"HERE" matching MCP servers:

Enables users to find people who recently started matching roles at target companies within a specified lookback window, returning flat JSON rows with profile, title, start month, prior role, move type, and source.

An MCP server for querying Historic Environment Records across England and Scotland, enabling searches of listed buildings, monuments, and heritage sites via ArcGIS REST APIs.

MCP server that exposes the Herdr terminal API as callable tools, enabling AI agents to manage terminal workspaces, tabs, panes, and agents. It dynamically generates tools from the Herdr API schema and communicates via Unix socket.

MCP server that connects AI clients to the arena-hero game's browser-stored exploration data via WebSocket, enabling queries for resource and obstacle coordinates.

Connects AI assistants like Claude and ChatGPT to HERO Handwerkersoftware so users can look up and manage customers, projects, quotes, invoices, appointments and catalogue products in plain language, and create new projects from emails or calls. Runs locally against the HERO API, staying read-only unless writes are explicitly enabled.

MCP server for the Computeback agent rewards marketplace and CB Hire B2B labor marketplace. Agents browse the storefront (compute, voice, memory, storage, 25+ categories) using $NOMD tokens, and discover/accept paid B2B work (email/voice/SMS/landing-page campaigns) and/or book travel on Autonomad for $NOMD earnings on Base L2.

Tell your AI agent what you want a model to do. It searches Hugging Face for each part of the job and tells you which parts already exist there: which are an exact fit, which to fine-tune, which to train, and which are just code. Every model it names is real, current, and sized for your hardware.

A comprehensive MCP server for checking package versions and rating package quality across Python (PyPI), JavaScript/TypeScript (npm), Dart (pub.dev), and Rust (crates.io) ecosystems.

Enables a primary Codex agent to queue independent, read-only research jobs that execute in parallel using any OpenAI Responses-compatible inference provider while the agent continues its own work.

Enables AI tools to manage Anki flashcards, including deck management, card search, creation, editing, deletion, and statistics.

Verified, version-pinned records of new dependency bugs. When your coding agent hits an error it cannot fix in one try, it looks the error up here before searching the web: on 56 fresh bugs it said correctly whether the bug was known or fixed 91% of the time with Cairn, 68% without. Read-only by default. Benchmark and data (CC BY 4.0): https://cairncommons.dev/benchmark

AgentRoots is an MCP server for agent continuity that preserves goals, findings, and evidence across sessions. It enables agents to propose, review, and reuse compact, evidence-backed state instead of replaying transcripts.

Provides 13 Solana DeFi intelligence tools for AI agents, paid per-call via micropayments (USDC). Enables pulling live DeFi data and automatic payment settlement.