"PlayStation 2" matching MCP servers:

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

Read-only MCP server for CometBFT/Cosmos validator operators: checks signing liveness and downtime-jail risk, diagnoses chain halts (who isn't voting), and reports peer topology and upgrade readiness. Keyless and GET-only, with node IPs masked by default.

Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (42 meta-tools / 57 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.

Enables LLMs to interact with embedded devices by reading and writing Segger RTT data through a J-Link debugger.

Persistent, consensus-validated institutional memory for AI agents. Gives LLMs real memory that survives across sessions - validated through BFT consensus, not just dumped to a file.

Enables users to manage their Zaim household account data through OAuth 1.0a authentication. It provides 14 tools to retrieve, create, update, and delete financial records and master data like categories and accounts.

Adds security capabilities like port scanning, TLS inspection, DNS enumeration, process monitoring, secrets scanning, HTTP header auditing, and CVE checking to Claude Code and Cursor.

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.

Local-first knowledge operating system and deterministic issue-to-PR factory for AI coding agents. Features hybrid storage (SQLite+FTS5), 7-mode token-aware context compiler, LifeOS txonomy, and MCP stdio server.

MCP server for the Cloudflare API v4, written in Go. Exposes 28 read tools across zones, DNS, WAF/firewall, rate limits, HTTP request logs, Security Center, and threat intelligence.

An MCP server that lets AI agents (Claude Desktop, Claude Code, and other MCP clients) drive impersonate-proxy — switch TLS (JA3/JA4) and HTTP/2 fingerprints, User-Agent, spoofed client IP and upstream proxies, then verify what the server actually sees, all in one conversation.

Enables LLMs to read and search X posts, manage users and lists, upload media, and publish posts using the X API v2 with OAuth user context.

Enables reading and writing MS Excel files, including cell values, formulas, sheet creation, copying, formatting, and on Windows, live editing and screen captures.

A self-hosted MCP server that retrieves git-backed engineering experience records (issues, fixes) to inform LLM coding agents, preventing repeated mistakes with a relevance floor.

Create and save recipes in Paprika with natural language!

Enables AI assistants to create, validate, render, export, save, and incrementally edit D2 diagrams using complete source or the Oracle API, with bundled layouts, themes, and workspace-secured assets.

Enables AI agents to inspect database schemas and run single read-only statements across PostgreSQL, MySQL, MariaDB, SQLite and MongoDB connections, returning compact TSV results that keep token usage low. Both MCP tools work uniformly regardless of how many connections are configured, and connection names are exposed in the server instructions.

Deterministic, schema-driven Go Fiber project scaffolder with an embedded MCP server.

MCP server that lets AI agents drive the LuckyStar/LS_KTool Android memory-debugging stack, exposing tools for memory read/write, scanning, pointer operations, and device/process management via the Model Context Protocol.

lunar-mcp is a Go-based MCP server that provides 28+ tools for Chinese traditional calendar, fortune telling, and divination. It enables AI agents to integrate Chinese cultural computations into their workflows.

AI modifies a function but misses 5 callers that also need updating. crag fixes this — it builds precise call graphs via static analysis, so AI knows exactly what's affected before making changes.