Langmcp

MCP文档知识

提供方 未标注

文档知识 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

一个MCP服务器,与LangChain检查点和记忆存储连接,用于在AI应用开发过程中辅助监控和可观测性。

一句话选型结论

按资料字段整理

Langmcp 属于文档知识类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

记忆

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
uvx "langmcp[all]" --version

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Langmcp当前 未标注 stdio · 本地进程 本地部署 有 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类文档知识本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

8.5 KB
来自项目仓库与上游目录的原文,未做删改

LangMCP

Read-only MCP server for inspecting LangGraph checkpoints, thread state, and long-term memory.

LangMCP helps you answer the debugging question that traces do not always answer:

> What is actually saved in my LangGraph persistence layer right now?

It is not a generic SQL MCP. It uses LangGraph-native checkpointer and store APIs,
connects through named profiles, and keeps database credentials out of tool
arguments.

Why LangMCP

When a stateful agent behaves strangely, the problem is often not only the prompt.
It might be the checkpoint it resumed from, the user ID in configurable state, the
store namespace used for memory, or an oversized message history.

LangMCP gives MCP clients such as Cursor and Claude Desktop a safe inspection
surface for those questions.

LangMCP Not LangMCP
Read-only inspection of LangGraph persistence Arbitrary SQL execution
Profile-based connections Raw DSNs in model-facing arguments
Tools, resources, and prompts for debugging state A replacement for LangSmith or LangGraph Studio
Local stdio MCP server for development LangGraph Agent Server API

Use LangSmith for traces, LangGraph Studio for visual graph workflows, and
LangMCP when you want an assistant in your editor to inspect persisted state
through a narrow read-only interface.

Features

  • Profile-based config with environment variable expansion.
  • Read-only enforcement in v0.1.
  • Secret redaction in health checks and error output.
  • PostgreSQL, SQLite, and Redis checkpointer inspection.
  • PostgreSQL PostgresStore long-term memory inspection.
  • MCP tools for threads, checkpoints, store data, and analysis.
  • MCP resources for stable readable state URIs.
  • MCP prompts for repeatable debugging workflows.
  • Pagination and truncation for large responses.

Installation```bash

uv pip install "langmcp[all]"


Or run without installing:```bash
uvx "langmcp[all]" --version

LangMCP supports Python 3.11 and 3.12. The repository includes a
.python-version file set to Python 3.12.

Configuration

Copy the example config and environment files:```bash
cp examples/langmcp.example.toml langmcp.toml
cp .env.example .env


Set a read-only database URI in `.env`:```dotenv
POSTGRES_URI=postgresql://READONLY_USER:READONLY_PASSWORD@HOST:5432/DB_NAME
LANGMCP_READ_ONLY=true

LangMCP loads .env automatically when present. Existing shell environment
variables take precedence.

Example langmcp.toml:```toml
[defaults]
profile = "dev"
read_only = true
max_response_chars = 250000

[profiles.dev]
checkpointer = "${POSTGRES_URI}"
store = "${POSTGRES_URI}"
user_namespace = "users/{user_id}"

[profiles.local_sqlite]
checkpointer = "sqlite:///./.langgraph/checkpoints.db"

[profiles.local_redis]
checkpointer = "redis://localhost:6379/0"


Set `user_namespace` to the namespace template your graph uses for long-term
memory. The default is `{user_id}` for compatibility. For stores organized as
`users//...`, use `users/{user_id}`. The `summarize_user_memory` tool
also accepts `namespace_prefix` to override the profile template for one call.

Environment overrides:

- `LANGMCP_CONFIG`
- `LANGMCP_PROFILE`
- `LANGMCP_READ_ONLY`
- `POSTGRES_URI`
- `LANGMCP_CHECKPOINTER_URI`
- `LANGMCP_STORE_URI`

## Verify Setup

Run:```bash
langmcp doctor --config ./langmcp.toml

The doctor command checks connectivity, backend types, setup status, package
versions, and redacts sensitive URI fields.

Cursor Setup

See examples/cursor-mcp.json.

Minimal shape:```json
{
"mcpServers": {
"langmcp": {
"command": "uvx",
"args": ["langmcp[all]", "serve", "--config", "ABSOLUTE_PATH_TO_LANGMCP_TOML"],
"env": {
"LANGMCP_READ_ONLY": "true",
"POSTGRES_URI": "postgresql://READONLY_USER:READONLY_PASSWORD@HOST:5432/DB_NAME"
}
}
}
}


