Langbase MCP integration
Creates and reconfigures pipes, manages retrieval memories and threads, and pulls execution traces when a run needs debugging.
20actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Create thread
Lyro starts new conversation threads for each customer issue. Your support team keeps interactions organized and easy to reference later.
List thread messages
Lyro retrieves full conversation history with a customer. Your team understands context instantly and avoids repeating questions or solutions.
Append thread messages
Lyro continues conversations with follow-up messages to customers. Your team maintains seamless dialogues without breaking context or losing thread history.
How businesses use Langbase + Lyro
Each card is one request a support team gets, and the Langbase actions Lyro runs to close it.
Stand up a pipe and adjust its configuration
Lyro creates a pipe and returns the object with its API key and URL, reads back the configuration of an existing one, and changes model settings, prompts, tools, or attached memory in place.
Create a New PipeGet Pipe DetailsUpdate an Existing PipeManage the memory a pipe retrieves from
Lyro creates a memory for a new corpus, lists what already exists so nobody duplicates one, and pages through the documents inside a memory with their metadata when retrieval looks wrong.
Create MemoryList MemoriesList Documents in MemoryKeep conversation threads organised
Lyro opens a thread for a new session, appends messages as the exchange continues, and lists or edits what is in one when a message needs correcting or the metadata needs updating.
Create ThreadAppend Thread MessagesList Thread MessagesDebug a run that did not behave
Lyro pulls the execution traces for a specific primitive, checks whether the API itself is healthy before anyone rewrites a prompt, and confirms the model in use is one Langbase supports.
List Execution TracesCheck API HealthList Available Models
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Langbase actions it has and picks the ones a request needs.
- 01
Connect Langbase
Authorize the Langbase account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Langbase actions that close it and chains as many as the request needs.
- 03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Everything else about Langbase
Setup, permissions, and the limits of what Lyro can do inside Langbase.
Only configure and inspect it. No action in this toolkit executes a pipe. Create a new pipe returns the pipe object including its API key and URL, and that endpoint is what your application calls at run time, while Lyro handles setup, updates, memory, and debugging around it.
Every action available in Langbase
All 20 actions your agent can call on Langbase, straight from the live MCP connection.
Append thread messages
Add new messages to an existing conversation thread.
Check API health
Check the health status of the Langbase API service.
Split content into chunks
Split content into smaller chunks.
Create thread
Create a new conversation thread.
Delete thread
Delete a thread that is no longer needed to manage conversation history.
Delete thread message
Delete a specific message from a conversation thread.
List documents in memory
List documents in a specific memory.
Get pipe details
Retrieve details of a specific pipe by owner and name.
Get thread details
Retrieve details of a specific conversation thread.
List available models
Get available AI models supported by Langbase.
List thread messages
List all messages in a conversation thread.
List execution traces
Get execution traces for debugging and monitoring pipe runs.
Create memory
Create a new memory.
Delete memory
Delete a specific memory.
List memories
List all memory objects.
Create a new pipe
Create a new pipe.
List all pipes
List all pipes.
Update an existing pipe
Update an existing pipe's configuration on Langbase.
Update thread metadata
Update an existing thread's metadata.
Update thread message
Update an existing message in a conversation thread.
The tools Langbase sits next to
Same connection, same setup. Pick the next one your team already uses.
Chatbotkit
Pulls bot transcripts and usage figures, clones blueprints into new bots, resyncs training datasets, and wires up messaging channels.
Flowiseai
Clones and updates chatflows, rewrites document store chunks behind bad answers, reads collected leads and feedback, and health-checks the instance.
Linkup
Searches the live web with date and domain filters, returns sourced answers or structured JSON, and fetches a page as markdown.
Promptmate.io
Runs a template against supplied data, reports app job status and results, and manages the webhook subscriptions behind those jobs.
Studio By Ai21 Labs
Creates and edits AI21 assistants, validates the Python behind their plans, indexes site content, and runs an assistant on request.
Zep
Writes thread messages into a user graph, retrieves the context relevant to the conversation, searches it semantically, and deletes data on request.
Ready to connect Langbase?
Authorize the account and your agent has all 20 actions from the first conversation.