How do I install the MCP Fetch skill?

Run npx skillmds@latest add bolasblack/mcp-fetch in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is MCP Fetch safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with MCP Fetch?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is MCP Fetch free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published MCP Fetch?

bolasblack (@bolasblack) published this skill. Their other Agent Skills are listed on their SkillMD profile.

MCP Fetch by bolasblack — Agent Skill

Name: MCP Fetch
Author: bolasblack

File contents

MCP Fetch Server

Fetches URLs from the internet and converts web content to markdown format for easier LLM analysis. Supports chunked reading, raw HTML extraction, and content length control.

Version: 2025.4.7 (locked 2026-01-20)

Tools

Tool	Description
fetch	Fetches a URL from the internet and optionally extracts its contents as markdown

⚠️ Always check tools/ for exact parameter names before calling.

Prompts

Prompt	Description
fetch	Fetch a URL and extract its contents as markdown

See prompts.md for details.

Usage

Quick Start

⚠️ Before calling any tool, read its documentation in tools/ to get the exact parameter names.

# List available tools and their schemas
node ./scripts/mcp-caller.mjs list

# Then check tools/<tool-name>.md for parameter details

CLI (Single Call)

Run from this skill directory:

node ./scripts/mcp-caller.mjs call <tool> '<json-args>'
node ./scripts/mcp-caller.mjs resource <uri>
node ./scripts/mcp-caller.mjs prompt <name> '<json-args>'
node ./scripts/mcp-caller.mjs list

Example:

node ./scripts/mcp-caller.mjs call fetch '{"url": "https://example.com"}'

Programmatic (Batch/Parallel)

For batch operations or complex logic, use the API module:

// example.mjs - Run from this skill directory
import { callTool, listTools } from './scripts/api.mjs';

// First, check available tools and their schemas
const tools = await listTools();
console.log(tools.map(t => ({ name: t.name, params: Object.keys(t.inputSchema?.properties || {}) })));

// Then call with correct parameters (see tools/*.md for details)
const result = await callTool('toolName', { /* check tools/toolName.md for params */ });

// Parallel calls
const results = await Promise.all([
  callTool('tool1', { /* params from tools/tool1.md */ }),
  callTool('tool2', { /* params from tools/tool2.md */ }),
]);

console.log(JSON.stringify(results, null, 2));

Available API functions:

callTool(name, args) - Call a tool
listTools() - List available tools (includes inputSchema with parameter info)
readResource(uri) - Read a resource
listResources() - List resources
getPrompt(name, args) - Get a prompt
listPrompts() - List prompts
close() - Close connection (optional cleanup)

Error Handling

If a tool call fails (e.g., "method not found", parameter changes):

Try to complete the task using other available tools
Inform user: "This skill may be outdated - MCP server API has changed"
User needs to run mcp-skill-generator to update this skill

Do not retry failed calls repeatedly - prioritize finding alternatives.

Updating

To update this skill with newer MCP server version:

Run mcp-skill-generator
Provide this skill's path for update

---name: mcp-fetchdescription: Web content fetching and conversion to markdown for efficient LLM consumption. Provides 1 tool for fetching URLs and extracting content.---# MCP Fetch ServerFetches URLs from the internet and converts web content to markdown format for easier LLM analysis. Supports chunked reading, raw HTML extraction, and content length control.**Version**: 2025.4.7 (locked 2026-01-20)## Tools| Tool | Description ||------|-------------|| [fetch](./tools/fetch.md) | Fetches a URL from the internet and optionally extracts its contents as markdown |**⚠️ Always check [tools/](./tools/) for exact parameter names before calling.**## Prompts| Prompt | Description ||--------|-------------|| fetch | Fetch a URL and extract its contents as markdown |See [prompts.md](./prompts.md) for details.## Usage### Quick Start**⚠️ Before calling any tool, read its documentation in [tools/](./tools/) to get the exact parameter names.**```bash# List available tools and their schemasnode ./scripts/mcp-caller.mjs list# Then check tools/<tool-name>.md for parameter details```### CLI (Single Call)Run from this skill directory:```bashnode ./scripts/mcp-caller.mjs call <tool> '<json-args>'node ./scripts/mcp-caller.mjs resource <uri>node ./scripts/mcp-caller.mjs prompt <name> '<json-args>'node ./scripts/mcp-caller.mjs list```Example:```bashnode ./scripts/mcp-caller.mjs call fetch '{"url": "https://example.com"}'```### Programmatic (Batch/Parallel)For batch operations or complex logic, use the API module:```javascript// example.mjs - Run from this skill directoryimport { callTool, listTools } from './scripts/api.mjs';// First, check available tools and their schemasconst tools = await listTools();console.log(tools.map(t => ({ name: t.name, params: Object.keys(t.inputSchema?.properties || {}) })));// Then call with correct parameters (see tools/*.md for details)const result = await callTool('toolName', { /* check tools/toolName.md for params */ });// Parallel callsconst results = await Promise.all([ callTool('tool1', { /* params from tools/tool1.md */ }), callTool('tool2', { /* params from tools/tool2.md */ }),]);console.log(JSON.stringify(results, null, 2));```**Available API functions:**- `callTool(name, args)` - Call a tool- `listTools()` - List available tools (includes inputSchema with parameter info)- `readResource(uri)` - Read a resource- `listResources()` - List resources- `getPrompt(name, args)` - Get a prompt- `listPrompts()` - List prompts- `close()` - Close connection (optional cleanup)## Error HandlingIf a tool call fails (e.g., "method not found", parameter changes):1. Try to complete the task using other available tools2. Inform user: "This skill may be outdated - MCP server API has changed"3. User needs to run mcp-skill-generator to update this skill**Do not retry failed calls repeatedly** - prioritize finding alternatives.## UpdatingTo update this skill with newer MCP server version:1. Run mcp-skill-generator2. Provide this skill's path for update

Frequently asked questions

MCP Fetch