langchain

A connection between LangChain, a framework for building language-model applications, and MCP, a standard for connecting those applications to tools.

In plain words
What is it for?
Use it to connect LangChain agents to one or more MCP servers and access their tools through a standard interface.
Why use it?
It avoids writing separate integrations for every tool server and lets an agent discover and use tools from multiple MCP servers.

Agent

Install

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.

agentmods
npx agentmods add agents/ibm/mcp-context-forge/langchain
Clone the repo
git clone --depth 1 https://github.com/IBM/mcp-context-forge
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00452
Opus 5 $0.00000 $0.00226
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash ec9efd8ff6a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

langchain 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 2d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • langchain — 100% identical, 0 lines differ
  • langchain — 100% identical, 0 lines differ
docs/docs/using/agents/langchain.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LangChain Integration with ContextForge

LangChain is a framework for developing applications powered by language models. Integrating LangChain with the Model Context Protocol (MCP) allows agents to utilize tools defined across one or more MCP servers, enabling seamless interaction with external data sources and services.


🧰 Key Features

  • Dynamic Tool Access: Connects to MCP servers to fetch available tools in real time.
  • Multi-Server Support: Interact with tools defined on multiple MCP servers simultaneously.
  • Standardized Communication: Utilizes the open MCP standard for consistent tool integration.

🛠 Installation

To use MCP tools in LangChain, install the langchain-mcp-adapters package:

pip install langchain-mcp-adapters

🔗 Connecting to ContextForge

Here's how to set up a connection to your ContextForge:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent

client = MultiServerMCPClient(
    {
        "gateway": {
            "url": "http://localhost:4444/mcp",
            "transport": "streamable_http",
        }
    }
)

Replace "http://localhost:4444/mcp" with the URL of your ContextForge.


🤖 Creating an Agent

After setting up the client, you can create a LangChain agent:

agent = create_react_agent(
    tools=client.get_tools(),
    llm=your_language_model,
)

Replace your_language_model with your configured language model instance.


🧪 Using the Agent

Once the agent is created, you can use it to perform tasks:

response = agent.run("Use the 'weather' tool to get the forecast for Dublin.")
print(response)

📚 Additional Resources


Read the full file on GitHub · 77 lines

Changes

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.

  1. 2d ago First seen · 77 lines · 0 tokens per session scan A ec9efd8ff6a2

Subscribe to this mod's changes

langchain is an agent published in the GitHub repository IBM/mcp-context-forge (4,399 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 452 tokens. 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 2026-08-30.