Artificial Intelligence
LangChain MCP connector
The LangChain connector links your LangChain sessions, session views, insights and insight configs to Claude, ChatGPT, Cursor and other MCP clients through one Elaichi endpoint, so each person works in LangChain as themselves with every action logged.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect LangChain to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect LangChain once
-
Open Connections, choose Add connection, and pick LangChain.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a LangChain API key. One person generates a token in LangChain and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect LangChain to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect LangChain to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect LangChain to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect LangChain to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with LangChain through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Check on a session before standup
Ask for the dashboard of a LangChain session by name and get a plain summary of how it is doing, without opening another tab.
-
Engineering
Set up a new session for a launch
Create a LangChain session for a new feature, then rename or update it later as the project changes shape.
-
Product
Turn a question into a saved view
Describe what you want to see and have a LangChain session view created for it, then rename a batch of views in one go when naming conventions change.
-
Data science
Read the insights on a session
Pull the session insights LangChain has generated, ask what stands out, and create or adjust an insights config to change what gets tracked next.
-
Operations
Tidy up old sessions in bulk
List every LangChain session, spot the ones nobody has touched, and delete them together once the team agrees.
-
Support
Confirm LangChain is healthy during an incident
Check LangChain's health status and the metadata on the affected session so you can tell customers what is going on with confidence.
Try asking
- “Summarize this week's LangChain sessions by status.”
- “Which session views changed most in the last 14 days?”
- “List sessions missing metadata from last week's runs.”
AI tools
LangChain tools for your AI agents
382 tools are ready to call through Elaichi's MCP endpoint the moment you connect LangChain, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting LangChain gets you
6 screens from the product, each doing one job for your LangChain account.
The agent
Ask about your sessions, get real answers.
Ask plain-language questions and get answers pulled from live LangChain session records.
- sessions
- session views
- metadata
- dashboards
Ask Elaichi to work across your apps.
Summarize this week's LangChain sessions by status.
Which session views changed most in the last 14 days?
List sessions missing metadata from last week's runs.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint, every client, no shared keys.
Connect Claude, ChatGPT and Cursor to one governed LangChain endpoint, no SDK required.
Copy the endpoint
Tool catalog
382 LangChain tools, ready without custom code.
Browse all 382 LangChain tools, resources and methods without writing any custom code.
- List all LangChain info healths
- Get single LangChain session dashboard by ID
- Get single LangChain session by ID
- Update a LangChain session by ID
Toolboxes
Every team gets its own LangChain toolbox.
See toolboxes scoped to each team, from sessions to session views.
- Engineering
- Data Science
- Product
- Support
Shared connections
Share LangChain access without ever sharing credentials.
See who connected each LangChain account and how many teams and members use it.
- Engineering Prod
- Data Science
- Product Analytics
- Support Ops
Audit log
Every LangChain action, logged and attributable.
Track when, who, what happened, type and resource for every LangChain call.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
Schedules trigger real LangChain work end to end.
A schedule fires, fetches LangChain sessions, drafts a digest, and waits for approval before posting.
LangChain digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch sessions
LangChain
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
LangChain
Queued
Collections and dashboards
See LangChain health without asking anyone.
Four metrics and a 14 day chart track LangChain records, refreshed on schedule automatically.
LangChain health
Refreshed 4 minutes ago · every 15 minutes · from the sessions collection
Sessions
1,284 ↓ 12%
Session views
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Sessions created
Last 14 days
By team
Share of activity
Engineering Prod 34%
Data Science 27%
Product Analytics 21%
Support Ops 18%
FAQ
Frequently asked questions
How do I connect LangChain to Claude?
Connect LangChain in Elaichi first, which asks for your LangChain API key and nothing else, so there is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in with your Elaichi account when prompted and LangChain is ready to use in Claude.
Does LangChain work with ChatGPT and Cursor as well as Claude?
Yes. Once LangChain is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect LangChain once and every client picks it up.
What can an AI agent actually do with my LangChain data?
An agent can list your LangChain sessions, open a session's dashboard and describe how it is performing, create or rename sessions and session views, and read or create session insights and insight configs. It can also check LangChain's health and pull session metadata when something looks off. LangChain has a large set of actions, so short concrete asks like "show me the dashboard for the checkout session" work better than long paragraphs.
Does connecting LangChain give the AI access to every session in my workspace?
No. Access follows the LangChain API key of the person who connected it, so an agent only sees the LangChain sessions, views and insights that key already reaches. Elaichi can narrow that further with per-action restrictions, and it can never widen it beyond what LangChain itself allows.
Can I stop an agent from deleting or changing things in LangChain?
Yes. Restrictions in Elaichi work per action, so you can allow reading LangChain sessions and insights while blocking deleting sessions, bulk deleting or editing insight configs. A blocked action is never shown to Claude, ChatGPT or Cursor at all, so no prompt can reach it.
What happens to a LangChain connection when someone leaves?
Offboarding a person in Elaichi ends their access to LangChain at once, across every client they used. A shared LangChain connection keeps working for everyone else on the team. If you want LangChain gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.
Put LangChain in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.