"An MCP that connects to local software" matching MCP servers:

Local-first Microsoft Outlook MCP server: a single Go binary that manages calendar events and mail through the Microsoft Graph API over stdio, with tokens stored in the OS keychain and no Entra ID app registration required. Exposes four aggregate tools (calendar, mail, account, system) dispatched by an operation verb, with multi-account support and read-only and mail-gating modes.

Connects AI tools to GitHub and local git repositories, enabling natural language management of issues, PRs, code analysis, and workflows.

Enables AI assistants to read, search, organize, and draft email, manage calendar items, and look up contacts through the user's already signed-in classic Outlook desktop app on Windows, with outgoing actions defaulting to drafts for review.

Baryon connects MCP-compatible AI assistants to Proton Mail through a local bridge, enabling email search, reading, attachment handling, and draft creation while enforcing deliberate permission limits. It runs locally and cannot send, delete, or modify mail.

A self-hosted WhatsApp gateway that connects a personal WhatsApp account to AI agents and applications over REST and MCP. It maintains a local message archive and enforces per-client, per-chat permissions for reading and sending messages.

Connects coding agents to local development services managed by Kranz. Agents can inspect service health, ports, logs, and run history, and perform lifecycle actions through the same live runtime as the TUI and CLI.

An MCP server that provides Claude Code with 99 methodology skills, seed patterns, decision logging, and memory tools to improve software development decisions. It acts as a cognitive scaffold layer, enabling better working methods rather than just additional data.

An MCP server and Go library that connects AI assistants to DataHub metadata catalogs, enabling dataset search, schema exploration, lineage tracing, and glossary access.

A local MCP server that unifies email and calendar management across multiple providers, enabling AI agents to search, read, and write with explicit approval and local-first security.

Zero-dependency local proxy that wraps any MCP server to redact secrets, strip hidden-Unicode prompt injection, and block writes to protected paths like ~/.ssh and .env.

Enforces structured, evidence-guided software engineering tasks with cognitive actions (investigate, plan, verify, remember) and persistent state for LLM-based coding agents.

Gives AI coding agents persistent, structured memory of a software project across sessions — goals, architecture, tech stack, decisions, and progress — stored locally in an embedded SQLite vault. Agents recall and update that context automatically through MCP tools whenever they open the project.

Enables local macOS integration between Apple Reminders and Home Assistant via an MCP server, using EventKit to read and write allowlisted data.

Provides a single local MCP endpoint that connects Gmail, GitHub, Slack, Notion, and Linear once, with multiple accounts per service, so any AI agent can use per-agent tokens, policies, and optional result filtering without re-authenticating.

Enables governed multi-agent software factory operations through eight typed, audited tools for Sprint planning, submission, decisions, inspection, cancellation, and resumption.

An MCP server that enables controlled Xiaohongshu content publishing with an immutable review workflow, requiring explicit human confirmation before any release. It supports content generation, local editing, compliance recall, and one-time authorized posting, defaulting to generate-only mode.

MCP server that connects AI assistants to your real Telegram account via User API (MTProto). Features default-deny ACL with per-chat permissions, message search, file sending, forwarding, media downloads, and rate limiting.

A Code Indexing MCP Server that connects AI coding assistants to external codebases, providing accurate and up-to-date code snippets to reduce mistakes and hallucinations.

A Model Context Protocol server that connects AI coding agents to Gerrit code review, enabling change search, diff review, and comment publishing without leaving the session.

A local-first MCP server that indexes Markdown/Obsidian folders and lets AI clients retrieve cited local context through MCP.

An MCP server that enables AI applications to interact with DiceDB databases.

An MCP (Model Context Protocol) server that inspects your local development environment and reports missing dependencies, version mismatches, and misconfigured environment variables to any MCP-compatible AI assistant. Works with Claude Desktop, Cursor, Gemini CLI, and any other client that supports stdio-transport MCP servers.

Haft is an MCP server that enforces engineering discipline for AI-assisted software delivery, providing tools for problem framing, decision contracts, and commission-based execution harnesses.

An MCP server for querying Grafana Loki directly with a discovery-first workflow — labels, values, series, and LogQL queries without requiring Grafana.

ContextLattice is an HTTP-first, MCP-compatible memory/context/task orchestrator that persists writes and returns fused recall from specialized stores with local-first defaults. Primary URL: https://contextlattice.io/ Install: https://contextlattice.io/installation.html Troubleshooting: https://contextlattice.io/troubleshooting.html

An MCP server providing web search, image search, and page scraping tools to LLMs without requiring API keys.

Fetches documents by URL, DOI, ISBN, PMID or PMCID, and reports a block as a block, never as an empty success.

Records your terminal sessions per command (PTY + OSC 133) into local SQLite, so AI agents can search, retrieve, and diff what commands actually printed. Secret redaction is applied by default to everything served over MCP.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

Serves the review notes left at lines of a diff in seam, a terminal diff viewer, to an agent with the code around them. The agent answers each note, and the answer shows in seam at that line.