"JSON Web Tokens" matching MCP servers:

Enables AI agents to delegate simple text subtasks such as summarising, translating, classifying, extracting, and reformatting to free web AIs through the user's own Edge/Chrome browser, returning only plain-text answers to save the main model's context and tokens.

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.

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.

An MCP server that gives AI agents fast access to verified EVM chain information, including RPC URLs, chain IDs, explorers, and native tokens.

Enables Codex to send text tasks to ChatGPT web, await responses, continue conversations, choose reasoning effort, and manage projects through MCP tools on macOS.

Structured web extraction for AI agents. Pass any URL and a prompt, get clean JSON data back. Native MCP server with 100 free requests/month.

Sub-15ms edge intelligence tools for Claude Desktop, Cursor, and LLM agent loops. Provides sub-millisecond LLM JSON repair, web-to-markdown token compression (cuts context tokens up to 90%), PII redaction, and RFC 5322 B2B email deliverability verification at zero marginal token cost.

Lets a frontier coding agent delegate research, cataloguing, and long-running computation to a local LLM with guarded filesystem, web, and Python execution tools, preserving the agent's context and tokens.

Enables Codex to use an authenticated ChatGPT Web session as a reasoning and coding backend through isolated browser sessions, without granting ChatGPT direct workspace access.

Enables Claude Code to browse and import conversations from a user's claude.ai account, making mobile chat history available in the editor. Includes tools to list, read, and save web conversations locally.

An MCP server that enables web search capabilities using OpenAI's o3 model, allowing AI assistants to perform text-based web searches and return AI-powered results.

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

An MCP server that provides AI agents with real-time access to curated Web3 jobs.

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 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.

Exposes two tools, fetch_page and extract_from_html, so agents can retrieve web pages as markdown or plain text without ever launching a separate install step. Fetching escalates cheapest-first (HTTP requests, identity switching, JSON-LD/JS-state/AMP/feed extraction, then optional headless browser) and always returns a machine-readable reason such as captcha, login wall, or paywall when a page cannot be read.

A Model Context Protocol server that enables Claude Desktop to browse the web, likely allowing the AI to access and interact with web content.

An MCP bridge that exposes DeepSeek Harness (DSH) web UI's cordis RPC API as stdio tools, enabling any MCP client to manage workspaces, create/resume sessions, send messages, and fetch session stats.

Enables MCP-capable agents to perform local web research under a declared plan with session budgets, user-approved limit extensions, and guardrails for safe searching, page fetching, content extraction, and audit logging.

Auto-discovers MCP servers for your project and tracks ROI per session. One install: npx -y @perceptdot/core. Your agent finds its own tools and reports tokens saved.