Langchain MCP ToolsCAUTION
MCP to LangChain Tools Conversion Utility / Python
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP to LangChain Tools Conversion Library / Python [](https://github.com/hideya/langchain-mcp-tools-py/blob/main/LICENSE) [](https://pypi.org/project/langchain-mcp-tools/) [](https://dependents.info/hideya/langchain-mcp-tools-py)
A simple, lightweight library to use Model Context Protocol (MCP) server tools from LangChain.
Project Status
This library currently supports MCP Protocol version 2025-03-26. It does not support the MCP 2026-07-28 specification.
For new projects, we recommend using LangChain's official LangChain MCP Adapters library, which provides comprehensive MCP integration for LangChain.
This project is now in maintenance / dormant mode. Existing users may continue using it with MCP servers compatible with the 2025-03-26 specification, but new MCP protocol features will not be actively implemented here.
Introduction
A simple, lightweight library to use Model Context Protocol (MCP) server tools from LangChain.
Its simplicity and extra features for local MCP servers can make it useful as a basis for your own customizations. However, it only supports text results of tool calls and does not support MCP features other than tools.
LangChain's **official LangChain MCP Adapters** library, which supports comprehensive integration with LangChain, has been released. You might want to consider using it if the extra features that this library supports are not neces
2a53d2d939bdOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add langchain-mcp-tools --env BRAVE_API_KEY=${BRAVE_API_KEY} --env GITHUB_PERSONAL_ACCESS_TOKEN=${GITHUB_PERSONAL_ACCESS_TOKEN} -- uvx langchain-mcp-tools{
"mcpServers": {
"langchain-mcp-tools": {
"command": "uvx",
"args": [
"langchain-mcp-tools"
],
"env": {
"BRAVE_API_KEY": "${BRAVE_API_KEY}",
"GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_PERSONAL_ACCESS_TOKEN}"
}
}
}
}Exposed tools (9)
7 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add | write | Add two numbers together. |
authenticated_echo | read | Echo back a message with authentication context. |
create_document | write | Create a new document for the authenticated user. |
echo | read | |
get_current_user | read | Get information about the currently authenticated user. |
get_user_info | read | Get information about the authenticated user. |
greet | read | Return a greeting message. |
hello | read | |
list_user_documents | read | List documents accessible to the authenticated user. |
Trust audit
CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (10 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (8)
print(f"Bearer {token}")print(f"🔑 Using token: {token[:50]}...")"url": "http://127.0.0.1:8001/mcp",
"url": "http://127.0.0.1:8003/mcp",
"url": "http://127.0.0.1:9999/mcp",
"url": "http://127.0.0.1:8003/mcp",
"url": "http://127.0.0.1:8001/mcp",
.env.template
Gates applied: no_behavioural_pass.
2a53d2d939bdfull audit observations/trust-audit/mcp-server/hideya__langchain-mcp-tools.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 2a53d2d939bd | CAUTION | B | 87 | first audit |
Questions
What is the Langchain MCP Tools MCP server?
MCP to LangChain Tools Conversion Utility / Python
What tools does Langchain MCP Tools expose?
9 in total: 7 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Langchain MCP Tools safe to connect to an agent?
With care. The audit graded it B (87/100) and found 8 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Langchain MCP Tools need?
It reads BRAVE_API_KEY and GITHUB_PERSONAL_ACCESS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Langchain MCP Tools run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as langchain-mcp-tools.
How current is this page?
The grade is for one exact copy of the source (2a53d2d939bd), read on 2026-10-08. The repository is watched and re-audited when it changes.