"A database that can be operated or managed" matching MCP servers:

Enables AI assistants to interact with self-hosted Dynatrace Managed environments to retrieve observability data, security insights, and performance metrics. It allows users to query problems, logs, events, and SLOs through natural language interfaces in both local and remote modes.

Provides live wait times and office details for all 60 Oregon DMV field offices by scraping the ODOT website, with no authentication required.

Enables LLM agents to access Global Database's company intelligence, including company profiles, financials, ownership, people search, prospecting, and KYB/compliance lookups against official registries.

Enables enterprise agent fleets to register workers, dispatch tasks by capability, monitor continuous heartbeat telemetry, trip automated circuit breakers, and recover from checkpointed state through a zero-dependency MCP server.

A Model Context Protocol server that enables LLMs like Claude to interact with SQLite and SQL Server databases, allowing for schema inspection and SQL query execution.

Enables orchestration of worker registration, capability-based task dispatch, heartbeat telemetry, automatic circuit breaking, and checkpoint recovery for distributed agent operations.

MCP-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.

Enables teams to automate certificate issuance and query engagement data from the thatsme platform via AI-powered tools like search_events and issue_certificates.

Checks whether an open-weight LLM fits your GPU: VRAM for weights, KV cache and overhead at each quantisation, a tokens-per-second ceiling, the longest context that fits, and what would work instead when it doesn't. Reads any Hugging Face repo's config.json. Free, read-only, no API key.

Universal HTTP 402 Micropayment Protocol & Autonomous Economic Settlement Engine for AI Agents on Base L2.

A server that provides access to Baidu Cloud Vector Database functionality through the Model Context Protocol, enabling LLM applications to perform vector searches and database operations via natural language.

Answers why a specific number in a Chinese listed company moved — margins, cash flow, inventory, management commentary, policy impact — by reading filed reports and IR transcripts and returning figures with the document and announcement number attached. It deliberately refuses price, valuation, and recommendation queries, returning a "gone_by_design" error instead.

Enables searching and retrieving content, module information, and Twig template snippets from a-blog cms via its GET API.

Lets an AI assistant read call and message history, send texts and picture messages, reach Phone Book contacts by name, and — once switched on — place calls run by a voice agent, all limited to the phone numbers the user ticks. Hosted remotely with OAuth sign-in, so nothing needs to be installed locally.

Gives AI assistants full control over Microsoft Access databases, enabling creation and management of forms, VBA, tables, queries, and more through natural language.

Enables semantic code search across multi-language codebases using natural language queries, integrated with Qdrant vector database for fast, cached retrieval.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

Perfume database API with verified notes: 1,500+ perfumes, 160+ houses, 400+ raw materials in a fragrance ingredients database. 12 tools over MCP and REST, OpenAPI spec, free and keyless, answers in 10 languages. Look up a note or raw material and get the perfumes that use it, or a perfume and get its full top, heart and base pyramid. Built by Scento.

Connect your database to your AI agent, read-only, without sharing your password. Maplith Bridge serves a folder of data files over MCP behind a token you create, and fills it from PostgreSQL under a role that can only read.

A free, open reputation registry for AI microservices: check a service's trust score before calling it and submit a rating afterward. Ratings can be backed by cryptographic receipts signed by the service and are recorded in a verifiable Merkle audit log.

This MCP server is designed for planning with Claude Code, Cline, or Cursor and making changes with Cerebras to maximize speed and intelligence while avoiding API limits. It uses the Qwen 3 Coder model for high-quality code generation and can be embedded in IDEs.

Enables MCP clients such as Claude to look up AI agents registered in the ERC-8004 registries on Robinhood Chain, retrieving profiles, owners, feedback, validations, settlement evidence, and USDG-weighted trust scores. It is read-only and requires no wallet or API key, and can be reached either as a hosted remote endpoint or locally via npx.

Enables MCP clients to run 80+ ready-made AI apps and generate images, videos, and songs from text prompts or local photos, using the free house engine without an API key or premium models with one. Results can be polled and saved directly into a folder.

A Model Context Protocol server that enables large language models to access database metadata and perform cross-engine data querying across diverse database ecosystems.

An MCP server that lets any MCP client run or join a governed MACP Decision session, enforcing who may propose, vote and commit, and returning a binding Commitment whose hash anyone can recompute.

Local MCP consistency checks for supplied OAuth test results and release evidence. Two separately launched Python stdio servers; checks test supplied-value consistency, not authenticity, live proof, or approval. Weio is operated by AI agents under human ownership.

Self-hosted Docker sandboxes for coding agents: create a sandbox with its own Docker daemon, deploy a docker-compose stack into it, read and write its files, and get a URL for every app. Tokens can be limited to one sandbox.

Provides an MCP endpoint for agents to check whether a real-world fact can be verified, covering businesses, listings, objects, and places, while refusing claims about individuals. It acts as a demand sensor that logs verification attempts, even for unfulfillable requests.

A server that interfaces with the Hedera Testnet Mirror Node API, converting its OpenAPI-defined endpoints into MCP-compatible tools that can be accessed over Server-Sent Events (SSE).

Enables AI agents to keep a dedicated local workspace for file-producing tasks, preserving source material, numbered output versions, checks, and approvals so work can be resumed across conversations. It also tracks declared inputs and workflow steps so affected stages can be rebuilt and versioned recipes reused for new tasks.