# Langbase — MCP server on mcp.ai
> Connect your Langbase account and use 20 tools for AI agents straight from your AI agent. Connect with your own API key. Langbase is a serverless AI developer platform that enables developers to build, collaborate, and deploy AI agents and applications with composable AI infrastructure.

By: mcp.ai · official
Page: https://mcp.ai/langbase

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_langbase?ms=1787296020000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/langbase/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/langbase/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/langbase/skill.md
Postman collection (v2.1): https://mcp.ai/langbase/postman.json

## Tools
- langbase_append_thread_messages(messages: object[], threadId: string) — Tool to add new messages to an existing conversation thread. Use when continuing a chat session or adding context to a thread.
- langbase_check_health() — Tool to check the health status of the Langbase API service. Use when you need to verify API availability.
- langbase_chunker_split_content(content: string, overlap?: integer, chunk_size?: integer, chunker_type?: string) — Tool to split content into smaller chunks. Use when processing large text segments to fit downstream limits.
- langbase_create_thread(messages?: object[], metadata?: object, threadId?: string) — Tool to create a new conversation thread. Use when starting a fresh chat session or grouping messages into a distinct thread.
- langbase_delete_thread(threadId: string) — Tool to delete a thread that is no longer needed to manage conversation history. Use when you need to permanently remove a thread by its ID.
- langbase_delete_thread_message(threadId: string, messageId: string) — Tool to delete a specific message from a conversation thread. Use when you need to remove a message from a thread by its ID.
- langbase_document_list(limit?: integer, memoryName: string, startAfter?: string, includeVectors?: boolean) — Tool to list documents in a specific memory. Use when you need to fetch document metadata (and optionally vectors) from a memory after confirming its name. Supports pagination via limit and startAfter
- langbase_get_pipe(pipe_name: string, owner_login: string) — Tool to retrieve details of a specific pipe by owner and name. Use when you need to fetch configuration and settings of a particular pipe.
- langbase_get_thread(threadId: string) — Tool to retrieve details of a specific conversation thread. Use when you need the full thread details by its ID after confirming its existence.
- langbase_list_models() — Tool to get available AI models supported by Langbase. Use to discover text and image generation models from various providers.
- langbase_list_thread_messages(limit?: integer, before?: string, threadId: string) — Tool to list all messages in a conversation thread. Use after obtaining the thread ID to fetch its messages.
- langbase_list_traces(limit?: integer, order?: string, offset?: integer, primitiveId: string, primitiveName: string) — Tool to get execution traces for debugging and monitoring pipe runs. Use when you need to retrieve trace logs for a specific primitive.
- langbase_memory_create(name: string, top_k?: integer, chunk_size?: integer, description?: string, chunk_overlap?: integer, embedding_model?: string) — Tool to create a new memory. Use when storing a new memory record in Langbase after confirming memory details.
- langbase_memory_delete(memory_name: string) — Tool to delete a specific memory. Use when you need to permanently remove a stored memory by its name.
- langbase_memory_list() — Tool to list all memory objects. Use when you need to fetch stored memories for context retrieval.
- langbase_pipe_create(json?: boolean, name: string, stop?: string[], model?: string, store?: boolean, top_p?: number, status?: string, stream?: boolean, upsert?: boolean, moderate?: boolean, max_tokens?: integer, description?: string, temperature?: number, tool_choice?: string, presence_penalty?: number, frequency_penalty?: number, parallel_tool_calls?: boolean) — Tool to create a new pipe. Use after configuring pipe parameters. Returns an array of pipe objects, each including API key and URL.
- langbase_pipe_list() — Tool to list all pipes. Use after authentication to retrieve the complete list of pipes. Returns an array of pipe objects; callers must handle list iteration.
- langbase_update_pipe(json?: boolean, name?: string, stop?: string[], model?: string, store?: boolean, tools?: object[], top_p?: number, memory?: object[], status?: string, stream?: boolean, messages?: object[], moderate?: boolean, pipe_name: string, variables?: object[]|object, max_tokens?: integer, description?: string, temperature?: number, tool_choice?: string|object, presence_penalty?: number, regenerateApiKey?: boolean, frequency_penalty?: number, parallel_tool_calls?: boolean) — Tool to update an existing pipe's configuration on Langbase. Use when modifying model settings, parameters, prompts, tools, or memory. The pipe must already exist.
- langbase_update_thread(metadata?: object, threadId: string) — Tool to update an existing thread's metadata. Use when you need to modify metadata fields for managing and organizing conversation threads.
- langbase_update_thread_message(content?: string, metadata?: object, threadId: string, messageId: string) — Tool to update an existing message in a conversation thread. Use when you need to modify the content or metadata of a specific message.

## Example prompts
- "What can I do in Langbase?"
- "Show me a summary of my Langbase account"

## Links
Docs: https://mcp.ai/docs/mcps/langbase
Website: https://mcp.ai/mcps/langbase