"Current oil price lookup" matching MCP servers:

Enables MCP clients to control a Nordic PPK2 for power profiling: configure source/measurement modes, set voltage, power DUT, measure current/power/energy, and capture logic channels.

Crash-test AI agents on real professional decisions. Agents take real tariff classification and patent examination cases, search reference libraries and rulebooks, submit a decision, and get an exact score with a receipt against what the professional actually decided. Most cases were decided after current models were trained.

MCP server for automating and introspecting native Qt applications (QWidget and QML) without source changes. Enables AI agents to control running Qt apps through UI snapshots, element lookup, and real input simulation.

Agentic Hardware-in-the-Loop (Agentic HIL) lets coding agents develop firmware on real embedded boards: flash, reset, read UART and exchange CAN traffic, diagnose and fix. Local, policy-gated MCP tools support OpenOCD, pyOCD and STM32CubeProgrammer, with pytest for CI.

MCP server for controlling B&K Precision and Manson bench power supplies, enabling voltage/current setting, output switching, and power cycling.

Enables an MCP client to generate synthetic Workday test data by searching for a template worker, cloning their job and organization context, and creating a fresh fake identity. It exposes separate tools for search, template lookup, identity generation, and a human-approved Workday Hire_Employee submission against a local mock tenant.

A Model Context Protocol server providing security vulnerability intelligence tools including CVE lookup, EPSS scoring, CVSS calculation, exploit detection, and Python package vulnerability checking.

Enables AI agents to query synthetic packaged-coffee pricing data for elasticity estimates, price-change simulations, guardrail checks, price-ladder validation, and competitor positioning while logging read-only tool calls. It also includes evaluation tooling for grading whether agents use those pricing tools correctly and ground their answers in tool outputs.

Enables AI agents to browse mobile-device availability and indicative pricing, ask the site questions, reserve free early-access slots, and check current capabilities for iOS Simulators, Android Emulators, and real phones.

Checks mocks, stubs, and spies against current production code to detect stale or mismatched test doubles without running any tests.

Enables Claude to interact with R package development workflows, including CRAN metadata lookup, dependency checking, testing, documentation validation, and release automation.

Enables agents to freeze the real inputs of a file or JSONL batch, then audit current outputs for missing, duplicate, unexpected, or malformed results and resume from the item IDs that still need repair. Runs locally over stdio with CPU only and no API key.

Enables coding agents to verify completion and current-state claims by classifying claims, requiring independent evidence/readback, resolving precedence conflicts, and blocking unsafe replays before reporting success.

MCP servers for building and running Xident age and identity verification from AI agents. They provide documentation lookup, sandbox test verifications, webhook debugging, and a production runtime with OAuth 2.1 authorization.

Provides AI tools with secure, real-time, permission-aware access to an Orangescrum workspace so users can search, create, and update projects, tasks, sprints, test cases, releases, risks, resources, and Wiki pages through natural language. It lets assistants summarize and plan work, automate repetitive effort, and keep delivery data current without switching context.

Currents MCP Server

Enables AI agents to build, launch, inspect and drive Garmin Connect IQ apps in the macOS Connect IQ simulator, returning screenshots paired with recognised on-screen text and tap-ready coordinates. It runs whole interaction flows—including the same steps across several watch devices—in a single call, without needing the simulator to be frontmost or the screen unlocked.

Exposes five tools that let an assistant list and inspect schema-mutation benchmark tasks, grade submitted JSON tool calls against canonical answers, run the benchmark against a chosen model, and read dataset provenance. It enables measuring whether a model follows the current tool schema or falls back on a memorized one.

A local MCP server providing 7 QA testing tools for client validation, test case generation, percentile calculation, HTTP error classification, SLA evaluation, API response validation, and customer lookup, intended for use with OpenCode or VS Code Copilot.

Lets any MCP-capable coding agent read and update an app's QA memory, test-case catalogs, coverage gaps, and Playwright run history. It exposes 11 tools covering status, scanning, case lookup, next-ID generation, memory search/add/forget, and result ingestion.