What can you do with this server?

The superFetch MCP Server fetches public web pages and converts HTML into clean, AI-readable Markdown — ideal for feeding web content to LLMs. * Fetch & Convert Web Content: Retrieve content from any public HTTP(S) URL and transform it into clean Markdown, with noise removal (navbars, footers, clutter) applied by default * Code Host Integration: Automatically rewrite GitHub, GitLab, Bitbucket, and Gist URLs to raw content endpoints * Caching: Results are cached for reuse; bypass with forceRefresh for fresh content, or access cached content via internal://cache/{namespace}/{hash} * Inline Size Control & Task Mode: Limit returned Markdown size with maxInlineChars; large or slow fetches can run asynchronously via task mode to avoid truncation/timeouts * Structured Metadata: Responses include url, resolvedUrl, finalUrl, title, markdown, fromCache, fetchedAt, contentSize, and truncated * Built-in Resources & Help: Access guidance via internal://instructions and a get-help prompt for usage details * HTTP Server Mode: Optional HTTP server with host/origin validation, authentication (static tokens, OAuth), rate limiting, and health checks * Security: SSRF protections, local/private network blocking, TLS support, and protocol version validation * Read-only: Purely a content fetcher — no JavaScript execution or page interaction * Broad Client Support: Works with VS Code, Cursor, Claude Desktop, LM Studio, and other MCP-compatible clients

Which integrations are available for this server?

Automatically rewrites Bitbucket URLs to their raw content versions to extract clean, readable text from code repositories. Automatically rewrites GitHub and Gist URLs to their raw content versions to extract clean, readable text from code repositories. Automatically rewrites GitLab URLs to their raw content versions to extract clean, readable text from code repositories.

How do I use superFetch MCP Server?

1. Click on "Install 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., "@superFetch MCP Server fetch and clean the content from https://www.wired.com/story/ai-chip-wars/" 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.

Fetch URL MCP Server

npm version License

Install in VS Code Install in VS Code Insiders Install in Visual Studio

Add to LM Studio Install in Cursor Install in Goose

A web content fetcher MCP server that converts HTML to clean, AI and human readable markdown.

Overview

The Fetch URL MCP Server provides a standardized interface for fetching public web content and transforming it into Markdown enriched with structured metadata. It validates URLs, applies noise removal heuristics, and caches results for reuse. The server supports both inline and task-based execution modes, making it suitable for a wide range of client applications and LLM interactions.

Key Features

fetch-url validates public HTTP(S) URLs, fetches the page, and returns cleaned Markdown plus structured metadata.
The tool advertises optional task support and emits progress updates while fetching and transforming larger pages.
GitHub, GitLab, Bitbucket, and Gist page URLs are rewritten to raw-content endpoints when possible before fetch.
internal://instructions and internal://cache/{namespace}/{hash} expose built-in guidance and cached Markdown as MCP resources.
HTTP mode adds host/origin validation, auth, rate limiting, health checks, OAuth protected-resource metadata, and cached-download URLs.

Requirements

Node.js >=24 (from package.json)
Docker is optional if you want to run the published container image.

Quick Start

Use this standard MCP client configuration:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

Client Configuration

Install in VS Code

Add to .vscode/mcp.json:

{
  "servers": {
    "fetch-url-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

Or install via CLI:

code --add-mcp '{"name":"fetch-url-mcp","command":"npx","args":["-y","@j0hanz/fetch-url-mcp@latest"]}'

For more info, see VS Code MCP docs.

Install in VS Code Insiders

Add to .vscode/mcp.json:

{
  "servers": {
    "fetch-url-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

Or install via CLI:

code-insiders --add-mcp '{"name":"fetch-url-mcp","command":"npx","args":["-y","@j0hanz/fetch-url-mcp@latest"]}'

For more info, see VS Code Insiders MCP docs.

Install in Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Cursor MCP docs.

Install in Visual Studio

For solution-scoped setup, add this to .mcp.json at the solution root:

{
  "servers": {
    "fetch-url-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Visual Studio MCP docs.

Install in Goose

Add to ~/.config/goose/config.yaml on macOS/Linux or %APPDATA%\Block\goose\config\config.yaml on Windows:

extensions:
  fetch-url-mcp:
    name: fetch-url-mcp
    cmd: npx
    args: ['-y', '@j0hanz/fetch-url-mcp@latest']
    enabled: true
    type: stdio
    timeout: 300

For more info, see Goose extension docs.

