"A server to improve math capability of AI" matching MCP connectors:

500+ pay-per-call tools + skill packs. USDC + USDG on 12 chains, or free via proof-of-work.

Neutral freight reference + validation layer for AI agents: ADR, HS, UN/LOCODE, freight math

Neutral, verification-gated MCP directory of Japan construction contractors (KIRA-audited).

Host-owned vacation-rental direct booking via VRP. Signed offers, 0% commission. Not an OTA.

SEC dilution data, live market data, and news for U.S. equities, with point-in-time as-of queries

Find 76,000+ curated healthcare service vendors across 25 categories and all 50 US states.

MCP server for live, sourced Brazilian public data from the official IBGE APIs.

SSRF-safe web intelligence: 4 outcomes, 43 paid x402 tools, 3 free tools and a URL preview.

Enumerate and inspect PubFi capabilities, then execute an exact selected route.

Live internet-censorship signals and tamper-evident, pre-registered, hash-chained AI model evals.

Manage products, EU Digital Product Passports, operator parties, and GS1 EPCIS supply-chain events.

MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania).

Plain-English git via MCP: 22 tools to branch, commit, push, and tag. No git jargon.

User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.

APILayer MCP Adapter turns APILayer's REST APIs into Model Context Protocol tools so any MCP-compatible client can call them directly in conversation. The first release ships ipstack IP geolocation and security lookups (single IP, caller's IP, and bulk). Additional APILayer services are added by registering them in a single config file, so the catalog grows without client-side changes.

Generate, edit, and export data-architecture diagrams from your AI. Column lineage, PNG in chat.

MCP server for generating rough-draft project plans from natural-language prompts.

AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.

Research-only MCP server that turns your AI into a quant research desk: describe any strategy in plain English, get a real backtest with institutional metrics and a verifiable audit bundle. No trades and your AI never writes the code, so it can't fool the numbers.

Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.