# What can LangChain do on LinkedIn with Finchreach?

Source: https://finchreach.com/integrations/langchain
Third-party facts checked on 2026-10-28.

LangChain can read your LinkedIn feed, messages and notifications, search LinkedIn, and draft posts, comments, messages and connection invitations through Finchreach’s remote MCP server. Add the server to LangChain and sign in to Finchreach (OAuth) or use your Finchreach API key; every write waits in your approval queue until you approve it.

## What can LangChain do on your LinkedIn?

LangChain lets you build your own LinkedIn agent in code. Finchreach provides the tools and the approval queue, so you don’t have to build a LinkedIn integration or a review step yourself.

> Ask your assistant: “An agent that reads my LinkedIn feed and writes a daily digest of posts in my field.”

> Ask your assistant: “A pipeline that drafts a LinkedIn post from each new article in our CMS.”

> Ask your assistant: “A research agent that finds people on LinkedIn by role and company and drafts invitations.”

| Reads (run right away) | Writes (wait for your approval) |
| --- | --- |
| `linkedin_list_accounts`: The LinkedIn accounts connected to your workspace | `linkedin_create_post`: A text post |
| `linkedin_get_profile`: A LinkedIn profile | `linkedin_send_dm`: A direct message |
| `linkedin_get_feed`: Your home feed | `linkedin_send_invitation`: A connection invitation, with an optional note |
| `linkedin_get_notifications`: Your notifications | `linkedin_react_to_post`: A reaction on a post (like by default) |
| `linkedin_get_conversations`: Your message threads | `linkedin_unreact`: Removes your reaction from a post |
| `linkedin_get_messages`: The messages in a thread | `linkedin_comment_on_post`: A comment on a post |
| `linkedin_search`: Search everything, posts, people or companies | `linkedin_delete_comment`: Deletes one of your comments |
| `linkedin_get_received_invitations`: Coming soon: the connection invitations waiting for your answer | `linkedin_accept_invitation`: Coming soon: accepts a received invitation |
| `linkedin_get_action`: The status of a write: waiting for approval, approved, rejected or done |  |

## What happens when LangChain drafts something?

1. LangChain calls a write tool, for example `linkedin_create_post` with the text it wrote.
2. Finchreach doesn’t post it. It stores a pending action and tells the assistant it is waiting for approval.
3. You open [Approvals](https://finchreach.com/approvals), read the exact text and the account it would go out from, and approve or reject it.
4. Approved actions run on LinkedIn; rejected ones never do. LangChain can check the outcome with `linkedin_get_action`.

> Approval mode is on by default for every workspace. It is what makes it reasonable to let an assistant draft in your name.

## Does LangChain work with Finchreach today?

|  | LangChain |
| --- | --- |
| Remote MCP servers | Built in |
| Finchreach (OAuth or API key) | Connects directly |
| How sure we are | High: from the official docs |
| Checked on | 2026-10-28 |

Headers work on the HTTP and SSE transports. The adapters repo is archived in favour of `langchain[mcp]`; newer docs show an `MCPAdapter` API we haven’t verified.

Finchreach’s server, `https://mcp.finchreach.com/mcp`, uses Streamable HTTP (pasting the bare `https://mcp.finchreach.com` works too). It signs in with OAuth 2.1, where you log in to Finchreach and approve a LinkedIn account and scopes, or with an API key sent as `Authorization: Bearer lk_…` or `X-API-Key`.

## How do I connect LangChain?

1. Create an API key under [API keys](https://finchreach.com/api-keys) and connect your LinkedIn account under [Accounts](https://finchreach.com/accounts).
2. Install the adapters: `pip install langchain-mcp-adapters`.
3. Create a `MultiServerMCPClient` with the `streamable_http` transport and the header, as below, and load the tools.
4. Ask LangChain to list your LinkedIn accounts to check the connection.

Python:
```python
from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({"finchreach": {
    "transport": "streamable_http",
    "url": "https://mcp.finchreach.com/mcp",
    "headers": {"Authorization": "Bearer lk_YOUR_KEY"},
}})
tools = await client.get_tools()
```

Replace `lk_YOUR_KEY` with your key. The [step-by-step LangChain guide](https://finchreach.com/guides/langchain) has every step, a test prompt and troubleshooting.

## Questions

### Can LangChain post on LinkedIn without me?

No. With approval mode on, the default, every write LangChain makes through Finchreach (posts, comments, reactions, messages, invitations) becomes a pending action. You approve or reject it under [Approvals](https://finchreach.com/approvals) before anything happens on LinkedIn.

### Can LangChain post images, schedule posts or manage a company page?

Not through Finchreach today: posts are text only, there is no scheduling, and company pages and analytics aren’t supported. Writes happen when you approve them.

### Is it safe for my LinkedIn account?

Any automation of a personal LinkedIn account carries some risk under LinkedIn’s User Agreement, and no tool can promise otherwise. Finchreach lowers it by keeping a person in the loop: nothing goes out until you approve it, and actions happen at your pace, not in bulk.

## Sources

- [LangChain docs](https://github.com/langchain-ai/langchain-mcp-adapters)
- [docs.langchain.com](https://docs.langchain.com/oss/python/langchain/mcp)

## Related

- [Step-by-step: connect LangChain](https://finchreach.com/guides/langchain)
- [Build a LangChain agent that drafts LinkedIn comments for approval](https://finchreach.com/blog/langchain-linkedin-comment-drafts)
- [All integrations](https://finchreach.com/integrations)