"JSON Web Tokens" matching MCP servers:

Enables AI-powered instant code merging at 10,000+ tokens/sec and agentic codebase search with natural language queries through the Relace API.

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.

A FastMCP server that turns JSON data into Plotly figures, deployable as an isolated service on Modal. Data goes in as JSON; a validated Plotly figure (JSON) or a rendered PNG comes back over the Model Context Protocol.

Wraps MiniMax AI as an autonomous code executor for Claude Code, offloading coding tasks to save Claude subscription tokens.

Enables AI assistants to run, list, and analyze Lupa test suites, returning structured JSON results for debugging.

Provides sandboxed code execution and data processing for CSVs and logs to achieve over 95% token savings. It enables secure multi-language execution and progressive tool disclosure to optimize LLM context usage.

Enables AI assistants to solve linear, integer, mixed-integer, and knapsack optimization problems using Google OR-Tools via a simple JSON interface.

A tool that allows Claude Code to use Gemini AI as an MCP server, leveraging Gemini's large context window for analyzing large files while saving Claude Code tokens.

Implements Solana blockchain functionality for the LetsBonk launchpad, enabling users to launch and trade tokens on letsbonk.fun.

A backend service for executing transactions on Binance Smart Chain, enabling secure transfers of BNB and BEP-20 tokens, smart contract interactions, and token creation through structured MCP integration.

Enables an assistant to edit .asc schematics, run the simulator, and read logs and waveforms through stable JSON tools.

An MCP server that uses Groq's API to expose raw chain-of-thought tokens from Qwen's qwq model, enabling LLMs to think step-by-step before responding.

Connects to SolidWorks 2022 over COM to run, test, and auto-fix VBA macros, returning structured diagnostics for iterative correction by Claude.

AI-powered command execution and tool plugin framework with secure Python evaluation, knowledge management, and web dashboards.

Turns a logged-in ChatGPT Web conversation into an OpenAI-compatible HTTP endpoint, letting any compatible client send chat completions and responses without an API key. Native tool calls tunnel back to the local MCP server and execute under bubblewrap sandboxing with capability-bound session tokens, idempotent turns, and DOM-captured answers.

A self-hosted OAuth MCP server that connects ChatGPT developer mode to an isolated coding workspace for listing and opening projects, reading and editing files, running shell commands, and observing or acting on terminal sessions.

Enables AI agents to perform safe sandboxed expression evaluation, symbolic calculus such as derivatives, simplification, equation solving and integration, statistical analysis, and JSON-native matrix operations. Everything is computed statelessly through the Model Context Protocol over stdio, HTTP, or SSE.

Enables AI assistants to securely inspect, search, edit, build, and test explicitly authorized local development projects over MCP, with sandboxed filesystem access and sensitive-file protection.

Provides access to OpenAI's advanced models (including o3) with integrated web search, Python code interpreter, and combined analysis capabilities. Enables users to perform web searches, execute code in sandboxed environments, and combine search with analysis through natural language.

Enables AI clients such as Claude Desktop, Cursor, and VS Code to connect via SSE and JSON-RPC, discover C# methods as MCP tools, and execute them with generated schemas. It also provides a Blazor WebAssembly inspector for monitoring and testing tool calls.