"Using llama.cpp and Searxng with local models" matching MCP servers:

A TypeScript-based MCP server for SearXNG that allows users to create and summarize text notes using simple URIs and metadata, facilitating natural language interaction with stored content.

Local-only MCP server for saving and restoring conversation context across AI agent sessions using JSON files on disk.

Enables ChatGPT web to read local files, search code, run shell commands, and drive a local Codex CLI via an official MCP connector, with human approval for risky commands and full audit logging.

Enables ChatGPT to read and edit local text files, apply precise string replacements, and run Bash commands on a user's own macOS or Linux machine through a secure local tunnel without exposing public ports.

MCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.

MCP server providing WP-CLI, MySQL, and filesystem access for Local by Flywheel WordPress sites, enabling direct management without HTTP endpoints.

Enables Claude to create, read, update, and search notes in a local Obsidian vault, with automatic YAML frontmatter and folder management.

Enables AI clients like ChatGPT or Codex to manage files and local Git repositories within an explicitly authorized workspace, with server-enforced path boundary checks and optional remote Git operations.

Enables MCP-compatible AI clients to securely access explicitly authorized local project files and run approved development commands with bounded execution and audit logging.

Lets ChatGPT, Claude Desktop, Claude Code, and other MCP clients run an allowlisted set of local commands and read files from a chosen directory, so an assistant can analyse a codebase or trigger local generators (images, sprites, assets) without metered API tokens. The server is read-only and deny-by-default by default, with no shell, path containment, opt-in writes, and required auth when exposed over HTTP.

Exposes local file I/O, a restricted shell whitelist, and SQLite helpers for safe integration with AI clients like Cursor and Claude Desktop.

Transform any local file into AI-optimized markdown format for seamless integration with Claude Desktop, Claude Code, and other MCP clients.

For people who want their AI to run the build, read the error and check the dev server itself, instead of pasting output into chat. Works with Claude Desktop (one-click installer), Cursor, Claude Code and Cline. Runs locally over stdio or HTTP, no telemetry. A seatbelt for everyday mistakes, not a sandbox.

MCP server for privacy-gated local Apple data access including Mail, Messages, Notes, Calendar, Contacts, Photos, Reminders, Voice Memos, and iCloud Drive.

Delegates heavy, repetitive, and verifiable tasks like PDF extraction, code analysis, and log processing to a local LLM to reduce token consumption for frontier AI models, while keeping decision-making with the main AI.

Enables local file reading and writing for your project via Claude Desktop, with tools to read, write, and list files in a specified root path.

A local-first MCP server for PageIndex — the vectorless, reasoning-based RAG framework. It lets local AI agents index and query local PDF and Markdown documents through a self-hosted PageIndex installation, without requiring any PageIndex cloud API key.

Enables ChatGPT to work directly on local projects by reading files, editing code, running tests and commands, inspecting Git state, and managing durable workflows, with optional delegation to local Codex agents for complex tasks.

Secure agent coding runtime for local Git repos with policy enforcement, RBAC, sessions, approval workflow, and sandboxed writes, optionally connectable to ChatGPT via Secure MCP Tunnel.

Enables AI assistants to search, read, create, and modify Markdown notes in local Obsidian vaults directly through filesystem operations. Supports tag-based discovery and frontmatter parsing without requiring Obsidian to be open, facilitating integration with VS Code Copilot via stdio transport.

Enables AeyeStudio AI chat to securely access and control local PC resources such as files, Excel, clipboard, apps, and shell through a localhost MCP agent with user approval.

Enables any MCP client to delegate a scoped task to a local Ollama model that runs its own tool-calling loop for file operations and web search, with an allow-listed folder security model.

Enables ChatGPT in Chat mode to read and write local files, view the screen, and control the macOS desktop, with target locking and local permission controls.

A security-first, read-only MCP server that lets clients browse and read text, PDF, and XLSX files from an explicit allowlist of local folders, with strict path and secret protections.

Enables ChatGPT to inspect selected local projects, make edits, run commands/tests, and review diffs through an authenticated MCP endpoint backed by a containerized workspace.

A simple MCP server for local documentation with RAG capabilities, enabling AI assistants to access and search local documents.

Enables a remote Hermes agent to inspect allowed files and propose patch/check requests on a local Git workspace, while the local operator retains approval and applies changes from isolated snapshots.

Enables MCP-compatible AI assistants to list, inspect, read, search, and modify local files and directories within configured filesystem roots, with permission controls and optional read-only or deletion restrictions.

Safe local MCP server for Windows to list, read, search, patch, backup, and verify code files in allowed folders, with Git integration and dry-run diffs.

A deterministic, fail-closed MCP server that discovers approved local resources, plans bounded routes, and renders—but never executes—selected calls.