"Connecting Claude and Ollama" matching MCP servers:

Delegates tasks from an Anthropic-backed Claude Code session to Ollama-backed Claude Code sessions, allowing them to run side-by-side without sharing environment variables.

Enables Claude Code to search, browse, and read its own past conversation history across all projects using BM25 keyword search.

Searches your local Claude Code conversation history to recall and resume past solutions.

Review and rewrite LangChain, LlamaIndex, Ollama, and XRPL code against current APIs, plus runnable examples, import lookup, and XRPL tx skeletons that never submit. Live docs included. $0.001 USDC on Base or 1000 drops XRP.

Enables a Claude Code agent to fetch remaining 5-hour and weekly subscription usage limits, reset times, and per-window breakdowns as JSON. It provides the same figures as /usage through a local, read-only tool.

Enables retrieving real Claude subscription usage statistics, including the 5-hour session window, weekly limit, and per-model limits, from the same endpoint Claude Code uses.

Enables OpenAI Codex to consult Claude Code for co-analysis, adversarial second opinions, and read-only file review over the Model Context Protocol, with Claude remaining advisory and unable to modify files.

An MCP server for creating named checkpoints and snapshots of projects, with selective file restore, content diffs, and artifact preservation, enabling safe recovery from external file changes in Claude Code.

Checkpoints Claude Code session states locally to survive CLI crashes, token limits, and /clear resets without context rebuilds.

An MCP server that lets Claude read and write your Things 3 tasks on macOS via AppleScript.

Lets Claude Code delegate tasks to OpenRouter-backed Claude Code sessions in isolated child processes, keeping Anthropic and OpenRouter credentials separate. It adds a model catalog, per-job cost tracking, and API-key management for running tasks on 400+ OpenRouter models.

Enables AI agents to offload mechanical, high-token work to local Ollama models through MCP, with role-based model discovery, batch processing, and file-aware inputs.

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

Serves 484 Claude Code skills and 17 global rules as MCP tools, enabling skill and rule retrieval, keyword search, and project-level rule discovery for any Claude client.

Pull Deep Memory from across your Claude Code Sessions — when you need it.

Integrates Google's Gemini AI models into Claude Code and other MCP clients to provide second opinions, code comparisons, and token counting. It supports streaming responses and multi-turn conversations directly within your existing AI development workflow.

Lets Claude read email and read/write calendar events for personal Microsoft accounts (Hotmail/Outlook/Live) via Microsoft Graph API, filling the gap where the official connector only supports work/school accounts.

Wraps the Claude Agent SDK as MCP servers, letting you spawn multiple specialized Claude Code agents — each with its own model, tools, system prompt, and personality — from any MCP client.

Enables peer-to-peer asynchronous conversation between Claude.ai and Claude Code instances via a shared file-based notebook, allowing them to leave messages, start threads, and organize by project.

Enables users to strip statistical AI text watermarks by rewriting wording while preserving meaning, structure and formatting, running locally with the user's own OpenRouter key including free models. Works in Claude Desktop, Claude Code, Codex, Cursor and any other MCP client, returning the rewritten text with a novelty percentage.