Cross-platform native service manager (systemd, launchd, Windows services) with a built-in stdio MCP server, so coding agents can start, inspect, read logs of, and schedule long-running processes as persistent services instead of backgrounding them with & or nohup.
MCP server for a self-hostable personal planner — exposes memo, todo, calendar event, and cross-resource full-text search tools so Claude, Cursor, or any MCP client can manage your schedule and notes in natural language.
alalanet-agent is the open local client of alalanet.com, the free service an AI agent asks before it installs, connects or pays. A stdio MCP server whose key stays on your machine: it signs agent passports, receipts, skill and package releases, mail and memory locally (16 tools) and checks files and agents against alalanet's public transparency log. Hosted checks: https://alalanet.com/mcp.
Read-only MCP server for Huawei GaussDB (centralized & distributed), built for coding agents. Three-layer write protection, multi-instance config, schema exploration and single-SELECT execution.
Enables AI assistants and local LLMs to interact with BirdNET-Go bioacoustic observatories, providing tools to query recent and historical bird detections, monitor station health, and retrieve audio clips.
Manage SockDock rules from an MCP client: Slack posts that run Claude Code, Codex or a program on your Mac, through one Socket Mode app. Needs SockDock running.
Zabbix MCP server and CLI in one Go binary. 15 task-shaped tools: current problems, host investigation, why an alert did or did not arrive, metrics, maintenance. Zabbix 6.4+.
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.
Self-hosted Go MCP server that crawls documentation sites into local Markdown/JSONL corpora and lets agents read pages, run crawls, check freshness, and diff changes with zero network access at read time. Single static binary, no CGO, Apache-2.0.
Enables a coding agent to get short, token-efficient answers about a project through grouped searches, focused symbol or section reads, and bounded read-only script output, with safety limits on paths, secrets, commands, and response size.
A wallet for AI agents: test funds, payments, paid APIs and escrow on Aether.
Give an AI agent its own wallet on Aether, a proof-of-work chain with post-quantum (ML-DSA-44) signatures. The agent gets an address and testnet funds in one step, then sends and receives AETH or USDC under per-payment and daily limits you set. It can pay for APIs that answer HTTP 402, sell its own, rate the services it
Lets a model use hundreds or thousands of MCP tools without loading them: it puts five tools in front of a large MCP server or gateway, so the model searches for the tool it needs and calls it. Search combines BM25 with a multilingual embedding model that runs inside the proxy.
Agent memory for facts that change. When a user corrects something, Recall replaces the old fact, tells the agent what it replaced, and keeps the old value in a history. Ask what was believed on any date, see every change to a fact, or diff two dates. Runs locally on polign_db, Postgres with pgvector, MongoDB, or Qdrant. Apache 2.0.
Safe write access for AI agents. Stellar Jay is an append-only business fact store: every change is kept, attributed to the agent that made it, and can be undone. Agents record, correct and retract facts, read entities, and reverse a bad run with undo_changes. Self-host with stellarjay-mcp (Go, AGPL) or connect to the hosted AvianSuite server at https://mcp.aviansuite.com/mcp.
A deterministic symbol oracle over a locally built index of the repository: whether a symbol exists, what a file declares, and what changed structurally since the last snapshot. It also ships a PreToolUse guard that stops an Edit/Write referencing a function, constant or type the repo does not declare, before the write lands rather than after the build fails.
No LLM, no API keys, no network, no l
Enables AI agents to store and retrieve self-hosted memories over MCP (stdio or Streamable HTTP) using local embeddings that work fully offline. Writes are redacted before they hit storage and every read is recorded in an exportable, append-only audit log.
Review a coding agent's work decision by decision: the agent records each decision and runs before/after examples on the old and new code; reviewers approve or reject, and rejections go back to the agent.
Self-hosted webhook relay and tunnel with Noise NK encryption. Inspect requests, replay webhooks, trace AI pipelines, connect/disconnect tunnels — 13 MCP tools. No tokens or passwords needed.
Lets AI agents read what Kubernetes containers were doing right before they were OOMKilled or crashed: Java heap histograms and Go heap profiles taken before the kill, logs of the dead instance, and core dumps matched to the pod. Read-only tools to list captures, read summaries and raw evidence, and see which containers are near their memory limit now.
Unofficial MCP server for Octopus Energy customers in the UK. Lets Claude and other AI assistants read your smart meter usage, costs, tariffs and bills, find the cheapest Agile half-hours and, if you allow it, manage Intelligent Octopus EV charging and join Saving Sessions. Read-only by default, with an optional audit log. Runs in Docker or as a one-click Claude Desktop bundle.
Official MCP server for Skycloak (managed Keycloak) that enables managing clusters, realms, applications, identity providers, users, themes, exports, SIEM destinations, and webhooks through natural language, with OAuth or API key authentication.
Manage your entire notification infrastructure using natural language. Trigger workflows, create users, manage preferences, update tenant branding, and access docs — all from Cursor, Claude Desktop, or Windsurf. 24 tools covering email, SMS, push, WhatsApp, Slack, MS Teams, and in-app notifications.
API client for coding agents. Sends saved HTTP, GraphQL and gRPC requests, runs collections with their checks, and creates or edits requests over stdio or loopback HTTP, with secret values redacted and calls limited to an allowlist of hosts.
Universal session & handoff layer for AI coding agents: shared task, decision, blocker and test state, checkpoints, and deterministic handoff between Claude Code, Codex, OpenCode, Cursor, Cline, pi and omp. Local SQLite, git-aware, 25 tools + 7 resources over stdio or streamable-http.
Drives an Android emulator or a physical device over adb. The agent screenshots, reads the UI hierarchy with true device-pixel coordinates, taps and types, manages app lifecycle, reads logcat, and runs Gradle builds and tests.
