LangChain

corsairTools turns a Corsair instance into LangChain.js tools, one tool per API operation. Hand them to createReactAgent({ tools }) or model.bindTools(...) and the model can call Slack, GitHub, Gmail, Linear, Stripe, and the rest of the plugin catalog. The credentials never leave your database. Corsair runs OAuth server-side, stores the encrypted tokens under your own key, and the tool call reads them at execution time. The model sees tool names and results, never a token.

Install

npm install @corsair-dev/langchain @langchain/core corsair

pnpm add @corsair-dev/langchain @langchain/core corsair

yarn add @corsair-dev/langchain @langchain/core corsair

Then add one @corsair-dev/* package per service you connect, plus your LangChain model and agent runtime:

npm install @corsair-dev/slack        # one per integration
npm install @langchain/openai @langchain/langgraph

@langchain/core is a peer dependency. The adapter imports it lazily, so installing @corsair-dev/langchain alone never pulls LangChain into a project that does not use this entrypoint.

Quickstart

Create the Corsair instance

Build it once and reuse it. authType: 'managed' lets Corsair hold the OAuth connection; the tokens stay encrypted in your database under your kek.

corsair.ts

import { createCorsair } from 'corsair';
import { slack } from '@corsair-dev/slack';
import { database } from './db';

export const corsair = createCorsair({
  plugins: [slack({ authType: 'managed' })],
  database,
  kek: process.env.CORSAIR_KEK,
  hub: { projectApiKey: process.env.CORSAIR_API_KEY },
});

Build the tools

corsairTools is async. It returns one DynamicStructuredTool per operation, ready for any LangChain agent.

import { corsairTools } from '@corsair-dev/langchain';
import { corsair } from './corsair';

const tools = await corsairTools({ corsair, plugin: 'slack' });

Give them to an agent

agent.ts

import { ChatOpenAI } from '@langchain/openai';
import { createReactAgent } from '@langchain/langgraph/prebuilt';
import { corsairTools } from '@corsair-dev/langchain';
import { corsair } from './corsair';

const tools = await corsairTools({ corsair, plugin: 'slack' });

const llm = new ChatOpenAI({
  model: 'gpt-4.1-mini',
  configuration: {
    baseURL: 'https://llm.corsair.dev/v1',
    apiKey: process.env.LITELLM_API_KEY,
  },
});

const agent = createReactAgent({ llm, tools });

const result = await agent.invoke({
  messages: [{ role: 'user', content: 'List the Slack channels.' }],
});
console.log(result.messages.at(-1)?.content);

Route model calls through the Corsair LLM gateway (llm.corsair.dev, OpenAI-compatible) to keep spend on budget-limited keys. Point any @langchain/openai model at it with the configuration.baseURL shown above. See LLM gateway.

Choosing which tools

Scope the toolset so the model only sees what the task needs. Fewer tools means cleaner prompts and fewer wrong turns.

// A whole plugin, as a toolkit:
await corsairTools({ corsair, plugin: 'slack' });

// Specific operations only:
await corsairTools({
  corsair,
  operations: ['slack.api.channels.list', 'slack.api.messages.post'],
});

// Every operation of every registered plugin (omit both):
await corsairTools({ corsair });

Multi-tenancy

On a multi-tenant instance, pin the tenant whose stored credentials the tools should use. Each tenant owns its own connections, so the same code serves every user:

const tools = await corsairTools({
  corsair,
  plugin: 'slack',
  tenantId: user.orgId,
});

Single-tenant instances ignore tenantId.

API

function corsairTools(options: CorsairToolsOptions): Promise<DynamicStructuredTool[]>

CorsairInstance

required

The value from createCorsair() (or corsair.withTenant(...)).

string

Include every operation of one plugin. Omit plugin and operations to include all registered plugins.

string[]

Include only these operation paths, e.g. slack.api.channels.list.

string

Use the stored credentials of this tenant. Ignored on single-tenant instances.

Notes

Tool names. The operation path becomes the tool name with . replaced by _ (slack.api.channels.list becomes slack_api_channels_list), so it satisfies the model’s function-name constraint.
Schemas. Corsair is on Zod v4, which current @langchain/core accepts directly. No JSON Schema conversion step.
Results. String results pass through; anything else is JSON-encoded into the tool message the model reads.

The tool runs whatever operation the model picks with the tenant’s real credentials. Scope with plugin or operations so an agent can only reach the APIs the task actually needs.

Get Started

Frameworks

Adapters

Workflows (beta)

Reference

Install

Quickstart

Choosing which tools

Multi-tenancy

API

Notes

​Install

​Quickstart

​Choosing which tools

​Multi-tenancy

​API

​Notes

Install

Quickstart

Choosing which tools

Multi-tenancy

API

Notes