Add to LM Studio

Add to ~/.lmstudio/mcp.json on macOS/Linux or %USERPROFILE%/.lmstudio/mcp.json on Windows:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see LM Studio MCP docs.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Claude Desktop MCP docs.

Use the CLI:

claude mcp add fetch-url-mcp -- npx -y @j0hanz/fetch-url-mcp@latest

For project-scoped config, Claude Code writes .mcp.json with:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"],
      "env": {}
    }
  }
}

For more info, see Claude Code MCP docs.

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Windsurf MCP docs.

Add to ~/.config/amp/settings.json on macOS/Linux, %USERPROFILE%\.config\amp\settings.json on Windows, or .amp/settings.json for workspace-scoped config:

{
  "amp.mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

Or install via CLI:

amp mcp add fetch-url-mcp -- npx -y @j0hanz/fetch-url-mcp@latest

For more info, see Amp docs.

Open the MCP Servers panel, choose Configure MCP Servers, and add this to cline_mcp_settings.json:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Cline MCP docs.

Use the CLI:

codex mcp add fetch-url-mcp -- npx -y @j0hanz/fetch-url-mcp@latest

Or add this to ~/.codex/config.toml or project-scoped .codex/config.toml:

[mcp_servers.fetch-url-mcp]
command = "npx"
args = ["-y", "@j0hanz/fetch-url-mcp@latest"]

For more info, see Codex MCP docs.

Add to .vscode/mcp.json:

{
  "servers": {
    "fetch-url-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see GitHub Copilot MCP docs.

Open Personal > MCP Servers in Warp, choose + Add, and either add a CLI server with:

command: npx
args: ["-y", "@j0hanz/fetch-url-mcp@latest"]

Or paste this JSON snippet when using Warp's multi-server import flow:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Warp MCP docs.

Use Kiro's MCP Servers panel or the Add to Kiro install flow. Kiro stores workspace-scoped MCP config in .kiro/settings/mcp.json and user-scoped config in ~/.kiro/settings/mcp.json.

For this server, use:

command: npx
args: ["-y", "@j0hanz/fetch-url-mcp@latest"]

For more info, see Kiro MCP docs.

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Gemini CLI MCP docs.

Add to ~/.config/zed/settings.json:

{
  "context_servers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"],
      "env": {}
    }
  }
}

For more info, see Zed MCP docs.

Use the Augment Settings panel and either add the server manually or choose Import from JSON:

{
  "mcpServers": {
    "fetch-url-mcp": {
      "command": "npx",
      "args": ["-y", "@j0hanz/fetch-url-mcp@latest"]
    }
  }
}

For more info, see Augment MCP docs.

Use Roo Code's MCP Servers UI or marketplace flow.

For this server, use:

command: npx
args: ["-y", "@j0hanz/fetch-url-mcp@latest"]

For more info, see Roo Code docs.

Use Kilo Code's MCP Servers UI or marketplace flow.

For this server, use:

command: npx
args: ["-y", "@j0hanz/fetch-url-mcp@latest"]

For more info, see Kilo Code docs.

Use Cases

Fetch documentation pages, blog posts, or reference material into Markdown before sending them to an LLM.
Retrieve repository-hosted content from GitHub, GitLab, Bitbucket, or Gists and let the server rewrite page URLs to raw endpoints when possible.
Reuse cached Markdown through internal://cache/{namespace}/{hash} or bypass the cache with forceRefresh for time-sensitive pages.
Use task mode for large pages or slower sites when the inline response would otherwise be truncated or delayed.

Architecture

[MCP Client]
  ├─ stdio -> `src/index.ts` -> `startStdioServer()` -> `createMcpServer()`
  └─ HTTP (`--http`) -> `src/index.ts` -> `startHttpServer()` -> HTTP dispatcher
       ├─ `GET /health`
       ├─ `GET /.well-known/oauth-protected-resource`
       ├─ `GET /.well-known/oauth-protected-resource/mcp`
       ├─ `GET /mcp/downloads/{namespace}/{hash}`
       └─ `POST|GET|DELETE /mcp`

`createMcpServer()`
  ├─ registers tool: `fetch-url`
  ├─ registers prompt: `get-help`
  ├─ registers resources:
  │    - `internal://instructions`
  │    - `internal://cache/{namespace}/{hash}`
  ├─ enables capabilities: completions, logging, resources, prompts, tasks
  └─ installs task handlers, log-level handling, and shutdown cleanup

