langmcp
About
A MCP server that connects with LangChain Checkpointers, Memory Stores to aid in monitoring and observability during development of AI Applications
Details
- Author
- xmassmx
- Categories
- AI, Infrastructure, Developer Tools
Jump to
Setup
Install langmcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/xmassmx/langmcp
Follow the installation instructions in the repository README, then restart your MCP client.
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.
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.
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.
- 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.
- PostgreSQLPostgresStorelong-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.
LangMCP supports Python 3.11 and 3.12. The repository includes a.python-versionfile set to Python 3.12.
Copy the example config and environment files:
cp examples/langmcp.example.toml langmcp.toml cp .env.example .env
POSTGRES_URI=postgresql://READONLY_USER:READONLY_PASSWORD@HOST:5432/DB_NAME LANGMCP_READ_ONLY=true
LangMCP loads.envautomatically when present. Existing shell environment variables take precedence.
[defaults] profile = "dev" read_only = true max_response_chars = 250000 [profiles.dev] checkpointer = "${POSTGRES_URI}" store = "${POSTGRES_URI}" [profiles.local_sqlite] checkpointer = "sqlite:///./.langgraph/checkpoints.db" [profiles.local_redis] checkpointer = "redis://localhost:6379/0"
- LANGMCP_CONFIG
- LANGMCP_PROFILE
- LANGMCP_READ_ONLY
- POSTGRES_URI
- LANGMCP_CHECKPOINTER_URI
- LANGMCP_STORE_URI
The doctor command checks connectivity, backend types, setup status, package versions, and redacts sensitive URI fields.
{ "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" } } } }
Once connected through MCP, ask your assistant:
Use LangMCP to summarize thread THREAD_ID and check whether user memory exists for USER_ID.
Compare checkpoint CHECKPOINT_A and CHECKPOINT_B for thread THREAD_ID. Tell me what changed.
Analyze whether thread THREAD_ID is carrying too much context.
Investigate a possible memory gap for thread THREAD_ID and user USER_ID.
All tools accept optionalprofileunless noted. Responses includeprofile,truncated, and pagination fields where applicable.
Resources expose readable state through stable MCP URIs.
For multi-part namespaces, prefer theget_store_itemtool if your MCP client treats/as a path separator inside resource parameters.
Prompts package repeatable investigations.
- Tools accept profile names, not raw DSNs.
- read_only=trueis enforced in v0.1.
- Use a read-only PostgreSQL user for shared environments.
- Passwords are redacted inhealth_checkand CLI output.
- Redis thread discovery usesSCANwith limits. Avoid broad scans on very large instances.
- Commitexamples/langmcp.example.tomland.env.example, not reallangmcp.tomlor.envfiles.
uv pip install -e ".[all,dev]" ruff check . pytest tests/unit -v
Integration tests use local Docker services:
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 fromdocker-compose.test.yml. They are for Docker integration tests only.
- LangGraph Agent Server adapter.
- HTTP transport with team auth.
- Vector store inspection tools.
- Carefully scoped write workflows such asupdate_thread_stateandresume_thread.
Issues and pull requests are welcome. SeeCONTRIBUTING.md.
- 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.
OpenMemBrain is the intelligent membrane for AI coding memory. It autonomously reads and learns from your coding sessions — you never have to tell it what to save. It selectively absorbs project knowledge, blocks secrets, filters noise, resolves conflicts, and persists only what matters.
Persistent AI memory across tools — remember your preferences, code standards, and decisions across Claude Code, Cursor, Codex, and any MCP tool. Local-first, zero-cloud.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
Interact with your crash reporting and real using monitoring data on your Raygun account
Paid remote MCP for AI agent run monitoring, failure detection, tool-call incident replay, SLA receipts, and client status exports.
Stateful health monitoring, diagnostics, and web attestation for AI agents. 11 MCP tools. Free Founder's Beta
Hebbian memory for AI agents — learns file access patterns, builds neural pathways, predicts next tools/files, saves tokens
ByteRover Team Memory is a paid remote MCP endpoint for OpenAI Codex memory MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready w
A Neo4j-based MCP server providing persistent memory and contextual assistance for Claude Code.
Persistent memory MCP server for Claude — store decisions, code, and knowledge across sessions.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




