Skip to main content
Glama
scrapedatshi

scrapedatshi-mcp

Official
by scrapedatshi

autorag

Crawl an entire domain, chunk every page, embed all chunks, and inject into your vector database in a single call.

Instructions

Full AutoRAG pipeline: crawl an entire domain, chunk every page, embed all chunks, and inject into your vector database — all in a single call.

Use this when the user wants to bulk-ingest an entire website into their vector DB. This combines crawl_site + sync_to_vectordb into one operation.

⚠️ ALWAYS confirm the max_pages limit with the user before calling. Default is 5 pages. Each page is fetched, chunked, embedded, and injected. For large sites, warn about credit usage and wait times first.

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. Confirm max_pages with the user

  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.'

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

Keys can be omitted if set as environment variables.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe root domain to crawl (e.g. 'https://docs.example.com').
overlapNoToken overlap between consecutive chunks. Default: 50.
selectorNoOptional CSS selector applied to every page before chunking.
llm_modelNoLLM model name from verify_provider_key. Do not guess or hardcode.
max_pagesNoMaximum pages to crawl and inject. Default: 5. Maximum: 200. Always confirm with user for large sites.
vector_dbYesVector DB provider. Call list_vector_db_providers to see required config fields for each.
chunk_sizeNoTarget token count per chunk. Default: 512.
crawl_modeNo'sitemap': reads sitemap.xml (best for docs/blogs). 'spider': follows links from root URL (works on any site).sitemap
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.
exclude_patternNoSkip URLs containing this substring (e.g. '/blog/').
include_patternNoOnly crawl URLs containing this substring (e.g. '/docs/').
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.
embedding_api_keyNoAPI key for the embedding provider. Can be omitted if set as env var.
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 the full burden. It explains the pipeline steps and warns about resource usage. However, it does not explicitly state whether the operation is destructive (e.g., overwrites existing vectors) or idempotent, which is a minor gap.

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

Conciseness4/5

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

The description is well-structured with a clear opening statement, usage guidelines, and a detailed pre-flight list. It is relatively long but justified given the tool's complexity and number of parameters. Could be slightly more concise by reducing redundant emphasis on max_pages confirmation.

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

Completeness3/5

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

The description covers the overall process, pre-flight steps, and warnings, but it does not describe the return value or error handling. Since there is no output schema, the agent would benefit from knowing what the tool returns (e.g., status, count of ingested chunks) and how to handle failures.

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

Parameters3/5

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

Schema coverage is 100%, so each parameter already has a description. The description adds no new information about individual parameters beyond what the schema provides, but it does contextualize the flow and pre-flight requirements, which indirectly helps parameter understanding.

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 defines the tool as a full AutoRAG pipeline: crawl, chunk, embed, and inject into a vector DB. It distinguishes itself from siblings like crawl_site and sync_to_vectordb by combining them into a single operation.

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

Usage Guidelines5/5

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

The description provides explicit when-to-use (bulk-ingest entire website), a required pre-flight checklist with steps to call verification functions and confirm limits, and warns about credit usage and wait times. It also suggests alternatives and upgrades.

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