Registry / Discover, then inspect
MCP Server Registry.
An index with a memory.
Browse 2,232 listed servers in this view. Discover a public identity, then open its report to inspect the available findings and coverage.
The engine offers 184 detection rules. Listing a server does not mean every rule ran, or that the server was successfully launched.
US Business Entity Data
Provides access to SEC company search and SBA resources from US government databases.
us-census-bureau-data-api-mcp
The U.S. Census Bureau Data API MCP connects AI Assistants with official Census Bureau statistics.
user-feedback-mcp
Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor.
usermcp
With just one line of code, your MCP or agent can record and manage user preferences with the user profile MCP, without requiring any database dependencies.
Usitc Edis
USITC IDS (Investigations Database System, ids.usitc.gov) — the CASE
uteke
🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with semantic embeddings. Single Rust binary, zero config, fully offline.
Utilix
300+ offline developer utilities, plus 21 AI tools with a free API key. JSON, JWT, regex, cron, SQL.
UUID Generator — v4, v7, ULID, Nanoid (Batch 100)
Unique identifier generation API for AI agents. Generate UUID v4 (random), UUID v7 (time-sortable), ULID, or Nanoid. Batch up to 100 at once. Sortable, compact, or cryptographically random formats. Tools: utility_generate_uuid. Use this for database record IDs, session tokens, correlation IDs, or idempotency keys. Returns ready-to-use identifiers in your preferred format. Returns: {ids[], format, count}. No API key required — x402 micropayment $0.001/call on Base L2.
Val Town
Deploy serverless TypeScript on Val Town: HTTP vals, cron, SQLite, email, OAuth.
valv
Let coding agents query any SQL database safely. Read-only by default and scoped by your policies.
Vaultbase
Connect AI agents to a self-hosted Vaultbase backend: records, collections, hooks and SQL.
vcon-mcp
MCP Server for IETF vCon - Open Source Core
vector-embedding-mcp-server
MCP Server for AI Embedding and RAG functionality
Vector Panda
Operate your Vector Panda collections: search and upsert vectors, schema, measured indexes, exports.
vedb-mysql-mcp-server
MCP server for VeDB MySQL
vehicle-database
MotiveGrid Vehicle Database is an MCP server that provides AI assistants with grounded vehicle intelligence. Compare cars, retrieve vehicle scorecards, analyze five-year cost of ownership, evaluate safety and driver-assistance features, and generate personalized vehicle recommendations using structured automotive data instead of web search.
Vericto account (OAuth)
Your Vericto workspace over OAuth: setup status, rules, CI reports, docs search and SQL checks.
Vericto: database guardrails for AI agents
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
Vericto Proxy mode (local, PostgreSQL)
Read-only PostgreSQL for AI agents: every statement is checked before it runs. No account needed.
Vericto SQL Firewall
Check SQL against your Vericto rules before it runs: blocks destructive or risky statements.
Veto — SQL Safety & Cost Oracle
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Vibe BI MCP
Ask business questions in plain English. Get instant answers from your database, no SQL needed.
vibe-check-mcp-server
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
Victauri
In-process MCP server for Tauri apps: DOM, IPC with bodies, Rust state, SQLite. Debug builds only.
02
A name becomes
a traceable record.
Open a server to follow its findings into rule-level evidence, assessment method and coverage. A report keeps unavailable inputs and failed calls visible, so a gap cannot silently become a clean result.
A listed identity, an assessment and an observed response are different kinds of evidence.
Read the evidence modelCarry the record forward
A useful result survives its first reading.
Read the evidence in context before using an assessment in a deployment decision. Report exports preserve the result and its limits; signing depends on the deployment’s configured credentials.