"Apache Cassandra" matching MCP servers:

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.

Local-first MCP server providing semantic search over library docs, fully offline. Single Go binary speaks MCP over stdio against a vector index pinned to the binary version. Like Context7 with the internet turned off. Apache 2.0. Linux + macOS, also available as a container image.

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.

MCP server for PostgreSQL with typed tools (list, describe, read, aggregate, insert, update, delete), catalog SQL served as named tools, and free SQL that runs under the grants of each login. Each caller is limited to its own tools, databases and tables, and start checks refuse unsafe setups, such as a superuser login with free SQL on. Serves stdio and Streamable HTTP. Written in Go, Apache-2.0

MCP server for Evolveum midPoint identity governance. Tools for users, roles, access requests, approvals, tasks, resources and audit search, plus interactive MCP Apps views. Writes are off by default and return dry-run previews until you turn them on. Written in Go, Apache-2.0.

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.)

ToolMesh is an Apache-2.0, self-hosted MCP gateway written in Go that sits between AI agents and backend systems. It enforces a fail-closed pipeline on every tool call, including per-tool and per-user authorization, server-side credential injection, structured audit logging, and output policies. APIs are declared in YAML with DADL, turning REST endpoints into MCP tools without writing a custom MCP