Fetch Jsonpath Mcp
@ackness
A Model Context Protocol (MCP) server that provides tools for fetching and extracting JSON data from URLs using JSONPath patterns.
Overview
What is Fetch Jsonpath Mcp?
Fetch Jsonpath Mcp is a Model Context Protocol (MCP) server that provides tools for fetching JSON data and web content from URLs. It features intelligent content extraction, multiple HTTP methods, and browser-like headers for reliable web scraping, designed to reduce LLM token usage and hallucination by extracting only needed data via JSONPath patterns.
How to use Fetch Jsonpath Mcp?
Install in any MCP-compatible IDE by adding the server configuration with command uvx and args ["fetch-jsonpath-mcp"]. For Claude Code, run claude mcp add fetch-jsonpath-mcp -- uvx fetch-jsonpath-mcp. Tools include fetch-json, fetch-text, batch-fetch-json, and batch-fetch-text. Customize behavior via environment variables such as JSONRPC_MCP_TIMEOUT, JSONRPC_MCP_VERIFY, JSONRPC_MCP_HEADERS, and JSONRPC_MCP_PROXY.
Key features of Fetch Jsonpath Mcp
- Extract JSON data using JSONPath patterns.
- Support for all HTTP methods (GET, POST, PUT, DELETE, PATCH, HEAD, OPTIONS).
- Intelligent text extraction with Markdown, clean text, or raw HTML output.
- Batch processing of multiple URLs concurrently.
- Smart browser headers to prevent blocking.
- Reduced token usage and hallucinations.
Use cases of Fetch Jsonpath Mcp
- Extract specific fields from large API responses.
- Fetch and summarize web content in Markdown format.
- Batch fetch data from multiple endpoints for analysis.
- Post data to APIs and extract results.
- Scrape HTML pages with browser-like headers.
FAQ from Fetch Jsonpath Mcp
How does this reduce token usage?
By extracting only needed data using JSONPath patterns instead of fetching entire JSON responses, saving up to 99% of tokens.
What HTTP methods are supported?
All common HTTP methods: GET, POST, PUT, DELETE, PATCH, HEAD, and OPTIONS.
How do I set custom headers or a proxy?
Set environment variables JSONRPC_MCP_HEADERS for custom headers (merged with default browser headers) and JSONRPC_MCP_PROXY for an HTTP proxy.
What output formats are available for fetch-text?
Three formats: markdown (default), clean_text (pure text with HTML tags removed), and raw_html (original HTML).
Can I fetch multiple URLs at once?
Yes, use the batch-fetch-json and batch-fetch-text tools to process multiple URLs concurrently.
