Integration

Botpress integration

Botpress Cloud is a platform for building AI chatbots and agents. Through the API a workflow can read a bot's conversations, messages, users, participants and events, update or delete conversations and users, manage the bot's Tables (create tables, find, insert, update, upsert and delete rows), and manage its Files: list, search indexed documents in natural language, read passages, edit metadata, delete files and manage knowledge bases. Sending messages, creating conversations, states, actions, workflows and integrations go through the bot runtime and are not exposed, nor is file upload (it needs a second request to a signed URL), table import or export, or the Admin API (workspaces, bots, integrations). Authentication is a Personal Access Token (Profile Settings) or a Bot Access Key sent as a Bearer token, plus the bot's ID in the x-bot-id header.

Connect Botpress How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Botpress.Built from the 39 Botpress tools below, on the connection you add once.

What you can do with Botpress

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Table, 5 operations

create_tableCreate tablePOSTInitiates the creation of a new table based on the provided schema, excluding system-managed fields like IDs and timestamps.
delete_tableDelete tableDELETEPermanently deletes a table and all its associated data from the system. Use with caution, as this action cannot be undone.
get_tableGet tableGETRetrieves detailed information about a specific table, identified by its name or unique identifier.
list_tablesList tablesGETLists the bot's tables with their ID, name, column schema, key column and tags. Use a table name or ID as table in the row tools.
update_tableUpdate tablePUTUpdates the schema or the name of an existing table.

Conversation, 4 operations

delete_conversationDelete conversationDELETEPermanently deletes a Conversation. It cannot be undone. Also immediately deletes corresponding Messages.
get_conversationGet conversationGETRetrieves the Conversation object for a valid identifier.
list_conversationsList conversationsGETLists the bot's conversations, most recent first, filtered by tags, participants, integration, channel, dates or message count. Paginate with nextToken from meta.nextToken.
update_conversationUpdate conversationPUTUpdate a Conversation object by setting the values of the parameters passed. Any parameters not provided will be left unchanged.

File, 4 operations

delete_fileDelete fileDELETEDeletes a file of the bot, by ID or key. This cannot be undone.
get_fileGet fileGETReturns one file by ID or key: size, content type, upload status, indexing flag, tags, metadata and its URL.
list_filesList filesGETLists the bot's files with their key, size, content type, upload status, indexing flag, tags and URL, filtered by tags, ids or indexing state. Paginate with nextToken from meta.nextToken.
update_file_metadataUpdate file metadataPUTUpdates a file's metadata, tags, access policies or expiry without changing its content. Keys left out are kept; set a key to null to delete it.

Knowledge base, 4 operations

create_knowledge_baseCreate knowledge basePOSTCreates a knowledge base for grouping files.
delete_knowledge_baseDelete knowledge baseDELETEDeletes a knowledge base.
list_knowledge_basesList knowledge basesGETLists the bot's knowledge bases (groups of files the bot answers from).
update_knowledge_baseUpdate knowledge basePUTUpdates a knowledge base.

User, 4 operations

delete_userDelete userDELETEPermanently deletes a User. It cannot be undone.
get_userGet userGETRetrieves the User object for a valid identifier.
list_usersList usersGETLists the bot's users (people who talked to it), most recent first, optionally only the participants of one conversationId. Paginate with nextToken from meta.nextToken.
update_userUpdate userPUTUpdate a User object by setting the values of the parameters passed. Any parameters not provided will be left unchanged.

Row, 3 operations

create_table_rowsCreate table rowsPOSTInserts one or multiple new rows into the specified table.
get_table_rowGet table rowGETFetches a specific row from a table using the row's unique identifier.
update_table_rowsUpdate table rowsPUTUpdates specified rows in a table, allowing partial success with detailed feedback on errors.

Event, 2 operations

get_eventGet eventGETRetrieves the Event object for a valid identifiers.
list_eventsList eventsGETLists the bot's events, most recent first, filtered by type, conversation, user, message, workflow or status. Paginate with nextToken from meta.nextToken.

Message, 2 operations

get_messageGet messageGETRetrieves the Message object for a valid identifier.
list_messagesList messagesGETLists the bot's messages, most recent first, optionally for one conversationId, tags or a date range. Paginate with nextToken from meta.nextToken.

Participant, 2 operations

get_participantGet participantGETRetrieves a Participant from a Conversation.
list_participantsList participantsGETRetrieves a list of Participant for a given Conversation.

Column, 1 operation

rename_table_columnRename table columnPUTRenames an existing column within a table to better reflect its content or usage. The operation targets a specific table and requires the current and new column names.

Delete, 1 operation

delete_table_rowsDelete table rowsPOSTAllows selective deletion of rows or complete clearance of a table.

Duplicate, 1 operation

duplicate_tableDuplicate tablePOSTDuplicates the table schema & content

Find, 1 operation

find_table_rowsFind table rowsPOSTEnables the search and filtering of rows within a table based on specific criteria. This operation supports complex queries for advanced data manipulation and retrieval.

Passage, 1 operation

list_file_passagesList file passagesGETLists the text passages an indexed file was split into, in order. Paginate with nextToken from meta.nextToken.

Search, 1 operation

search_filesSearch filesGETSearches the bot's indexed files in natural language (query) and returns the best matching text passages with their file, for RAG answers. Filter files with tags.

Tag, 1 operation

list_file_tagsList file tagsGETLists the tag names used on the bot's files. Read a tag's values with list_file_tag_values.

Upsert, 1 operation

upsert_table_rowsUpsert table rowsPOSTInserts or updates rows based on a key. If a row exists, it is updated; otherwise, a new row is created.

Value, 1 operation

list_file_tag_valuesList file tag valuesGETLists the distinct values used for one file tag.

Use Botpress from Claude Code, Cursor or Codex

Connect Botpress in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Botpress operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Botpress

Create your workspace
Sign up free. Nothing to install.
Connect Botpress once
Add your Botpress connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.