`fetch-url` execution
  ├─ validate input with `fetchUrlInputSchema`
  ├─ normalize URL and block local/private targets unless allowed
  ├─ rewrite supported code-host URLs to raw endpoints when possible
  ├─ fetch and cache content via the shared pipeline
  ├─ transform HTML into Markdown in the transform worker path
  └─ validate `structuredContent` with `fetchUrlOutputSchema`

Request Lifecycle

[Client] -- initialize {protocolVersion, capabilities} --> [Server]
[Server] -- {protocolVersion, capabilities, serverInfo} --> [Client]
[Client] -- notifications/initialized --> [Server]
[Client] -- tools/call {name, arguments} --> [Server]
[Server] -- {content: [{type, text}], structuredContent?, isError?} --> [Client]

MCP Surface

Tools

`fetch-url`

Fetch public webpages and convert HTML into AI-readable Markdown. The tool is read-only, does not execute page JavaScript, can bypass the cache with forceRefresh, and supports optional task mode for larger or slower fetches.

Parameter	Type	Required	Description
`url`	`string`	yes	Target URL. Max 2048 chars.
`skipNoiseRemoval`	`boolean`	no	Preserve navigation/footers (disable noise filtering).
`forceRefresh`	`boolean`	no	Bypass cache and fetch fresh content.
`maxInlineChars`	`integer`	no	Inline markdown limit (0-10485760, 0=unlimited). Lower of this or the global limit applies.

The response is returned as MCP text content and, when validation succeeds, as structuredContent containing url, resolvedUrl, finalUrl, title, metadata, markdown, fromCache, fetchedAt, contentSize, and truncated.

1. [Client] -- tools/call {name: "fetch-url", arguments} --> [Server]
2. [Server] -- dispatch("fetch-url") --> [src/tools/fetch-url.ts]
3. [Handler] -- validate(fetchUrlInputSchema) --> normalize / fetch / transform
4. [Handler] -- validate(fetchUrlOutputSchema) --> assemble content + structuredContent
5. [Server] -- result or tool error --> [Client]

Resources

Resource	URI	MIME Type	Description
`fetch-url-mcp-instructions`	`internal://instructions`	`text/markdown`	Guidance for using the Fetch URL MCP server.
`fetch-url-mcp-cache-entry`	`internal://cache/{namespace}/{hash}`	`text/markdown`	Read cached markdown generated by previous `fetch-url` calls.

Prompts

Prompt	Arguments	Description
`get-help`	none	Return Fetch URL server instructions: workflows, cache usage, task mode, and error handling.

MCP Capabilities

Capability	Status	Notes
completions	confirmed	Advertised in `createServerCapabilities()` and used by the cache resource template for `namespace` and `hash` completion.
logging	confirmed	Advertised in `createServerCapabilities()` and handled through `SetLevelRequestSchema`.
resources subscribe/listChanged	confirmed	Advertised in `createServerCapabilities()` and implemented for cache resource subscriptions and list changes.
prompts	confirmed	`get-help` is registered during server startup.
tasks	confirmed	Advertised in `createServerCapabilities()` and backed by registered task handlers plus optional tool task support.
progress notifications	confirmed	Tool execution reports `notifications/progress` updates during fetch and transform stages.

Tool Annotations

Annotation	Value
`readOnlyHint`	`true`
`destructiveHint`	`false`
`idempotentHint`	`true`
`openWorldHint`	`true`

Structured Output

fetch-url publishes an explicit outputSchema and returns structuredContent when the assembled response passes validation.

