langchain-ai/langchain-plugins is a marketplace of plugins for coding agents that provide skills and Model Context Protocol servers for the LangChain, LangGraph, Deep Agents, and LangSmith ecosystems. Developers use it to build or debug agent applications, consult current documentation, and inspect or evaluate LangSmith workspaces. The catalogue entries are the marketplace’s own plugin and MCP offerings.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/langchain-ai/langchain-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/langchain-ai/langchain-plugins/langchain-mcp-langchain-reference)<a href="https://agentmods.dev/mcp/langchain-ai/langchain-plugins/langchain-mcp-langchain-reference"><img src="https://agentmods.dev/badge/mcp/langchain-ai/langchain-plugins/langchain-mcp-langchain-reference.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
langchain-reference scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"langchain-reference": {
"type": "http",
"url": "https://reference.langchain.com/mcp"
}
}What else .mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 6 lines scan A cc8fc06d45f8
langchain-reference is an MCP server published in the GitHub repository langchain-ai/langchain-plugins (7 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/deepagents.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/deepagents.
agentguard47
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health. Runs locally from the @agentguard47/mcp-server npm package. Needs 2 environment variables to run.
acmi-mcp
Persistent agent memory via ACMI — Profile/Signals/Timeline. 16 tools on Upstash Redis. Runs locally from the @madezmedia/acmi-mcp npm package. Needs 2 environment variables to run.
veriswarm-mcp
VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol. Runs locally from the veriswarm-mcp Python package.
pulsefeed-x402
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores. Runs locally from the pulsefeed-x402-mcp npm package.