"PostgreSQL MCP (Multi-Version Concurrency Control or specific usage)" matching MCP servers:

Enables ingestion of HL7 v2, ASTM, and JSON control results, Westgard multirule evaluation, automatic patient-result holds, explainable root-cause investigation, and supervisor-approved CAPA workflows for clinical laboratories. Agents can also establish targets, compute Levey-Jennings and sigma statistics, and verify corrective actions before a supervisor lifts a hold.

A legal-tech focused system that coordinates specialized agents for document classification, deadline extraction from Spanish legal texts, and strategic business intelligence. It integrates with Claude via MCP to provide semantic document search and automated deadline tracking using a Supabase vector database.

Enables AI assistants to search and retrieve security, privacy, and AI-governance controls from multiple compliance frameworks (e.g., NIST, HIPAA, OWASP) with cross-references, providing authoritative cited control text.

Fail-closed evidence manifests for financial AI research: one manifest records evidence artifacts, cutoff timestamps, checks, AI usage and human approval — one verdict before anything ships. MCP tools: gov_check, gov_report, gov_init.

IBAN validation across 89 countries, BIC/SWIFT and Swiss clearing lookup, batch validation, payment-reference, postal-address and Swiss QR-bill checks for AI agents. Connect via MCP or the REST API. Includes free quotas, paid credits and a Pro subscription. SEPA and country-risk indicators support payment-data checks; they do not confirm account ownership or replace beneficiary AML/KYC screening.

Integrates the Metis FCA Handbook AI Harness into Claude Desktop to analyze FCA Handbook applicability for financial products, services, or firms, returning structured compliance reasoning with verbatim citations.

Enables agents to validate data safety before storing, transmitting, or logging data, preventing GDPR/HIPAA/PCI-DSS violations with clear verdicts like SAFE_TO_PROCESS, REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE.

Resolves a company name, registrable domain, or LEI to its GLEIF legal entity record — LEI, legal name, jurisdiction, entity status, and registration status — for $0.05 USDC on Base paid per call over x402, with no signup or API key. Includes a free, no-wallet preview of price and coverage plus hard per-call and per-session spend caps, while misses and ambiguous matches cost nothing.

Automates GSTR-1 filing through Sandbox.co APIs, enabling seamless integration with Claude Desktop or API for GST return submission.

MCP server for Woody, an AI firearms expert that answers questions with verified citations, checks state-specific laws, and routes to specialist agents.

Enables checking AI-drafted answers to US retirement-account questions, flagging wrong facts, personal recommendations, and promissory claims with IRS or FINRA sources before they reach customers.

Enables verification of Japanese companies through JP-Verify's API: checking qualified-invoice registration (T-numbers) and Corporate Numbers, resolving company names to candidate numbers, retrieving official or romanised English names and addresses, and fetching major-shareholder tables from EDINET filings. Supports single or batch lookups with API-key or key-less sandbox access, returning raw responses plus quota and provenance metadata.

Records a sale of a vehicle, equipment or stock and produces a printable bill of sale with signature lines. Drafts can be edited and finalized into a frozen signing copy rendered as Markdown or self-contained HTML for print-to-PDF.

Enables auditing one or many websites from an EU address for cookie consent behavior, returning per-domain rows on the consent platform, first-layer reject availability, trackers and tracking cookies before consent and after reject, and Global Privacy Control response. Runs the work on Apify and hands back the dataset rows through a single tool.

Provides deal mechanics for creators to understand and negotiate pricing models, usage rights, and negotiation moves, based on structure rather than rate quotes.

Enables AI assistants to search a library of over 20,000 open legal skills by keyword, by meaning, or a hybrid of both, filtering by jurisdiction, language, practice area, or tag. It also returns facet counts for the collection and retrieves the full text of any selected skill.

Scans source code for possible Korean compliance risks (PIPA, Network Act, Credit Information Act, E-Commerce Act) and maps findings to specific legal provisions. Runs locally, exposes MCP tools for scanning and law lookup, and does not constitute legal advice. That's hedged (matches the project's "possible risk / not legal advice" rule), keyword-rich for search, and names all four laws.

Contract and wills legal tools for AI agents: statute-cited requirements per contract type and US state, non-compete enforceability for all 50 states + DC, intake schemas, async multi-agent contract drafting with free previews, and contract risk analysis.

Enables an AI assistant to determine which inspections a Swedish residential or commercial building must or should have—covering OVK ventilation, energy declaration, lift, radon, legionella and fire safety—including how often, the legal basis, who may perform them, and what is overdue from supplied last-done dates. Read-only with no account or API key required, and answers available in English, Swedish or Spanish.

Enables LLM agents to extract, validate, and mask personally identifiable information using deterministic regular expressions, reducing token usage and hallucination risks.