Configuration

Variable	Default	Applies To	Notes
`HOST`	`127.0.0.1`	HTTP mode	Bind address. Non-loopback bindings also require `ALLOW_REMOTE=true`.
`PORT`	`3000`	HTTP mode	Listening port for `--http`.
`ALLOW_REMOTE`	`false`	HTTP mode	Must be enabled to bind to a non-loopback interface.
`ACCESS_TOKENS`	unset	HTTP mode	Comma- or space-separated static bearer tokens.
`API_KEY`	unset	HTTP mode	Alternate static token source for header auth.
`OAUTH_ISSUER_URL`	unset	HTTP mode	Enables OAuth mode when combined with the other OAuth URLs.
`OAUTH_AUTHORIZATION_URL`	unset	HTTP mode	Optional explicit authorization endpoint.
`OAUTH_TOKEN_URL`	unset	HTTP mode	Optional explicit token endpoint.
`OAUTH_REVOCATION_URL`	unset	HTTP mode	Optional OAuth revocation endpoint.
`OAUTH_REGISTRATION_URL`	unset	HTTP mode	Optional OAuth dynamic client registration endpoint.
`OAUTH_INTROSPECTION_URL`	unset	HTTP mode	Required for OAuth token introspection.
`OAUTH_REQUIRED_SCOPES`	empty	HTTP mode	Required scopes enforced after auth.
`OAUTH_CLIENT_ID`	unset	HTTP mode	Optional introspection client ID.
`OAUTH_CLIENT_SECRET`	unset	HTTP mode	Optional introspection client secret.
`SERVER_TLS_KEY_FILE`	unset	HTTP mode	Enable HTTPS when set together with `SERVER_TLS_CERT_FILE`.
`SERVER_TLS_CERT_FILE`	unset	HTTP mode	TLS certificate path.
`SERVER_TLS_CA_FILE`	unset	HTTP mode	Optional custom CA bundle.
`SERVER_MAX_CONNECTIONS`	`0`	HTTP mode	Optional connection cap.
`SERVER_HEADERS_TIMEOUT_MS`	unset	HTTP mode	Optional Node server tuning.
`SERVER_REQUEST_TIMEOUT_MS`	unset	HTTP mode	Optional Node server tuning.
`SERVER_KEEP_ALIVE_TIMEOUT_MS`	unset	HTTP mode	Optional keep-alive tuning.
`SERVER_KEEP_ALIVE_TIMEOUT_BUFFER_MS`	unset	HTTP mode	Optional keep-alive tuning buffer.
`SERVER_MAX_HEADERS_COUNT`	unset	HTTP mode	Optional header count limit.
`SERVER_BLOCK_PRIVATE_CONNECTIONS`	`false`	HTTP mode	Enables inbound private-network protections.
`MCP_STRICT_PROTOCOL_VERSION_HEADER`	`true`	HTTP mode	Requires `MCP-Protocol-Version` on session init.
`ALLOWED_HOSTS`	empty	HTTP mode	Additional allowed `Host` and `Origin` values.
`ALLOW_LOCAL_FETCH`	`false`	Fetching	Allows loopback and private-network fetch targets.
`FETCH_TIMEOUT_MS`	`15000`	Fetching	Network fetch timeout in milliseconds.
`USER_AGENT`	`fetch-url-mcp/<version>`	Fetching	Override the outbound user agent string.
`MAX_INLINE_CONTENT_CHARS`	`0`	Tool output	`0` means no explicit inline truncation limit.
`CACHE_ENABLED`	`true`	Caching	Enables in-memory fetch result caching.
`TASKS_MAX_TOTAL`	`5000`	Tasks	Total task capacity.
`TASKS_MAX_PER_OWNER`	`1000`	Tasks	Per-owner task cap, clamped to the total cap.
`TASKS_STATUS_NOTIFICATIONS`	`false`	Tasks	Enables status notifications for tasks.
`TASKS_REQUIRE_INTERCEPTION`	`true`	Tasks	Requires task interception for task-capable tool execution.
`TRANSFORM_CANCEL_ACK_TIMEOUT_MS`	`200`	Transform workers	Cancellation acknowledgement timeout.
`TRANSFORM_WORKER_MODE`	`threads`	Transform workers	Worker execution mode.
`TRANSFORM_WORKER_MAX_OLD_GENERATION_MB`	unset	Transform workers	Optional worker memory limit.
`TRANSFORM_WORKER_MAX_YOUNG_GENERATION_MB`	unset	Transform workers	Optional worker memory limit.
`TRANSFORM_WORKER_CODE_RANGE_MB`	unset	Transform workers	Optional worker memory limit.
`TRANSFORM_WORKER_STACK_MB`	unset	Transform workers	Optional worker stack size.
`FETCH_URL_MCP_EXTRA_NOISE_TOKENS`	empty	Content cleanup	Extra noise-removal tokens.
`FETCH_URL_MCP_EXTRA_NOISE_SELECTORS`	empty	Content cleanup	Extra DOM selectors for noise removal.
`FETCH_URL_MCP_LOCALE`	system default	Content cleanup	Locale override for extraction heuristics.
`MARKDOWN_HEADING_KEYWORDS`	built-in list	Markdown cleanup	Override heading keywords used by cleanup.
`LOG_LEVEL`	`info`	Logging	`debug`, `info`, `warn`, or `error`.
`LOG_FORMAT`	`text`	Logging	Set to `json` for structured logs.