Argon gives AI agents isolated MongoDB sandboxes where they can work on a copy of existing data. Users can review what changed and choose whether to merge or discard it.
Unofficial MCP server for Hive (British Gas) smart heating. Lets Claude and other AI assistants check your thermostats, radiator valves, hot water, plugs and lights and, if you allow it, boost the heating, set temperatures, switch on the hot water and set holiday mode. Read-only by default, with an optional audit log of every change. Runs in Docker or as a one-click Claude Desktop bundle.
Transparent Go proxy that intercepts, signs, rate-limits, redacts, and audits all MCP JSON-RPC tool calls without modifying client or server. Stores to JSONL or SQLite with HMAC-SHA256 signatures.
Where AI agents meet, work, and keep their word: public rooms, private messages, paid tasks and memory, with a Bitcoin-anchored record. Free over MCP (https://swarmmemo.com/mcp/core) or HTTP; Python, JS, LangChain and CrewAI packages.
Gives AI assistants real-time access to web data with the ability to scrape any website, bypass anti-bot systems, extract structured data, and capture screenshots through enterprise-grade infrastructure.
Enables AI assistants to explore a PostgreSQL database, run bounded read-only SQL, inspect query plans, test hypothetical indexes, find slow queries, and check database health with compact CSV output.
HTTP(S) and WebSocket debugging proxy, like Proxyman or Charles, that AI agents drive over MCP: summarize captured traffic, read requests with secrets masked, diff a working request against a failing one, mock responses, set breakpoints and throttle the network.
MCP server built into Karakoram, an Apache-2.0 self-hosted control plane for PostgreSQL, MySQL, MongoDB and other databases on Zerops, Dokploy or Nomad. Read-only by default: list and inspect clusters, backups, operations, events and metrics, plus cluster_diagnose and wait. (The maintainer, Samyazz, works at Zerops.)
Pit Officer sits between your AI agent and your broker or exchange account and checks every order before it is sent. Limits an AI agent cannot change: order size, order rate and a profit-and-loss stop. Block the account to stop new orders. The agent connects over MCP; read-only tools are on by default, and you choose which order tools it may call. Open source, Apache 2.0.
Enables read-only search and retrieval of your email across multiple IMAP accounts through a local notmuch index, served over authenticated HTTP for MCP clients like Claude or Codex.
Nido is a local QEMU VM manager. Install it on your computer from https://github.com/Josepavese/nido and run nido mcp via stdio, or use npx -y nido-mcp@latest mcp with QEMU installed locally. It manages VMs on that same computer; a server hosted by Glama cannot access your local VM inventory.
rhizome-mcp is a local-first MCP server for task tracking and coordination of autonomous AI coding agents, providing crash-safe issue claiming, durable project memory, and dependency graphs using SQLite. It enables agents from different MCP-compatible clients to share a consistent view of project work with no accounts, Docker, or network dependency.
Enables AI agents to manage App Store Connect releases—versions, builds, TestFlight groups, metadata, pricing, reviews, and submission—while staying read-only by default and requiring human approval before any public or destructive action.
Enables AI agents to list, describe, and invoke scoped capabilities so they can perform brokered HTTP or SSH operations without ever receiving the underlying credential. All uses are deny-by-default, revocable, expiring, and recorded in a hash-chained audit log.
Local harness for Codex, Claude Code, opencode and other coding agents: agents record pitfalls and design decisions as Markdown files reviewed in the same PR as the code, and route only task-related records to the next agent.
A TypeScript server implementing the Model Context Protocol that provides secure code execution in isolated Docker containers, allowing LLM applications to safely run Python, Go, or JavaScript code snippets.
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.
The most powerful MCP server for Slack Workspaces. This integration supports both Stdio and SSE transports, proxy settings and does not require any permissions or bots being created or approved by Workspace admins 😏.
Zero trust gateway for MCP servers. Aggregate, filter, and securely access MCP tools from anywhere without VPNs, open ports, or exposed endpoints. Built on OpenZiti, zrok, and Agora with cryptographic identity, mTLS, per-client isolation, and tool-level permission control.
Manage a fleet of OPNsense firewalls from an AI agent, inside guardrails it can't drive around.
MCP server for central management of OPNsense firewall fleets. 129 tools across devices, config sync, tasks, schedules, templates, backups and remote consoles - destructive actions confirmation-gated, MCP-issued tokens lifetime-bounded, backup and storage secrets excluded from the toolset entirely.
Enables AI agents to query cluster-wide network traffic, investigate API calls, and perform root cause analysis using natural language, with access to decrypted TLS traffic and Kubernetes context.
Written in Go, MOB³ features its own HTML rendering engine with JavaScript support, an ANSI renderer, and inline image support. No GUI toolkit or persistent browser profile required. Built as a true terminal web browser for humans and AI agents.
Supercharge your apps with release monitoring, observability, and secret management. Deploy to your own infrastructure, or host on ours. From K8s to VM's to static sites.
Forge provides continuous profiling, tracing, metrics, dashboards, and can correlate with your recent releases. It is the most powerful way to empower your LLM.
Enables AI assistants to manage and query Tiger Cloud database services, including service lifecycle operations, database connections, and SQL execution.
A Model Context Protocol server for Massdriver that enables AI assistants to manage infrastructure platform resources like projects, environments, deployments, policies, and more. It provides 106 tools and supports stdio or HTTP transports.
Enables AI agents to look up real-time US and Canadian sales and use tax rates by street address, latitude/longitude, or postal code, retrieve jurisdiction-level breakdowns, and check account usage and quota. Connects over stateless Streamable HTTP with API-key authentication.