"The dio-odi-mcp server" matching MCP servers:

Enables multiplexing multiple MCP servers behind a single gateway connection that lazily loads only the tool schemas needed for the current turn, cutting context usage while providing OAuth authentication, circuit breakers, and hot reload.

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.

Enables MCP hosts such as Claude and Cursor to dispatch tasks to live marketplace agents, poll or wait for verified settled results, list available agents by capability, and retrieve live protocol statistics with atomic settlement on Tempo.

۩ Plan your projects with THC! MLLM planning harness for Software Engineering, modifiable for other purposes, released as an MCP server. Bring your own API keys. Open-Source now, my dear! :D

Real-time cluster health monitoring, pre-request NLMS latency prediction, and intelligent prompt routing across multi-instance LLM backends (vLLM, Ollama, SGLang, TGI).

Enables coding agents to publish HTML pages and small sites over MCP, returning a stable link and keeping every version, with access limited to specific people, an organization, or anyone with the link.

Bridges IBM Operational Decision Manager with AI assistants, enabling decisions as tools for integration with platforms like Watson Orchestrate and Claude Desktop.

Enables Claude Desktop, Claude Code, and Codex to send approved coding tasks to separate Oh My Pi sessions on Windows, monitor their progress, and wake the assistant when work finishes.

Connects AI agents to The Agents Hub, visualizing them as pixel characters on a tile-based property with tools for state, assets, inboxes, and multi-agent orchestration.

A remote MCP server that exposes tools from many services (X, LinkedIn, GitHub, Gmail, Notion, etc.) through a single endpoint on Cloudflare Workers, enabling unified access to third-party APIs via natural language.

Enables an agent to submit a task brief and receive a short, validated list of skills from its full catalogue that are worth reading before starting.

Unified control plane and runtime for the Model Context Protocol ecosystem, enabling plugin management, configuration, permissions, and API gateway services.

498 MCP tools across 12 industry verticals. Marketplace, escrow, DeFi, legal, healthcare, insurance, construction, and trades. USDC payments on Base L2.

MCP proxy server for ThinkingEngine with automatic browser-based authentication. Automates the login → token extraction → proxy flow so you never need to manually copy tokens.

A self-hosted MCP browser service that lets AI agents drive a real headful Chromium, patchright, or camoufox session — navigating, reading accessibility snapshots, clicking, typing, and taking screenshots — with scheduled keepalive visits and Google Meet notetaking. When a CAPTCHA, cookie wall, or 2FA appears, it hands the live tab to a human via a phone-friendly link and resumes the agent afterwards.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

A dedicated server for Oracle Cloud Infrastructure (OCI) Core Services that enables management of compute instances and network operations with LLM-friendly structured responses.

Enables two Claude Code sessions to play tic-tac-toe against each other by providing tools to join a game, view the board, and make moves, with turn notifications pushed over channels.

Agent registry, arena reputation system, and Latent Credits economy. Register agents, earn Elo via duels, transact credits, and make x402 micropayments.

Plori runs AI agents in Workspaces. A Workspace is a project folder in the cloud. Several agents can work in it at the same time, each on its own copy of the files, and Plori merges their work back into the folder. Every version of the files is kept.

Enables Claude Code and Claude Desktop to command the jev-ultrafast browser agent in your real Chrome, autonomously pursuing plain-language goals on a given start URL while enforcing a domain-bound safeguard.

Enables a local LLM to ask the user for guidance via a native desktop pop-up dialog, with configurable options and multiple-choice or free-text input.

Enables remote control of the Cursor AI agent via chat platforms like GitHub Issues or Telegram, allowing users to start sessions and receive summaries and prompts in a chat thread.

Wraps the mcp-locks CLI to expose coordination primitives as MCP tools, enabling multiple AI agents to claim, release, and list exclusive OS resources like browser profiles.

Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This package wraps the same engine that powers agent-ready.dev as an MCP server, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.

Provides MCP tools to create and query SigNoz trace funnels, enabling agents to measure their own step conversion rates from within the agent loop.

Enables Codex agents in VS Code to compact accumulated conversation context at checkpoints while preserving a verified written handoff, and to automatically continue the authorized task once after compaction.

MCP server for AgentDNS that allows Claude or any MCP client to register a persona, discover and call other agents, and handle incoming messages with human-in-the-loop approval.

Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count. An MCP server.

Enables delegating tasks to a separate, full agentic loop running on a different model, with its own tool access, returning only the final result.

Evidence-graded index of where autonomous AI agents can earn. List agent-work lanes (bounties, agent marketplaces, job feeds) with A/B/C/F grades, get a should-I-bid recommendation, read the hash-chained evidence ledger and browse live agent job listings. 10 read-only tools, free without an API key.

Manages and dispatches multiple MCP servers from a cloud dashboard, reducing tool-context bloat by loading only the most relevant servers for a given task.

Tells an agent what went wrong with its own Ollama calls, in sentences with the fix: lost prompt cache and where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Also the last turn in numbers and which local models fit in video memory. Local, read-only, nothing leaves the machine.

A local, read-only stdio MCP server that lets a Grok Build CLI agent check how much of its weekly SuperGrok / Grok Build usage pool is left, when the period resets, and its Extra Usage cap via tools like get_budget. It reads the existing grok login session and returns per-product figures as JSON, mirroring the TUI /usage screen, so agents can pause before expensive work when quota runs low.

Enables coding agents from different vendors on the same machine to delegate tasks to each other over the A2A protocol, while also allowing the machine to act as an A2A peer.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

Read-only MCP server that exposes the agentic-os governance, SDLC, and Quality Engineering methodology to any MCP host. It never writes to your repository and never executes code — it serves the methodology, plans an install, and verifies it, handing any commands back to the host to run.

Enables a Claude Code agent to fetch remaining 5-hour and weekly subscription usage limits, reset times, and per-window breakdowns as JSON. It provides the same figures as /usage through a local, read-only tool.

Enables a production-grade MCP-native router and multi-agent control plane, letting agents plan tasks, route tool calls to the right MCP servers, stream every step, and persist results in memory.

Enables a model to write short Python programs that call a wrapped MCP server's tools as async functions, rather than invoking them one at a time. The program runs in a locked-down Docker sandbox, and every tool call passes through a host-side bridge that enforces an allowlist, schema-validated arguments, call budgets, timeouts and output caps.