
MIT
MD3-Docs MCP
Documentation Access Search Developer Tools
ChouChiu
A
license
A
quality
A
maintenance
Provides AI assistants access to live Material Design 3 documentation including Foundations, Styles, and Components, returning official content as Markdown.
Updated 2 months ago (2026-07-29 12:36 UTC)
3
5 npm
1
MIT
Resemble AI MCP Serverofficial
Documentation Access AI & Machine Learning
resemble-ai
A
license
Not graded
quality
C
maintenance
Enables coding assistants to query Resemble AI documentation, search pages, and access OpenAPI schemas for code generation.
Updated 16 days ago (2026-09-07 16:40 UTC)
1
MIT

MetaMask Embedded Wallets MCP Server

MCP Tools

Skill

Universal install (works with 40+ agents)

MCP Server Setup

Cursor

VS Code (GitHub Copilot)

JetBrains (IntelliJ, PyCharm, WebStorm, Android Studio)

Claude Code CLI

Claude Desktop

ChatGPT Desktop

Windsurf

Kiro (AWS)

Warp Terminal

Cline (VS Code)

Continue.dev

Zed

Antigravity

Xcode (via GitHub Copilot)

Eclipse (via GitHub Copilot)

Neovim (avante.nvim)

Neovim (codecompanion.nvim)

Amp (Sourcegraph)

Goose

5ire

Aider

Codex CLI

Static docs (llms.txt)

Start building

Distribution

Environment Variables

Development

Updating Content

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Resemble AI MCP Serverofficial