Skip to main content
Glama
scrapedatshi

scrapedatshi-mcp

Official
by scrapedatshi

sync_to_vectordb

Scrape a web page, embed the content, and store vectors in your vector database in a single call. Add web data to your RAG pipeline for retrieval.

Instructions

Full RAG pipeline: scrape a URL, embed the chunks using your embedding provider, and inject the vectors into your vector database — all in one call.

Use this when the user wants to ADD web content to their vector DB for later retrieval. The user brings their own embedding provider and vector DB.

PRE-FLIGHT REQUIRED — before calling:

  1. Call verify_provider_key(embedding_provider, 'embedding') → get live embedding model list

  2. Present models to user, ask them to choose one

  3. Call list_vector_db_providers if user is unsure what config fields are needed

  4. Ask: 'Is this a JavaScript-heavy page or SPA?' → js_render

  5. Present Contextual Retrieval as a recommended upgrade: 'Would you like Contextual Retrieval (RAG 2.0)? It enriches each chunk with LLM-generated context before embedding, improving retrieval accuracy by 35–50%. Costs ~$0.001/chunk extra. If yes, I'll also need your LLM provider and model.'

  6. If contextual_retrieval=yes: call verify_provider_key(llm_provider, 'llm') too

Keys can be omitted if set as environment variables (OPENAI_API_KEY, PINECONE_API_KEY, etc.).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe web URL to scrape, embed, and inject into the vector DB.
overlapNoToken overlap between consecutive chunks. Default: 50.
selectorNoOptional CSS selector to target a specific page section.
js_renderNoUse headless browser to render JS before scraping. Ask the user before enabling.
llm_modelNoLLM model name from verify_provider_key. Do not guess or hardcode.
vector_dbYesVector DB provider. Call list_vector_db_providers to see required config fields for each.
chunk_sizeNoTarget token count per chunk. Default: 512.
llm_api_keyNoAPI key for the LLM provider. Can be omitted if set as env var.
llm_providerNoLLM provider for contextual retrieval. Verify with verify_provider_key(provider, 'llm') first.
embedding_modelNoEmbedding model name from verify_provider_key. Do not guess or hardcode.
vector_db_configYesProvider-specific config. Call list_vector_db_providers for required fields. API keys within this config can be omitted if set as env vars. Examples: pinecone: {"index_host": "https://my-index.svc.pinecone.io"} | qdrant: {"url": "https://cluster.qdrant.io", "collection_name": "docs"} | supabase: {"connection_string": "postgresql://...", "table_name": "documents"} | chroma: {"collection_name": "docs"}
embedding_api_keyNoAPI key for the embedding provider. Can be omitted if set as env var.
embedding_endpointNoPublic HTTPS endpoint for Ollama only (e.g. from ngrok). Not needed for cloud providers.
embedding_providerYesEmbedding provider. Call verify_provider_key(provider, 'embedding') first to get available models.
contextual_retrievalNoEnable RAG 2.0 contextual enrichment before embedding. Present as a recommended upgrade. Requires llm_provider and llm_model.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the full pipeline process and pre-requisites (e.g., need to verify provider keys). It mentions that keys can be omitted if set as env vars. However, it does not discuss side effects (e.g., overwriting existing data), error scenarios, or rate limits, leaving some gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: a one-line purpose, followed by usage context, then a numbered pre-flight list. It is front-loaded with the most important information. Every sentence adds value, and the length is appropriate for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (15 params, nested objects) and lack of output schema, the description covers the main behavioral aspects, prerequisites, and configuration. However, it omits what the tool returns (e.g., success status or vector count), which is a notable gap for completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining how to obtain values for parameters like 'embedding_model' (from verify_provider_key) and provides example configurations for vector_db_config. It also clarifies the purpose of optional features like 'js_render' and 'contextual_retrieval'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it performs a full RAG pipeline: scrape, embed, inject into vector DB. It specifies the verb ('ADD web content') and resource, and distinguishes from sibling tools like 'scrape_url' or 'ingest_file' by combining multiple steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use: 'when the user wants to ADD web content to their vector DB'. It provides a detailed pre-flight checklist referencing other tools. However, it does not discuss when NOT to use it or offer specific alternatives for other scenarios (e.g., if user already has chunks).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/scrapedatshi/scrapedatshi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server