Start the server directly:```bash
langmcp serve --config ./langmcp.toml

Example Assistant Prompts

Once connected through MCP, ask your assistant:```text
Use LangMCP to summarize thread THREAD_ID and check whether user memory exists for USER_ID.
text Compare checkpoint CHECKPOINT_A and CHECKPOINT_B for thread THREAD_ID. Tell me what changed.text
Analyze whether thread THREAD_ID is carrying too much context.
``````text
Investigate a possible memory gap for thread THREAD_ID and user USER_ID.


## MCP Tools

All tools accept optional `profile` unless noted. Responses include `profile`,
`truncated`, and pagination fields where applicable.

| Tool | Description |
|------|-------------|
| `health_check` | Connectivity, backend types, redacted URIs |
| `list_profiles` | Profile names and backend types |
| `list_threads` | Discover thread IDs |
| `get_thread_state` | Latest or specific checkpoint state |
| `list_checkpoint_history` | Paginated checkpoint list |
| `get_checkpoint` | Full snapshot for one checkpoint |
| `compare_checkpoints` | Diff values and message count delta |
| `summarize_thread` | Transcript-style summary |
| `analyze_context_window` | Token estimate and size warnings |
| `analyze_memory_gaps` | Store versus thread user ID hints |
| `list_namespaces` | Store namespace tuples |
| `search_store` | Search under namespace prefix |
| `get_store_item` | Full store value by key |
| `summarize_user_memory` | Grouped keys under a configured or explicit user namespace template |

## MCP Resources

Resources expose readable state through stable MCP URIs.

| Resource URI | Description |
|--------------|-------------|
| `langmcp://profiles` | Configured profiles and active profile |
| `langmcp://profiles/{profile}/health` | Connectivity and setup status |
| `langmcp://profiles/{profile}/threads` | Discovered thread IDs |
| `langmcp://profiles/{profile}/threads/{thread_id}/state` | Latest thread state |
| `langmcp://profiles/{profile}/threads/{thread_id}/summary` | Transcript-style thread summary |
| `langmcp://profiles/{profile}/threads/{thread_id}/checkpoints` | Recent checkpoint history |
| `langmcp://profiles/{profile}/threads/{thread_id}/checkpoints/{checkpoint_id}` | Full checkpoint snapshot |
| `langmcp://profiles/{profile}/threads/{thread_id}/context-analysis` | Context-window analysis |
| `langmcp://profiles/{profile}/store/namespaces` | Long-term memory namespaces |
| `langmcp://profiles/{profile}/store/items/{namespace}/{key}` | One store item |
| `langmcp://profiles/{profile}/users/{user_id}/memory-summary` | User memory summary |

For multi-part namespaces, prefer the `get_store_item` tool if your MCP client
treats `/` as a path separator inside resource parameters.

## MCP Prompts

Prompts package repeatable investigations.

| Prompt | Description |
|--------|-------------|
| `debug_thread` | Diagnose one thread from summary, checkpoints, context analysis, and memory hints |
| `investigate_memory_gap` | Check whether thread state and long-term memory are aligned |
| `compare_thread_checkpoints` | Explain behavioral differences between two checkpoints |
| `inspect_user_memory` | Summarize and sanity-check long-term memory for one user |

## Backend Matrix

| Backend | Checkpointer | Store in v0.1 |
|---------|--------------|---------------|
| PostgreSQL | Full | Full through `PostgresStore` |
| SQLite | Full | Not supported |
| Redis | Full | Not supported |

## Security

1. Tools accept profile names, not raw DSNs.
2. `read_only=true` is enforced in v0.1.
3. Use a read-only PostgreSQL user for shared environments.
4. Passwords are redacted in `health_check` and CLI output.
5. Redis thread discovery uses `SCAN` with limits. Avoid broad scans on very large instances.
6. Commit `examples/langmcp.example.toml` and `.env.example`, not real `langmcp.toml` or `.env` files.

## Development```bash
uv pip install -e ".[all,dev]"
ruff check .
pytest tests/unit -v

Integration tests use local Docker services:bash docker compose -f docker-compose.test.yml up -d POSTGRES_URI=postgresql://langgraph:langgraph@localhost:5442/langgraph \ REDIS_URI=redis://localhost:6379/0 \ pytest tests/integration -v -m integration

Use the local test values from docker-compose.test.yml. They are for Docker
integration tests only.

Roadmap

  • LangGraph Agent Server adapter.
  • HTTP transport with team auth.
  • Vector store inspection tools.
  • Carefully scoped write workflows such as update_thread_state and resume_thread.

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md.

Good first issue ideas:

  • Add examples for a specific LangGraph persistence backend.
  • Improve error messages for unsupported store backends.
  • Add a resource or prompt test for an edge case.

License

MIT. See LICENSE.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Langmcp 怎么安装?

在客户端按下面的安装命令接入:uvx "langmcp[all]" --version。装完在客户端配置里引用同一个包或端点。

Langmcp 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Langmcp 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Langmcp 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Langmcp 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Langmcp 能提供哪些能力?

资料显示能力标签包括 记忆。具体工具清单以官方文档为准。

Langmcp 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Langmcp 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。