Atlas / MCP servers / langchain-ai / LangChain.js MCP Adapters

LangChain.js MCP AdaptersSAFE

mcp/langchain-ai/langchain-js-mcp-adapters

** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters ** Adapters for integrating Model Context Protocol (MCP) tools with LangChain.js applications, supporting both stdio and SSE transports.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
7 6r · 1w · 0d
Transport
sse · streamable-http
License
MIT
Stars
248
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[!IMPORTANT] This package has been migrated into [the LangChainJS monorepo](https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters).

[](https://www.npmjs.com/package/@langchain/mcp-adapters) [](https://opensource.org/licenses/MIT)

This library provides a lightweight wrapper to allow Model Context Protocol (MCP) services to be used with LangChain.js.

This project has moved. For a current description of this project, please see the up-to-date README at the project's new location.

Read from source at commit 57ea4ffefd05OBSERVED · 2026-10-06
02

Connect

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-code
claude mcp add mcp-adapters --env FIRECRAWL_API_KEY=${FIRECRAWL_API_KEY} -- npx -y @langchain/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-adapters": {
      "command": "npx",
      "args": [
        "-y",
        "@langchain/[email protected]"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}"
      }
    }
  }
}
03

Exposed tools (7)

6 read · 1 write · 0 destructive.

ToolRiskDescription
addwriteAdds two numbers together
dividereadDivides two numbers
multiplyreadMultiplies two numbers
subtractreadSubtracts two numbers
tool1readTool 1
tool2readTool 2
weatherreadGet the weather for a given city
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (4)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.eslintrc.cjs
.eslintrc.cjs
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.yarnrc.yml
.yarnrc.yml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, debug, zod, @eslint/js, @langchain/core, @langchain/langgraph, @langchain/openai, @langchain/scripts
Why it matters. 37 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOInventory / provenance · inv.oversize · CWE-1104
.yarn/releases/yarn-3.5.1.cjs
.yarn/releases/yarn-3.5.1.cjs
Why it matters. 2226448 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-06 · audit v0.4.1 · source sha 57ea4ffefd05full audit observations/trust-audit/mcp-server/langchain-ai__langchain-js-mcp-adapters.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0657ea4ffefd05SAFEB89first audit
06

Questions

What is the LangChain.js MCP Adapters MCP server?

** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters ** Adapters for integrating Model Context Protocol (MCP) tools with LangChain.js applications, supporting both stdio and SSE transports.

What tools does LangChain.js MCP Adapters expose?

7 in total: 6 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is LangChain.js MCP Adapters safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does LangChain.js MCP Adapters need?

It reads FIRECRAWL_API_KEY 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.js MCP Adapters run?

It speaks sse and streamable-http, so it runs as a service you connect to over the network. It is published on npm as @langchain/mcp-adapters at 0.4.5.

How current is this page?

The grade is for one exact copy of the source (57ea4ffefd05), read on 2026-10-06. The repository is watched and re-audited when it changes.

Advertisement