"A system for semantic search in code repositories" matching MCP servers:

A semantic router that enables discovery, management, and execution of tools across multiple MCP servers using natural language.

Enables AI agents to access and act on web, desktop, and mobile interfaces via semantic accessibility trees, using MCP tools for querying, navigating, and executing deterministic UI actions without relying on screenshots or pixel coordinates.

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Enables Claude Code to control Firefox through tools for tabs, navigation, clicks, typing, scrolling, screenshots, page reading, forms, JavaScript, and console/network logs.

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 AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

A server that enables document searching using Vertex AI with Gemini grounding, improving search results by grounding responses in private data stored in Vertex AI Datastore.

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 users to describe an LLM fine-tuning workload once and receive ranked, task-aware GPU recommendations across a dozen cloud providers based on required VRAM/FLOPs, cost, and runtime. It surfaces the cheapest, fastest, and balanced options through MCP so coding assistants can plan training hardware without manual price comparison.

Enables multi-agent council workflows for coding assistants, providing parallel independent reviews, plans, brainstorms, validation, and research with strict read-only boundaries.

Universal search engine for AI agents. Discover products, services, and businesses across every category. 10 MCP tools, zero LLM calls, millisecond responses.

Provides access to a library of 18 specialized skills, project templates, and prompt patterns for Claude Code. It enables automated workflows for feature development, security audits, and system maintenance through multi-agent collaboration.

Enables agentic workflows to execute allow-listed side effects with automatic reverse-order compensation on failure, durable SQLite journaling, and idempotent rollback via MCP tools.

Domain-Driven MCP server for ed-tech workflows, exposing validated MCP tools backed by LangGraph agents, Supabase document retrieval, web search, and YouTube video discovery.

Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains, values compliance, signed communication, policy engine, task coordination, cross-layer integration, and agentic commerce. 264 tests passing.

Enables self-hosted AI gateway and agent control plane with governed MCP tools, virtual-key budgets, caching, and audit, supporting OpenAI, Anthropic, Gemini, MCP, and A2A protocols. It provides deterministic prompt enhancement and governed execution with a zero-credential first run.

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 AI agents to perform web search, extraction, and research across multiple provider backends with persistent multi-key rotation and auditable routing. Supports MCP, CLI, and Agent Skill entry points.

Enables OpenAI-compatible clients to access external tools, APIs, repositories, and data sources through MCP with allowlisting, approval, and argument validation, deployable as a FastAPI service or Python library.

Enables a Claude Desktop or Claude Code session to start, drive, and supervise interactive Claude Code CLI worker runs, including sending prompts, reading terminal output, waiting for completion, stopping runs, and managing settings and permissions.

Enables parallel research across multiple cheap AI worker models, splitting a question into sub-questions and synthesizing one sourced answer with references.

Lets agents run a small JavaScript program in a sandboxed worker that composes typed Jev judgments — claim checking, text screening, best-item picking, label classification, passage comparison, and yes/no questions — in a single call, returning only schema-validated results. A companion search tool exposes each judgment's JSON input and output schemas.

Enables MCP clients that lack built-in search — such as Claude Code through Bedrock or local LLM clients — to run web queries against Amazon's operated search index via a Gateway deployed in your own AWS account, with queries never leaving AWS and citation URLs preserved. Supports IAM/SigV4, Cognito, and API key authentication, per-gateway rate limits, IP and domain restrictions, and result filtering by domain and publication date.

Connects Windows-based Codex to the Cursor Agent CLI in WSL, providing a run_cursor tool to execute tasks in specified working directories and resume sessions per directory.

Composes arbitrary MCP tools using JavaScript, enabling discovery, composition, and execution of other MCP servers through a single 'exec' tool.

Enables Codex to delegate long-running work to Claude Code via blocking MCP calls, with tools for model discovery, run, and resume without polling.

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.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.