Schema | mcp-fetch

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_FETCH_PORT`	No	Port for HTTP transport mode	8000
`MCP_FETCH_CACHE_DIR`	No	Directory for storing cache files	./.mcp-fetch-cache
`MCP_FETCH_TRANSPORT`	No	Transport mode: stdio or http
`MCP_FETCH_TTL_SECONDS`	No	Time-to-live for cached items in seconds	1800
`MCP_FETCH_MAX_CACHE_BYTES_TOTAL`	No	Maximum total cache size in bytes (512 MiB)	536870912
`MCP_FETCH_MAX_SINGLE_TRANSFER_BYTES`	No	Maximum size for a single transfer in bytes (200 MiB)	209715200
`MCP_FETCH_WAIT_CHUNK_TIMEOUT_SECONDS`	No	Timeout for waiting on chunk data in seconds	30

Features and capabilities supported by this server

Capability	Details
`tasks`	{ "list": {}, "cancel": {}, "requests": { "tools": { "call": {} }, "prompts": { "get": {} }, "resources": { "read": {} } } }
`tools`	{ "listChanged": true }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name Description

Name	Description
fetch_page	Fetch/Crawl a dynamic web page and convert to Markdown (supports JavaScript). Use this tool to: Crawl/Scrape content from modern web pages (React, Vue, etc.) Get full page content after JavaScript rendering Download large page content via chunked streaming Protocol: Start: Provide url (required) → returns transfer_id + first chunk Continue: Provide transfer_id + offset → returns next chunk Args: url: Target http(s) URL (required for phase 1) to_markdown: Convert HTML to Markdown (default: True) wait_selector: CSS selector to wait for before capturing content Optional: headers, query, timeout_ms, max_scrolls, min/max_delay_ms, proxy/pool, user_agent, chunk_bytes Cursor: transfer_id, offset (for phase 2) Returns: Chunk: chunk_text or chunk_base64, next_offset, done, truncated Meta: transfer_id, status, headers, final_url, content_type, elapsed_ms Size: available_bytes, total_bytes
http_request	Perform a generic HTTP request (GET, POST, PUT, DELETE, etc) for APIs or raw data. Use this tool when: You need to call a REST API (JSON/XML) You need to use HTTP methods other than GET (POST, PUT, DELETE) You want to download a raw file without rendering (PDF, Image, etc) Note: For GET requests to renderable web pages, prefer `fetch_page` which handles dynamic content and JavaScript. Protocol: Start: Provide url (required) → returns transfer_id + first chunk Continue: Provide transfer_id + offset → returns next chunk

Fetch/Crawl a dynamic web page and convert to Markdown (supports JavaScript).

Use this tool to:

Protocol:

Args:

url: Target http(s) URL (required for phase 1)
to_markdown: Convert HTML to Markdown (default: True)
wait_selector: CSS selector to wait for before capturing content
Optional: headers, query, timeout_ms, max_scrolls, min/max_delay_ms, proxy/pool, user_agent, chunk_bytes
Cursor: transfer_id, offset (for phase 2)

Returns:

Perform a generic HTTP request (GET, POST, PUT, DELETE, etc) for APIs or raw data.

Use this tool when:

Note: For GET requests to renderable web pages, prefer fetch_page which handles dynamic content and JavaScript.

Protocol:

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

mcp-fetch