F
licenseNot graded
qualityB
maintenanceEnables AI agents to extract structured JSON data from web pages using presets or custom JSON schemas, with confidence scores and source snippets, paid per call via USDC on Base.
-
PulpMiner
Server Details
Turn any public webpage into JSON with AI, save it as a live JSON API, and call it from your agent.
Ownership verified
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- pulpminercom/pulpminer-mcp
- GitHub Stars
- 0
TDQS
Score is being calculated.
Available Tools
5 toolspulpminer_check_api_keyCheck PulpMiner credentialsRead-onlyInspect
Verify that a PulpMiner API key (PULPMINER_API_KEY locally, or Authorization: Bearer <key> on the hosted server) is set and valid (GET /external/n8n/auth). Free.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
pulpminer_fetch_api_dataFetch JSON from a saved PulpMiner APIIdempotentInspect
Call a saved PulpMiner API and return its JSON (GET /external/{apiId}, or POST with variables for dynamic APIs). Uses the PulpMiner API key (PULPMINER_API_KEY locally, or Authorization: Bearer <key> on the hosted server). Costs 0.4 credits (+0.1 if the API renders JS); cached APIs return fast.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| apiId | Yes | Numeric API id, the value after /external/ in the API URL (e.g. 566). | |
| variables | No | Only for dynamic APIs: values for every {{ variable }} in its dynamic URL, e.g. {"query": "laptops"}. |
pulpminer_generate_jsonGenerate JSON from a web page with AIInspect
Scrape a web page and convert it to structured JSON with an LLM (PulpMiner POST /external/ai/json). Pass jsonFormat to force an exact output shape; omit it to let the AI infer a flat JSON. Does not save anything. Costs 0.25 credits (+0.1 with renderJs). Can take 10-60s+. Needs only the PulpMiner API key (PULPMINER_API_KEY locally, or Authorization: Bearer <key> on the hosted server).
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| llm | No | LLM used to convert HTML to JSON. llm_2 = OpenAI GPT (default), llm_1 = Google Gemini, llm_3 = Groq (only if enabled for the account; otherwise the API returns 'bad request'). | llm_2 |
| url | Yes | Full URL of the web page to extract data from (http/https). | |
| scraper | No | Scraper backend. scraper_1 (default, supports useSession) or scraper_2. Try the other one if a site blocks scraping. | scraper_1 |
| renderJs | No | Render JavaScript in a headless browser before extracting (default true; adds 0.1 credits). | |
| selector | No | CSS selector to limit extraction to part of the page, e.g. "main" or "#results". Default: whole body. | |
| jsonFormat | No | Sample JSON whose keys define the output shape, e.g. {"title": "", "price": "", "items": [{"name": ""}]}. Key names are kept exactly; values are extracted from the page. | |
| useSession | No | Use a persistent scraping session (scraper_1 only; ignored for lifetime-plan accounts). | |
| extraLLMInfo | No | Extra natural-language instructions for the LLM, e.g. 'only the first 10 products, prices as numbers'. |
pulpminer_list_saved_apisList saved PulpMiner APIsRead-onlyInspect
List the APIs saved under this API key (GET /external/api/url), oldest first, paginated (pageSize 5-100; smaller values are raised to 5). Returns id, url, dynamic flag and dynamicUrl template for each. Free.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Only return the API with this id. | |
| page | No | Page number, starting at 1. | |
| pageSize | No | Items per page, 5-100 (values below 5 are raised to 5). |
pulpminer_save_as_apiSave a page-to-JSON config as a reusable APIInspect
Save a URL + JSON format as a PulpMiner API (POST /external/ai/json/save). Afterwards the data is available at {baseUrl}/external/{apiId} with the apikey header (see pulpminer_fetch_api_data). For a dynamic API, pass dynamicUrl with {{ variable }} placeholders, e.g. https://site.com/search?q={{ query }}; callers then supply those variables. Saving itself is free; each later fetch costs 0.4 credits (+0.1 with renderJs). Needs only the PulpMiner API key (PULPMINER_API_KEY locally, or Authorization: Bearer <key> on the hosted server).
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| llm | No | LLM used to convert HTML to JSON. llm_2 = OpenAI GPT (default), llm_1 = Google Gemini, llm_3 = Groq (only if enabled for the account; otherwise the API returns 'bad request'). | llm_2 |
| url | Yes | Page URL the API scrapes (for dynamic APIs: an example URL with real values). | |
| cache | No | Cache results: serve cached JSON (24h TTL) and refresh in the background when older than 15 min. | |
| scraper | No | Scraper backend. scraper_1 (default, supports useSession) or scraper_2. Try the other one if a site blocks scraping. | scraper_1 |
| renderJs | No | Render JavaScript in a headless browser before extracting (default true; adds 0.1 credits). | |
| selector | No | CSS selector to limit extraction to part of the page, e.g. "main" or "#results". Default: whole body. | |
| dynamicUrl | No | Optional URL template with {{ variable }} placeholders. When set the API becomes dynamic and must be called with variables. | |
| jsonFormat | Yes | Required. The JSON shape the API should return, usually the output of pulpminer_generate_json (values can be left as examples). | |
| useSession | No | Use a persistent scraping session (scraper_1 only; ignored for lifetime-plan accounts). | |
| extraLLMInfo | No | Extra natural-language instructions for the LLM, e.g. 'only the first 10 products, prices as numbers'. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
5 tool updates
- First observed
pulpminer_check_api_key - First observed
pulpminer_fetch_api_data - First observed
pulpminer_generate_json - First observed
pulpminer_list_saved_apis - First observed
pulpminer_save_as_api
Related MCP Connectors
Public web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON.
Turn any website into structured JSON data matching your custom schema.
- mcpOAuthcom.sequentum
Turn the web into structured, reliable, actionable enterprise data for AI Agents
Related MCP Servers
- AlicenseAqualityFmaintenanceStructured web extraction for AI agents. Pass any URL and a prompt, get clean JSON data back. Native MCP server with 100 free requests/month.3794 npmMIT
- AlicenseNot gradedqualityBmaintenanceGives AI agents a real browser to capture screenshots, PDFs, and post-JavaScript HTML directly from URLs, with no API key or signup required.MIT
foundrynet-scrapeofficial
FlicenseNot gradedqualityFmaintenanceEnables AI agents to extract clean, structured content from any web page via a pay-per-call API or with a Forge key.-
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.