"An explanation or resources about vectors (mathematics, physics, programming, or graphics)" matching MCP connectors:

Dedupe, flatten and clean messy JSON rows (emails, phones, URLs, HTML) in one call, as JSON or CSV.

Join two lists of JSON rows on a key, like SQL or VLOOKUP: left, inner, full, anti joins, union.

Compare two versions of a JSON row list: what was added, removed or changed, field by field.

Convert PDF bank statements to checked Excel, CSV or JSON with balance validation.

Sources in, feeds out: an open, ever-growing database of real-time public data, enriched.

Converts customer-supplied PDF bank statements into checked Excel, CSV, or JSON with balance validation. Hosted Streamable HTTP endpoint; each user brings their own MainBook API key, and the server never connects to bank accounts.

Deterministic company, entity and location lookups for agents - per call, x402 or API key.

Company-specific regulatory assessments for concrete business questions, as structured data or PDF.

Fuzzy entity resolution and dedupe for names, addresses, and company records — the "is this the same person/company" problem that breaks exact-match joins. Clean CRM exports, merge duplicates, reconcile vendor lists. Pay-per-call via x402 (USDC on Base): $0.008/call, no account or API key. tools/list and /openapi.json are free for discovery.

Scans text for personally identifiable information — emails, phone numbers, SSNs, credit card numbers, physical addresses, names — and returns a redacted version. Built for agents sanitizing user content, support tickets, logs, or documents before storage, sharing, or feeding into another LLM call. Pay-per-call via x402 (USDC on Base): $0.01/call, no account or API key. tools/list and /openapi.json are free for discovery.

Self-hosted, open-source MCP gateway: turn any API, database or MCP server into custom connectors for Claude, ChatGPT, Gemini, Copilot & Cursor — no code. Converts REST, SOAP, WSDL, GraphQL & SQL to MCP, with OAuth2, RBAC & audit log. 175+ pre-built adapters. This is the public read-only demo endpoint — run your own at https://github.com/HelpCode-ai/anythingmcp

Interact with your Google Cloud Datastream resources using natural language commands.

KamaiOAuth

io.kamai.mcp

Kamai is an AI-powered construction blueprint intelligence platform that automatically extracts quantities, measurements, objects, rooms, walls, and other structured data from construction drawings. Through MCP, you can connect Kamai directly to AI assistants and ask questions about your plans in natural language, generate takeoffs and tables, analyze relationships between building elements, and use blueprint data inside broader estimating, procurement, and construction workflows. Kamai turns

Chrysai provides a hosted MCP server for AI-driven data operations. After connecting an MCP client to the endpoint, you can use MCP tools such as create_app, list_apps, read_data, write_data, update_data, delete_data, and update_app, plus schema resources, to manage persistent structured data through natural language.

Send every row of a dataset, file or Google Sheet to any REST API as its own templated request.

Push rows from a dataset, file or Google Sheet into a Postgres, Supabase, Neon or MySQL table.

Extract text, tables and metadata from every PDF linked in a dataset, CSV or Google Sheet.

Run one LLM instruction over every row to classify, extract or summarise into new columns.

Baselight’s MCP server lets you seamlessly integrate your favourite applications with the Baselight platform. By connecting to the MCP server, you can browse, discover, and query 70,000+ datasets and 450+ billion rows directly from your preferred environment—whether you’re building, analysing, or exploring.

Document processing, data conversion, and web content APIs for AI agents. All tools are free via MCP. Also available as a paid x402 Agent API (Stellar XLM or Solana USDC, no API key required). Tools: extract text from PDFs, merge PDFs, generate QR codes, convert CSV to/from JSON, count words/stats, and fetch + clean any public URL with Mozilla Readability.