Crisp MCP integration for AI agents.
Connect AI agents to Crisp through 5 structured actions, including get conversation, send text message, and get website. Review authentication, inputs, workf…
- ACTION CONTRACTS
- 5
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Crisp integration exposes
The Crisp Agent App exposes 5 provider-backed actions for communication and marketing work. Its current contract lets an authorized agent retrieve one crisp conversation by session id, send an operator text message to a crisp conversation, and retrieve the crisp website connected to the configured token. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Crisp account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Crisp capabilities.
Showing 5 of 5 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_conversationREADRetrieve one Crisp conversation by session ID.
INPUTS: sessionId
send_text_messageWRITESend an operator text message to a Crisp conversation.
INPUTS: sessionId / content / origin
get_websiteREADRetrieve the Crisp website connected to the configured token.
list_conversation_messagesREADList messages in a Crisp conversation.
INPUTS: sessionId / timestampBefore / timestampAfter / timestampAround
list_conversationsREADList conversations for the connected Crisp website.
INPUTS: pageNumber / perPage / searchQuery / includeEmpty / filterUnread
INPUT CONTRACTS
Know what the action needs before it runs.
get_conversation
sessionIdOPTIONAL- The Crisp conversation session identifier.
send_text_message
sessionIdREQUIRED- The Crisp conversation session identifier.
contentREQUIRED- The text content to send to the Crisp conversation.
originOPTIONAL- The Crisp message origin to use for the text message.
list_conversation_messages
sessionIdREQUIRED- The Crisp conversation session identifier.
timestampBeforeOPTIONAL- A Crisp timestamp in milliseconds.
timestampAfterOPTIONAL- A Crisp timestamp in milliseconds.
timestampAroundOPTIONAL- A Crisp timestamp in milliseconds.
list_conversations
pageNumberOPTIONAL- The 1-based conversation page number to request from Crisp.
perPageOPTIONAL- The number of conversations to request per page.
searchQueryOPTIONAL- Search text used by Crisp conversation search.
includeEmptyOPTIONAL- Whether Crisp should include empty conversations.
filterUnreadOPTIONAL- Whether Crisp should return only unread conversations.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Conversation
Retrieve one Crisp conversation by session ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_conversationControl Send Text Message
Send an operator text message to a Crisp conversation. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
send_text_messageVerify with Get Website
Retrieve the Crisp website connected to the configured token. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_websiteSAFETY BOUNDARY
Operate Crisp with explicit limits
- Authorize Crisp with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Crisp rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Crisp task completed successfully.
CONNECTION MODEL
API key
Crisp token key used as the Basic Auth password. For website tokens, generate the key in Crisp Dashboard > Settings > Workspace Settings > Advanced configuration > API Token: https://app.crisp.chat/
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 4
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Crisp.