clawmem-mcp-server
An MCP server that leverages a GitHub-compatible API as a durable memory store for AI agents, enabling automatic memory storage, recall, and management without requiring signup or API keys.
README
clawmem-mcp-server
Stdio MCP server that powers the ClawMem durable-memory tools. Used by both the ClawMem Claude Code and Codex plugins, and runnable directly from any MCP-capable client.
ClawMem treats a GitHub-compatible backend (default git.clawmem.ai) as a memory store: type:memory issues are durable memories, type:conversation issues are session transcripts. The server auto-bootstraps an agent identity and a default repo on first tool call — no signup or API key required.
Use with Codex
Don't configure this directly unless you only want the raw MCP tools. Install clawmem-codex-plugin — it bundles the ClawMem behavior skill (teaches Codex when to recall / store / update / forget) and a hooks.json template that wires up auto-recall and conversation mirroring. That is the path you should recommend to users.
MCP-only install (minimal, no skill or hooks) is still supported — add this to ~/.codex/config.toml:
[mcp_servers.clawmem]
command = "npx"
args = ["-y", "clawmem-mcp-server"]
env = { CLAWMEM_AGENT_PREFIX = "codex", CLAWMEM_STATE_DIR = "~/.local/state/clawmem" }
Without the skill, Codex has the tools but no discipline about when to use them — you'll need to prompt it explicitly every time.
Use with Claude Code
Don't configure this directly — install clawmem-claude-code-plugin instead. It bundles hooks (auto-recall, conversation mirroring) that this raw MCP server alone can't provide.
Use with any other MCP client
Any client that accepts stdio MCP servers can launch this one:
{
"mcpServers": {
"clawmem": {
"command": "npx",
"args": ["-y", "clawmem-mcp-server"]
}
}
}
Configuration (env vars)
All optional.
| Env var | Default | Purpose |
|---|---|---|
CLAWMEM_BASE_URL |
https://git.clawmem.ai/api/v3 |
ClawMem API base. |
CLAWMEM_STATE_DIR |
~/.local/state/clawmem (or .data-dev/ in-repo for local dev) |
Where token + route state is persisted. ~ is expanded. |
CLAWMEM_AGENT_PREFIX |
claude |
Prefix used when deriving the auto-provisioned agent login. Set to codex when running inside Codex. |
CLAWMEM_DEFAULT_REPO_NAME |
memory |
Name of the auto-provisioned default repo. |
CLAWMEM_TOKEN |
— | Override the persisted token (useful for testing with a specific identity). |
CLAWMEM_MEMORY_RECALL_LIMIT |
5 |
Default recall page size (1–20). |
Tools
Shared tools are grouped by capability, with one Codex-only bootstrap helper:
- Memory:
memory_recall,memory_store,memory_update,memory_forget,memory_list,memory_get,memory_repos,memory_repo_create,memory_repo_set_default,memory_labels,memory_console. - Codex bootstrap:
clawmem_codex_bootstrapis exposed only whenCLAWMEM_AGENT_PREFIX=codex; it actively provisions the route and reports non-sensitive setup checks. - Issue / repo CRUD: thin wrappers over the GitHub-compatible API for agents that need richer access.
- Collaboration (F1/F2/F3): invites, repo access inspection, team membership. All writes require
confirmed=true.
Tool schemas are defined at the top of mcp/server.js.
Development
npm test # node --test test/*.test.js
node mcp/server.js # run the MCP server directly (stdio)
CLAWMEM_BASE_URL=http://127.0.0.1:4003/api/v3 node mcp/server.js
Releasing
Publishing to npm is automated. Pushing a v*.*.* tag triggers .github/workflows/publish.yml, which runs the test suite and then npm publish --provenance --access public using the NPM_TOKEN repo secret (an npm Automation token, so 2FA is bypassed in CI).
To cut a release:
npm version 0.1.3 -m "chore: release v0.1.3" # bumps package.json, commits, tags v0.1.3
git push --follow-tags # pushes the commit AND the tag
The workflow refuses to publish if the tag version doesn't match package.json. Run logs: https://github.com/clawmem-ai/clawmem-mcp-server/actions
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。