"MobX-State-Tree" matching MCP servers:

Enables AI agents to persist and restore checkpoint state, supporting crash recovery and replay for LangGraph-based workflows.

CLI + SDK + MCP server for ZSpace (极空间) NAS — zero-config file management from the terminal or AI agents. No password, no SSH: reads the desktop client's login state. 12 MCP tools covering ls / find / tree / upload / download / rename / move / copy / remove.

A runtime-free MCP server that converts source code into AST🌲, regardless of language.

Enables AI agents to commit stateful workflow checkpoints by calculating state hashes and rollback points through the Model Context Protocol. It provides deterministic, dependency-free checkpoint management for autonomous agent execution.

MCP server for AI-assisted development on the Lampa open-source TV app, providing read-only access to the source tree with 41 tools and 5 resources for structured analysis, planning, editing, and validation.

Ephemeral MicroVM-isolated code execution for AI agents. Run Python, Node, or bash — fresh hardware-isolated VM per call, hard-purged after. No state persists between calls.

Mneme exposes a governed Decision Index so MCP clients can propose candidate architectural decisions and query decision state, applicability, and traceability. Proposals remain non-authoritative: accepting or activating protections stays under explicit human control.

Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.

Generates a daily standup note from GitLab merge request or GitHub pull request state: what is ready to merge, what is blocked, what is stale, and what is waiting on your review. When CI is red it opens the failed job's log and reports the error lines, so the note says why the pipeline failed rather than just that it did.

Domain availability + registrar price comparison across 52 TLDs — see not just if a domain is free, but where it's cheapest (7 registrars, renewal traps exposed). Honest: shows an Unverified state instead of guessing. Free, no API key. For Claude, ChatGPT, Cursor & any MCP client.

13 AI-powered UML diagram tools for coding agents. Generates class, sequence, state, ER, threat model, deployment and architecture diagrams in Mermaid syntax. Works in Claude Code, Cursor and Windsurf.

Enables multi-level reasoning with configurable depth levels, session-based state management, structured thought input, and real-time trace resources.

Provides MCP-compatible agents structured access to official government records, including short-term rental permits, healthcare exclusions, childcare licensing, and NYC film permits.

MCP server for tidying a large Outlook / Hotmail mailbox via Microsoft Graph. Bulk moves, folder-tree surgery, inbox rules — no send tool, no permanent delete.

Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)

Enables git-versioned project state for AI sessions, capturing decisions, constraints, and rejected paths with confidence and provenance. It provides a deterministic resume context so new sessions continue without losing direction or re-proposing rejected work.

Provides MCP tools to create, run commands in, checkpoint, and delete durable cloud environments, giving coding agents persistent state between calls.

High-performance local MCP server and CLI written in Rust that scrubs 90%+ framework noise from AI debug logs with Tree-sitter AST validation and test rollback.

Enables browsing the Ptitchef recipe category tree and reading its recipes without an API key or account.

Offers a control surface for AI agent security with four independent checks: source-code scanning, tenant isolation, LLM content verification, and deploy gating. Currently in pre-release, with no functional scanning engines yet.