An event-driven MCP server that enables agents to share context streams, publish and subscribe to events, manage tasks, and follow protocols, keeping a fleet of agents mutually context-aware in real time.
A server built with mcp-framework that allows users to extend Claude's capabilities by adding custom tools that can be used through the Claude Desktop client.
A unified API server that enables interaction with multiple AI model providers like Anthropic and OpenAI through a consistent interface, supporting chat completions, tool calling, and context handling.
Provides a standardized protocol for tool invocation, enabling an AI system to search the web, retrieve information, and provide relevant answers through integration with LangChain, RAG, and Ollama.
AIFeed Open Standard. AIFeed Protocol to the building tools section. AIFeed enables web publishers to provide verified, token-efficient content feeds for AI agents.
Universal coordination hub for AI agents. Find collaborators, negotiate terms, form contracts, and build reputation through an MCP interface. Supports natural language search across agent networks.
A Python implementation of the MCP server that enables AI models to connect with external tools and data sources through a standardized protocol, supporting tool invocation and resource access via JSON-RPC.
An MCP server that seats multiple LLMs as a council, letting your assistant query them in parallel or in sequence, relay answers for cross-critique, and merge conclusions within one conversation.
Local-first shared memory and coordination layer for AI coding agents, with repository evidence, reservations, handoffs, code graph context, and dashboard review backed by PostgreSQL/pgvector.
MCP server that pings 130+ free coding LLM models across 17 providers in real-time, ranks them by latency, and helps AI agents pick the fastest available model.
Enables AI coding agents to offload large file reads and boilerplate code generation to cheaper or local worker models through MCP, reducing token consumption and keeping context clean.
Enables users to scan Hugging Face for Apple-MLX models, estimate memory fit and decode speed for their Mac, and get ranked recommendations for a use case, with all agent work running locally.
Security-enforcing MCP proxy that sits between an AI agent and any number of downstream MCP servers, intercepting every tool call through a capability-token policy gateway that can allow, deny, or escalate to human approval before the call reaches any real tool. It also exposes built-in operator tools for approval workflows, audit trail queries, token management, voice/HUD output, and hierarchical
Enables a Codex orchestrator to obtain a deterministic, local recommendation for a model and reasoning effort for a delegated coding task, without inference calls or API keys.
Enables selecting the best AI model and reasoning effort for any task by analyzing task requirements and live pricing, balancing intelligence, speed, and cost. Provides model recommendations, comparisons, and routing status through MCP tools.
Cost-aware multi-LLM routing MCP server that automatically routes tasks to free models first with fallback to paid, using task difficulty classification.
An MCP server that enforces explicit task ownership acceptance and requires a provenance tag (observed, reviewed, or reported) on every completion claim, preventing silent inheritance and unverified assertions in multi-agent systems.
Enables durable agent session transfer between machines by serializing state, provisioning sandboxes, and metering costs via MCP tools over a Postgres-backed state machine.
Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.
Enables Codex to submit, poll, and retrieve bounded text handoffs for durable image-generation and image-inspection jobs while keeping provider-returned media bytes outside the MCP boundary.
Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.
A proxy server that bridges AI agents and external APIs by dynamically translating OpenAPI specifications into standardized MCP tools, enabling seamless interaction without custom integration code.
Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.
Enables local-first management of OpenCode model routing, letting users discover, enable, and assign orchestrator/specialist roles to models while safely connecting the chosen policy to OpenCode via a local MCP bridge.
Routes subagent tasks across Claude and OpenAI lanes by task kind and quota state, deciding whether to spawn a single model, run a duel of both vendors, or run both and ship the merge. It records duels with attested proof-of-run session ids, grades sides blind with one judge per vendor, and tracks per-kind standings and lane pacing.
One MCP server that routes to 12+ AI providers for text, image, and video generation, with smart task delegation, web search, and model comparison—all from the terminal.
MCP server providing witness, recovery, and continuity primitives for AI agents, enabling them to articulate failure, preserve state across sessions, and coordinate via MCP, A2A, or REST.
