RyeDB MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RyeDB MCP Serverwhat rules and known failures apply to this project?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RyeDB™ MCP server
The Model Context Protocol server for RyeDB™: persistent project memory and a durable agent-to-agent channel (RyeChannel) for coding agents.
Status: early. The server is part of RyeDB core, which is developed in a private repository and is not publicly available yet. This repository is the server's public interface: the tool contract, client setup, and conformance checks. Nothing here pretends otherwise: you cannot run the server from this repository alone.
Tools
Tool | What it does |
| The current project memory: rules, decisions, known failures and their fixes. |
| Search recorded failures by text, signature or file path. |
| Record the root cause and fix for a failure. Stored as an unconfirmed claim. |
| Propose a rule in plain language. Advisory, never blocks. |
| Propose a blocking rule as a deny pattern with must-fail and must-pass examples. RyeDB proves the pattern; a human verifies it before it can block. |
| Record a design decision and why it was made. |
| Set the current task. |
| Post a persistent message to another agent, or broadcast. Kinds include |
| Read RyeChannel, or fetch and acknowledge your unread messages. |
| Tell the sender a message arrived ( |
| Tasks addressed to you or to everyone; open by default. |
There is also an internal hook tool used by Codex mcp_tool hooks. It is not for agents.
What is deliberately not a tool: verifying, retiring or approving anything. Agents can propose; only a human or CI can verify, and only verified rules can block a tool call. The trust model is documented with core.
Related MCP server: Continuity
Contract
contracts/mcp-tools.json is the machine-readable contract: a JSON Schema (2020-12) document listing every tool with its description and input schema. It is generated from the server's own tool definitions by npm run contracts in RyeDB core, and is never edited here. contracts/SOURCE.md records which commit it came from. npm test here checks that the file is well formed and internally consistent.
Use it
With access to RyeDB core, build it, then in your project:
node /path/to/core/packages/cli/dist/cli.js init # Claude Code: hooks + .mcp.json
node /path/to/core/packages/cli/dist/cli.js init --codex # also Codex: .codex/hooks.json + MCP entryor add the server by hand. Claude Code, .mcp.json:
{ "mcpServers": { "ryedb": { "command": "node", "args": ["/path/to/core/packages/cli/dist/cli.js", "mcp"] } } }Codex, .codex/config.toml:
[mcp_servers.ryedb]
command = "node"
args = ["/path/to/core/packages/cli/dist/cli.js", "mcp"]The server speaks MCP over stdio and talks to a per-project daemon over a local socket; it starts the daemon on demand. Details: docs/clients.md.
Tested with
Claude Code 2.1.307 and 2.1.308, and Codex CLI 0.163.0, both against the real binaries. Other MCP clients should work, since the server uses only initialize, tools/list and tools/call over newline-delimited JSON-RPC, but they have not been tested.
Development
npm test # validates contracts/mcp-tools.jsonRequires Node 22.18 or newer. Copyright (c) 2026 RyeDB. Licensed under Apache-2.0 (NOTICE).
RyeDB™ is a trademark of RyeDB. The Apache-2.0 licence covers the code; it does not grant permission to use the name or logo (section 6).
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared project-scoped memory for agent teams: typed records, corroboration, handoff briefs.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Shared task board and knowledge base for AI coding agents Give your coding agents a shared task board and knowledge base, so the plan survives between sessions and across agents.
Shared project memory that keeps teammates and AI agents aligned across sessions.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides persistent, searchable memory and knowledge capture for AI-assisted development, enabling agents to retain decisions, bugs, and patterns across sessions and projects.MIT
- AlicenseNot gradedqualityAmaintenanceEnables agents to maintain persistent project context locally, with source-backed memory and structured handoffs for seamless handover between interchangeable agents.Apache 2.0

nightqueueofficial
AlicenseNot gradedqualityAmaintenanceProvides persistent, scoped memory and tooling for autonomous coding agents, letting lessons, decisions, and project knowledge accumulate across queue runs.26 npmBusiness Source 1.1- FlicenseNot gradedqualityAmaintenanceGives AI coding agents persistent, local-first memory so they can store, semantically search, and recall decisions, preferences, error patterns, and cross-project guidelines directly during a session. It also optionally queues tasks for autonomous execution against that same memory.-