"Understanding File Reading in Programming" matching MCP servers:

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 local opencode agents to control a live Chrome browser via MCP tools, including tab management, JavaScript execution, clicking, form filling, page reading, screenshots, and console log retrieval.

Enables Claude Code, Codex, Devin, or any MCP client to control Chrome/Edge through the repository's browser extensions, with Claude-style visual tools or Codex-style text-first tools.

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

MCP server that lets Claude control multiple persistent browser tabs inside VS Code, with tools for navigation, clicking, typing, snapshotting pages, and reading console output.

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

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.

tooltrim reduces the tokens agents spend re-reading bloated tool results. Run it as an MCP server exposing compress and expand_tool_output, or as a gateway in front of any upstream MCP server: it re-exposes the upstream tools unchanged and shrinks each result (HTML/JSON/logs/tables) before it reaches the model, keeping the relevant content only.

A hardened, self-hosted MCP server that lets AI agents query and govern an Infraveil control plane in-loop, reading state and filing deploy/remediation requests that require human approval.

An MCP server that enables a supervising OpenAI Codex agent to delegate bounded implementation tasks to isolated worker threads with enforced file scopes and verification, optionally running in parallel git worktrees.

Drive the real, logged-in Chrome you already have open — cross-platform, token-budgeted reading (90%+ savings), and 24/7 headless Ubuntu support.

MCP server for inter-agent mailbox communication using file-based mailboxes in .claude directories.

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

Enables Claude to delegate web search, page reading, text drafting, and parallel multi-model image generation to cheaper helper models on any OpenAI-compatible backend. Claude stays in charge of planning and final decisions while consuming fewer of its own tokens.

It gives AI agents a ranked, token-budgeted digest of what changed since their last cursor, with drill-down handles and cursor acknowledgement, read from a local database of file and SQL source changes. It enables agents to act on current business state without re-reading and diffing everything themselves.

Enables two-model orchestration where Gemini in Google Antigravity delegates coding tasks to Qwen 3.8 Max in Qwen Studio Desktop via CDP, managing prompt delivery, file generation, continuation, and verification.

A dedicated server that wraps Google's Gemini AI models in a Model Context Protocol (MCP) interface, allowing other LLMs and MCP-compatible systems to access Gemini's capabilities like content generation, function calling, chat, and file handling through standardized tools.

Enables AI agents to drive a logged-in ChatGPT web session over CDP, including managing projects and chats, sending messages with file attachments, and retrieving long Pro replies.