"Searching for documents or information related to PDFs" matching MCP connectors:

The first low-latency wire service purpose-built for AI agents. Ingests 54+ public APIs and 71k RSS feeds across 232 countries, outputs CWF (Cognitive Wire Format) – 80% shorter than JSON, sub-second WebSocket delivery. 9 MCP tools: get_latest_signals, search_signals, get_fused_signal, scope_signals, get_facet_manifest, list_facets, get_related_signals, list_data_sources, get_billing_profile. 26 citable fusion products with verifiable formulas – no black-box scores.

Bounce Watch tells you what just changed at a company, and when. Who raised money. Who hired a senior person. Who opened an office, won a customer, announced a partnership, achieved a certification. Who is laying people off. Over forty kinds of event, and every single one carries the date it happened. That date is the whole point. Knowing a company raised money is not very useful on its own. Knowing they raised it eleven days ago is the difference between a good call and a late one. Ask in plain language — "which Dutch companies under 50 people raised in the last month", "what has been happening at stripe.com", "anything new at the companies I am watching" — and get real company names back with dates and sources. Three million events so far, and the list grows every day. Not every event matters the same. A funding round and a conference appearance are both events, but they are not the same news, so each one carries a score from 1 to 10. Set a minimum and the noise disappears from the answer. It can also come to you rather than waiting to be asked. Put a watch on a company and you get told the next time something happens there — pushed to your webhook, or waiting for you the next time you ask. And when we do not know, we say so. "Nothing happened at this company" and "we have not checked this company recently" look identical from the outside: an empty answer. An AI assistant will read that empty answer and confidently tell you the company is quiet. So every response says how recently we looked. Ask for something we do not recognise and we tell you what we do recognise, instead of quietly returning a few rows that look like a real answer. Ten tools, eight of them read-only. The two that write are annotated, so a client can gate them behind approval instead of guessing. Connect with OAuth — press Connect and approve in the browser, no key to paste. Every new account gets 2,500 free credits, no card and no expiry. Paid plans start at 99 EUR a month, and the same account covers the regular REST API too.

Ask Personio Recruiting the recruiting-ops questions dashboards miss by connecting applications, stage transitions, candidates, recruiting jobs, categories, org units, workplaces, jobs catalog, webhooks, event activity, and intake documents. Find stage-movement stalls, candidate freshness gaps, source quality by job/category, hiring load by department and workplace, webhook delivery issues, intake readiness gaps, and bottleneck owners. No dashboard build. No SQL.

Auto-discover validation rules from data — scan, profile, health-score. No rules to write.

Formula-backed WorkPaper tools for workbook readback, input edits, and JSON persistence.

Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.

Supplier intake and hidden-inventory matching for travel/resort/property offers.

DePIN telemetry, DAG manifold correlation, and verifiable data products for AI agents.

Baking unit conversion (cups/grams/temp/recipe scaling). convert_amount, convert_temperature

Multi-tenant FastMCP server for Charles Schwab brokerage data, monetized via DPYC Tollbooth

Wash-filtered intelligence for x402: categories, services, wash analysis, trends.

Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.

The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.

Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.

Fuzzy entity resolution and dedupe for names, addresses, and company records. $0.02/call via x402.

58 AI data quality, data matching, and data enrichment APIs for better data ROI

MCP server for Codat — companies, connections, invoices, bills and financial statements.

Read and write patients, facilities, medical documents, and consolidated FHIR records in Metriport.

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.

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.