HTTP Endpoints

Method	Path	Auth	Purpose
`GET`	`/health`	no, unless `?verbose=1` on a remote server	Basic health response, with optional diagnostics.
`GET`	`/.well-known/oauth-protected-resource`	no	OAuth protected-resource metadata.
`GET`	`/.well-known/oauth-protected-resource/mcp`	no	OAuth protected-resource metadata for the MCP endpoint.
`POST`	`/mcp`	yes	Session initialization and JSON-RPC requests.
`GET`	`/mcp`	yes	Session-bound server-to-client stream handling.
`DELETE`	`/mcp`	yes	Session shutdown.
`GET`	`/mcp/downloads/{namespace}/{hash}`	yes	Download route used by HTTP-mode cached fetch results.

Security

Control	Status	Notes
Host and origin validation	implemented	HTTP requests are rejected unless `Host` and `Origin` match the allowlist built from loopback, the configured host, and `ALLOWED_HOSTS`.
Authentication	implemented	HTTP mode supports static bearer tokens locally or OAuth token introspection; remote bindings require OAuth.
Protocol version checks	implemented	HTTP sessions validate `MCP-Protocol-Version` and pin it to the negotiated session version.
Rate limiting	implemented	Requests pass through the HTTP rate limiter before route dispatch.
Outbound SSRF protections	implemented	Local/private IPs, metadata endpoints, and `.local`/`.internal` hosts are blocked unless `ALLOW_LOCAL_FETCH=true`.
TLS	optional	HTTPS is enabled when both TLS key and certificate files are configured.
Stdio logging safety	implemented	Server logs are written to stderr, not stdout, so stdio MCP traffic stays clean.

Development

Script	Command
`clean`	`node scripts/tasks.mjs clean`
`build`	`node scripts/tasks.mjs build`
`copy:assets`	`node scripts/tasks.mjs copy:assets`
`prepare`	`npm run build`
`dev`	`tsc --watch --preserveWatchOutput`
`dev:run`	`node --env-file=.env --watch dist/index.js`
`start`	`node dist/index.js`
`format`	`prettier --write .`
`type-check`	`node scripts/tasks.mjs type-check`
`type-check:src`	`node node_modules/typescript/bin/tsc -p tsconfig.json --noEmit`
`type-check:tests`	`node node_modules/typescript/bin/tsc -p tsconfig.test.json --noEmit`
`type-check:diagnostics`	`tsc --noEmit --extendedDiagnostics`
`type-check:trace`	`node -e "require('fs').rmSync('.ts-trace',{recursive:true,force:true})" && tsc --noEmit --generateTrace .ts-trace`
`lint`	`eslint .`
`lint:tests`	`eslint src/__tests__`
`lint:fix`	`eslint . --fix`
`test`	`node scripts/tasks.mjs test`
`test:fast`	`node --test --import tsx/esm src/__tests__/*/.test.ts node-tests/*/.test.ts`
`test:coverage`	`node scripts/tasks.mjs test --coverage`
`knip`	`knip`
`knip:fix`	`knip --fix`
`inspector`	`npm run build && npx -y @modelcontextprotocol/inspector node dist/index.js --stdio`
`prepublishOnly`	`npm run lint && npm run type-check && npm run build`

Build and Release

The repository includes release automation under .github/workflows/.
Dockerfile and docker-compose.yml are available for container-based packaging and local runs.
npm run prepublishOnly runs the release gate: lint, type-check, and build.

Troubleshooting

For stdio mode, avoid writing logs to stdout; keep logs on stderr.
For HTTP mode, verify MCP protocol headers and endpoint routing.
Update client snippets when client MCP configuration formats change.

Credits

Dependency	Registry
@modelcontextprotocol/sdk	npm
@mozilla/readability	npm
linkedom	npm
node-html-markdown	npm
undici	npm
zod	npm

Contributing and License

License: MIT
Contributions are welcome via pull requests.

Install Server

security – no known vulnerabilities

license - not found

quality - confirmed to work

How are these scores calculated?

Resources

Need Help?

Report Issue

Related Servers

Tools

fetch-url

superFetch MCP Server

Fetch URL MCP Server

Overview

Key Features

Requirements

Quick Start

Client Configuration

Use Cases

Architecture

Request Lifecycle

MCP Surface

Tools

`fetch-url`

Resources

Prompts

MCP Capabilities

Tool Annotations

Structured Output

Configuration

HTTP Endpoints

Security

Development

Build and Release

Troubleshooting

Credits

Contributing and License

Resources

Tools

Latest Blog Posts

MCP directory API