AgentQL MCP Server
AgentQL MCP server for extracting structured JSON from public webpages using a URL and natural-language extraction prompt.
Open the source and read safety notes before installing.
Safety notes
- AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API.
- The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited.
- Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns.
- The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies.
- Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts.
Privacy notes
- Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API.
- Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material.
- AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files.
- Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session.
Prerequisites
- Node.js and npx available to the MCP client runtime.
- AgentQL API key from the AgentQL developer portal.
- Approved list of public webpages or domains Claude may query.
- Review of target site terms, robots guidance, rate limits, and data-use rules before extraction.
Schema details
- Install type
- cli
- Troubleshooting
- No
- Scope
- Source repo
- Estimated setup
- 10 minutes
- Difficulty
- beginner
- Website
- https://agentql.com
Full copyable content
{
"mcpServers": {
"agentql": {
"command": "npx",
"args": ["-y", "agentql-mcp"],
"env": {
"AGENTQL_API_KEY": "<your-agentql-api-key>"
}
}
}
}About this resource
Content
AgentQL MCP Server connects Claude and other MCP clients to AgentQL's web data
extraction API. It exposes a single tool, extract-web-data, which takes a
public webpage URL plus a natural-language prompt describing the fields to
extract, then returns structured JSON from AgentQL.
The server is distributed as the npm package agentql-mcp and runs over stdio
with an AGENTQL_API_KEY environment variable.
Source Review
- https://agentql.com
- https://github.com/tinyfish-io/agentql-mcp
- https://github.com/tinyfish-io/agentql-mcp/blob/main/README.md
- https://registry.npmjs.org/agentql-mcp
- https://github.com/tinyfish-io/agentql-mcp/blob/main/package.json
- https://github.com/tinyfish-io/agentql-mcp/blob/main/src/index.ts
- https://github.com/tinyfish-io/agentql-mcp/blob/main/LICENSE
These sources were reviewed on 2026-06-06. Prefer the live repository, README, npm registry metadata, package metadata, source implementation, and license for current package names, tool behavior, API requirements, and licensing.
Features
- npm package
agentql-mcp. - Stdio MCP server launched with
npx -y agentql-mcp. - Single
extract-web-datatool. - Inputs for public webpage URL and natural-language extraction prompt.
- Calls AgentQL's query-data API endpoint.
- Returns extracted structured JSON as MCP text content.
- README examples for Claude Desktop, VS Code, Cursor, and Windsurf.
- MIT license.
Installation
Configure an MCP client with the npm package and an AgentQL API key:
{
"mcpServers": {
"agentql": {
"command": "npx",
"args": ["-y", "agentql-mcp"],
"env": {
"AGENTQL_API_KEY": "<your-agentql-api-key>"
}
}
}
}
Restart the MCP client after adding the server. Keep prompts narrow, such as a specific list of fields to extract from an approved page.
Use Cases
- Extract product names, prices, and URLs from an approved public catalog page.
- Convert event listings or search results into structured JSON.
- Pull public page metadata into a research table.
- Ask Claude to compare extracted fields across several approved public pages.
- Prototype extraction prompts before building a dedicated ingestion pipeline.
- Use structured results as input to a report, spreadsheet, or downstream review workflow.
Safety and Privacy
AgentQL MCP sends the target URL and extraction prompt to a third-party API, and the returned page data is then visible to the MCP client and model session. Use it only for approved public webpages, respect target-site terms and robots guidance, and do not use it to collect private, paywalled, access-controlled, or prohibited data.
Treat extracted web content as untrusted. It may include stale data, ads, tracking fragments, copyrighted text, personal data, or prompt-injection instructions. Keep the AgentQL API key out of shared configs and logs.
Disclosure
AgentQL provides a hosted data extraction API. This listing is not sponsored, paid, or affiliate-driven, and it is scoped to the source-backed MCP server and npm package.
Duplicate Check
No AgentQL MCP Server, tinyfish-io/agentql-mcp, agentql-mcp, or matching
source URL entry was found in content/mcp, content/tools, content/guides,
content/agents, or content/skills.
Source citations
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.