"An agent for conducting research" matching MCP servers:

The Problem Modern distributed systems and AI agents require robust operational scaffolding. Simple CRUD apps or mock loops fail when subjected to real-world edge cases, asynchronous boundaries, and security constraints. The Solution An isolated execution platform for AI agents. An agent is given a broken service and a bounded toolset inside a disposable sandbox. Every command passes throug

A local MCP server that lets Hermes supervise Claude Code, delegating focused coding, research, or review tasks to the Claude Code CLI and managing worker sessions, background jobs, cancellations, and read-only reviews.

MCP server for persistent SSH sessions with tmux integration, port forwarding, and SFTP file writes, built for AI agent workflows.

Remote MCP server for Android CLI agent build gate that enables checking builds, suggesting fixes, explaining permission blockers, issuing receipts, and exporting logs.

MCP wrapper for the agent-msg.sh file-based message bus, enabling MCP-compatible clients to send, receive, and manage inter-agent messages with bound identity and HMAC-signed payloads.

An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.

An MCP (Multi-Agent Conversation Protocol) server that enables interaction with Google's Managed Service for Microsoft Active Directory through its OpenAPI, allowing users to manage identity resources through natural language.

A single-purpose MCP server that lets an AI assistant run commands over SSH on a fixed, pre-configured host only, with an explicit per-call confirmation gate before execution.

MCP server for overseer.nvim — gives any MCP-capable coding agent running inside Neovim (Claude Code, Codex, Gemini CLI, opencode) the same visibility and control over tasks the user has: list, run, tail, restart, stop. Agent-started dev servers land in the user's own task list instead of becoming invisible orphaned processes.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

An open MCP server that gives any AI agent SSH access to remote Linux/Unix machines — shell commands, file read/write, and SFTP transfers.

Provides blocking await tools to poll commands, URLs, or files until a condition is met, eliminating the need for sleep loops in agent workflows.

Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Percival Ubuntu is a security-focused MCP server for safe Ubuntu operations, optimized for the Nanobot agent. It enables file management and command execution under strict security policies.

An MCP server for creating, validating, and formatting Git commits with emojis following the conventional commit standard.

Enables Windows users to connect Antigravity CLI as an MCP subagent for coding tasks such as file reading, code execution, edits, and terminal commands, with model selection, conversation continuity, and streaming progress.

Enables an AI agent to run shell commands and move files inside a WSL distro on the same Windows machine via wsl.exe, with no sshd, key, or port required. Each pre-registered distro-and-user entry enforces guard policies limiting dangerous commands, Windows interop, write targets, and accessible paths.

Provides workspace-scoped file operations and command execution tools for building Cursor-style agents, along with system prompts and tool definitions for LLM integration.

An MCP server that enables agents to run commands interactively in live terminal panes a user can watch and type in, and to list, create, read from, and send keys to any session, window, or pane.

Lets an agent load a design once into a long-lived OpenSTA session and then run static timing and power analysis through dedicated tools or arbitrary Tcl commands. Enables setup/hold slack, TNS/WNS, fmax, DRV, and power queries against the live session.

Enables AI assistants to manage remote servers via SSH with 14 commands for execution, file transfer, auditing, and monitoring.

agentic_ssh is written in Rust and specifically engineered to provide agent-hardened, token-efficient, and asynchronous SSH orchestrations for AI agents. It automatically discovers hosts from your local SSH configurations, manages connection heartbeats, handles silent network dropouts, and supports detached background job scheduling with isolated session logging

An MCP server for driving an ITS session on a PiDP-10 emulator over raw TCP, supporting persistent connections, raw control-byte transmission, and escape syntax for DDT commands. It enables interaction with ITS systems through natural language via MCP tools like open, send, read, and status.

Provides a secure interface to run Anthropic's Claude Code CLI as an MCP server, enabling task execution, persistent memory, and integration with MCP-enabled IDEs.

Drive Elixir terminal UIs headlessly from an agent: start a TUI session, send keystrokes, take structured screenshots, and read TEA model state as MCP resources. Also exposes adaptive-UI recommendation tools and, when raxol_agent is loaded, read-only coding-agent session tools.

An MCP server that lets an AI agent use a real terminal the way a person does: type, press keys, click, read the screen, take a screenshot.

Delegates coding and read-only exploration tasks to the Antigravity CLI as blocking headless runs, mirroring live progress to on-disk stream transcripts and diffing git status to report touched files and out-of-scope edits. Supports resumable conversations, per-call model/agent/effort overrides, idle and hard timeouts, and discovery of available models and agent profiles.

Enables an AI agent to run local tools on the user's own machine via stdio, including command execution, workspace file read/write, and system status checks.

Enables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.