npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@sanity/context-langchain

v0.1.0

Published

Sanity Context for LangChain agents

Readme

@sanity/context-langchain

Sanity Context for LangChain agents. Connect a LangChain agent to a Context MCP endpoint. The agent gets the endpoint's current tools on every run, so changes to the endpoint's sources in the Context app reach it without a restart. The agent loads the initial context itself, through the initial_context tool.

It takes the endpoint URL and an organization API token with Context access (Viewer is enough). Keep the token server-side. Create one connector per endpoint and token, and reuse it across runs.

Install

npm install @sanity/context-langchain langchain @langchain/core @langchain/langgraph @langchain/mcp-adapters @langchain/anthropic

Install the package for your model provider; the example uses @langchain/anthropic.

Use it

import {createSanityContext} from '@sanity/context-langchain'
import {createAgent} from 'langchain'

const sanity = createSanityContext({
  url: process.env.SANITY_CONTEXT_MCP_URL!,
  token: process.env.SANITY_ORGANIZATION_TOKEN!,
})

const agent = createAgent({
  model: 'anthropic:claude-sonnet-5-5',
  systemPrompt: 'You are a support agent.',
  // First, so other middleware sees the Sanity tools.
  middleware: [sanity.middleware],
})
  • Requires langchain 1.6 or later.
  • Before every model call, the middleware lists the endpoint's tools, one request per step.
  • A Sanity tool call that fails reaches the model as an error it can act on. Like any middleware that wraps tool calls, it makes LangChain rethrow errors from your own tools; add LangChain's toolErrorMiddleware to send those to the model.

Errors

  • A missing URL or token, or a URL that isn't https, throws when you create the connector.
  • When the tools can't be listed, the agent run fails with Could not connect to Sanity Context: …, or Sanity Context rejected the token … for a 401 or 403.
  • Tool results contain your content, so anyone who can edit that content can influence what the agent does.

See the Sanity Context guide for LangChain for setting up an endpoint and a token.