Social media · https://api.linkedin.com
set up terra — https://useterra.app/llms.txt
claude mcp add --transport http terra https://useterra.app/mcp
Settings → Connectors → add https://useterra.app/mcp as a custom connector.
Add https://useterra.app/mcp as a remote MCP connector in its tool settings.
Settings → Connectors → Add custom connector → https://useterra.app/mcp.
Point it at https://useterra.app/mcp (HTTP transport).
curl -fsSL https://useterra.app/install.sh | sh
LangChain, CrewAI or any code: /call/<tool-id> + X-Terra-Token: <token>. No SDK.
Using terra, upload a video to attach to a post. Show me the price first.
terra call linkedin.linkedin.user.profile
Connect once; useterra.app keeps the credential server-side and injects it per call. No key on any machine.
The provider's own rate, $0.000 markup. How billing works.
Calls through your own connection are not metered by terra.
Connect your account with the provider's supported authentication method.
Another provider is a different word in the prompt, not a new integration.
The same token calls AnyAPI, Bright Data, ContactOut and 3,539 other tools.
linkedin.linkedin.image.upload.initlinkedin.linkedin.user.post.createlinkedin.linkedin.user.profilelinkedin.linkedin.video.upload.finalizelinkedin.linkedin.video.upload.initReliability badges come from live traffic through useterra.app. Live-verified means a successful provider check; it does not verify every request variant.
Yes. This is an own-account connection: you sign in to LinkedIn once and your agent uses that connection through your useterra.app token. Calls on it are never metered.
Run: claude mcp add --transport http terra https://useterra.app/mcp. One MCP server carries LinkedIn and the rest of the catalog.
Anything that speaks MCP (Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, Grok) and anything that can make an HTTP request (LangChain, CrewAI, LlamaIndex, plain code).
No. useterra.app serves LinkedIn's real API through its own metered proxy: the request is the provider's own, the credential is injected server-side, and the answer is relayed verbatim. The official LinkedIn channels are linked above.