"KLM" matching MCP servers:

An MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) when you need deeper analysis on complex problems.

Provides a universal bridge to interact with any OpenAI-compatible LLM API (local or cloud), enabling model testing, benchmarking, quality evaluation, and chat operations with performance metrics.

Share code context with LLMs via MCP or clipboard

An MCP server that provides LLMs access to other LLMs

MCP server that lets Claude analyze huge files (logs, dumps, etc.) via a sandboxed Python REPL and recursive language models, keeping content out of the prompt. Zero-setup with Claude Code login, Docker sandbox by default, and tools for loading, searching, chunking, and querying large contexts.

Provides symbolic reasoning capabilities by converting natural language logical problems into Answer Set Programming (ASP) format and solving them using the Clingo solver. Enables users to perform formal logical reasoning, verify logical arguments, and get step-by-step explanations for complex logical problems.

An implementation of the Recursive Language Models architecture that enables AI agents to process massive documents by programmatically decomposing them into sub-queries. It allows for cost-effective and accurate reasoning across millions of tokens by treating long-form data as an external environment for root and worker models.

MCP server that enables verified code execution with LLM reasoning using Recursive Language Models (RLM). It supports tasks like code generation, data analysis, and complex task decomposition.

Enables the analysis of massive datasets by storing data in external variables via a sandboxed Python REPL instead of the model's context window. This allows users to process files larger than 100MB without polluting the context or hitting token limits.

A server that enables browser-based local LLM inference using Playwright to automate interactions with @mlc-ai/web-llm, supporting text generation, chat sessions, model switching, and status monitoring.

Provides AI coding assistants with a persistent Macaulay2 1.26 session, letting them run computations such as Groebner bases, free resolutions, Betti tables, primary decompositions, and Hilbert polynomials while preserving state across calls.

An MCP server that provides a persistent sandbox for AI coding agents to explore codebases server-side, returning only compact summaries to reduce context consumption.

Provides WebAssembly-based, sandboxed tools for JavaScript execution, binary disassembly, file recovery, steganography, image optimization, data processing, PDF redaction, secret scanning, and semantic search.

Enables integration of local LLM capabilities with MCP-compatible clients like Claude Desktop, Continue.dev, and Cline. Provides tools for processing text prompts through local language models using a customizable inference function.

Enables zero-install Macaulay2 computations from JupyterLab in a browser, including Groebner bases, resolutions, Betti tables, and package loading via the Model Context Protocol.

Enables multiple AI agents to share and read each other's responses to the same prompt, allowing them to reflect on what other LLMs said to the same question.

Enables LLMs to execute Python code in isolated sandboxes with file operations and MCP integration, supporting multi-round execution and plot capture.

Enables interaction with self-hosted LLM models via Ollama and Supabase database operations. Supports text generation, SQL queries, and data storage/retrieval through natural language commands.

A serverless-accelerated hybrid development platform that minimizes dependencies in the local development environment and organically combines a virtual operating system kernel inside a web browser with the local host resources.