Enables Codex to run image generation and inspection as durable, restart-reconcilable local jobs that keep provider-returned media behind the tool boundary and hand back only bounded text, hashes, relative references, and Job IDs. It also supports idempotent submission, job history, and an offline deterministic mock provider for validating transport and persistence behavior without spending API credits.
An MCP server that keeps raw tool output out of the context window by sandboxing and compressing results (about 98% reduction), persisting file edits, git operations, tasks and decisions in SQLite with BM25 retrieval so the agent resumes after compaction, and enforcing routing across 17 platforms via MCP and hooks. It also encourages the model to write scripts that compute answers and log only results instead of reading large data into context.
Routes questions to a council of AI models (local and cloud) and synthesizes their answers in five configurable modes: individual, categorized, deconflicted, pooled, and dialectic.
MCP server providing lossless file reads with deduplication, per-repo token metering, and HMAC-signed context receipts. Enables auditable, vendor-neutral measurement of what an AI agent saw.
Provides a single MCP gateway that discovers, plans, lazy-loads, calls, and unloads tools from downstream MCP servers on demand, reducing context usage while keeping all tools accessible through one connection.
Local MCP server that lets Claude Code delegate bounded, read-only tasks to external AI models (Codex, Grok, local OpenAI-compatible servers) via CLIProxyAPI.
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.
A local plugin for Codex and Claude Code that replaces earlier images with short placeholders. Its MCP tool retrieves the original image by ID when needed, even after context compaction.
An MCP server that exposes tools for sub-agent style reasoning across multiple LLM providers, enabling delegation of prompts to various models and running critique loops, debates, red-teaming, and answer ranking.
A reusable MCP server providing shared, versioned context across AI agents and devices via a private GitHub workspace, with tools to discover projects, bootstrap, query, and close out task state.
Aggregator MCP proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery, and compresses large tool outputs (HTML→Markdown, JSON summarization) with full-output retrieval via read_more and a per-session token-savings report.
Proxy for OpenAI-compatible backends that compacts conversation history before the context window fills, with read-only MCP tools to search and read back the archived originals.
Provides persistent memory, identity, and context for Claude sessions through a memory graph, enabling recall, storage, and relationship management of entities and decisions.
Enables multiple AI coding agents and humans to coordinate through a Git-native Markdown blackboard (.context/ + AGENTS.md), where they can inspect workspace overviews, claim and toggle ready tasks, record architecture decisions, synthesize shared prompts, and hand off work via atomic, lock-protected writes that prevent lost updates and formatting drift. It also serves a fully offline local web dashboard that live-syncs any blackboard change over WebSocket.
Enables coding agents to run budgeted tests and checks under a countdown with a stop rule, shape long logs into concise failure summaries, and guard pre-existing test files against silent assertion rewrites. It also delivers relevance-filtered project memory and renders a token-and-time roadmap of the orchestrator and every subagent spawned for a task.
Universal agent registry, discovery, and cross-protocol messaging for any MCP-compatible AI agent, enabling registration, discovery, and message translation across six protocols.
Exposes runtime-local capabilities from browsers, apps, devices, and local processes to AI agents through a unified MCP bridge, enabling path-based discovery and invocation of live context.
Connects Codex to local and cloud language models from MoE4All, GLM, DeepSeek, and OpenAI-compatible endpoints through a controlled MCP worker boundary, enabling read-only worker analysis, provider configuration, and VS Code model setup while keeping write authority with Codex.
Exposes a context_folding MCP tool that lets an agent mark conversation history entries (user messages, model replies, tool results) as foldable, keep, or unmarked and replace marked content in outgoing model requests with a head, a concise summary, and an original-entry ID, without altering the client's own full history. Enables listing, paginated reading of originals, layered expansion via previous IDs down to the original, status inspection, and cleanup, with folding applied only when token thresholds and trusted cost-accounting gates are satisfied.
Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.
Enables developers to expose custom tools, prompts, and resources to MCP clients from a stateless App Router route handler. Serves the current 2026-07-28 protocol natively while a compatibility layer supports 2025-era Streamable HTTP clients.