CommPeak MCP integration for AI agents.
Connect AI agents to CommPeak through 8 structured actions, including get stream, send sms, and get stream token. Review authentication, inputs, workflows, a…
- ACTION CONTRACTS
- 8
- 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 CommPeak integration exposes
The CommPeak Agent App exposes 8 provider-backed actions for communication and marketing work. Its current contract lets an authorized agent retrieve one textpeak stream by id, send one or more sms messages through a textpeak stream, fetching the stream token with the api key before sending, and retrieve the stream token used to call textpeak messaging endpoints. 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 CommPeak account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real CommPeak capabilities.
Showing 8 of 8 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_streamREADRetrieve one TextPeak stream by ID.
INPUTS: streamId
send_smsWRITESend one or more SMS messages through a TextPeak stream, fetching the stream token with the API key before sending.
INPUTS: streamId / sender / messages
get_stream_tokenREADRetrieve the stream token used to call TextPeak messaging endpoints.
INPUTS: streamId
list_domainsREADList TextPeak domains in the CommPeak account.
INPUTS: page / itemsPerPage
list_incoming_messagesREADList incoming TextPeak messages with optional filters.
INPUTS: streamId / sender / destination / startDate / endDate
list_messagesREADList outgoing TextPeak messages with optional filters.
INPUTS: type / status / streamId / phone / startDate
list_sendersREADList TextPeak sender identities in the CommPeak account.
INPUTS: page / itemsPerPage
list_streamsREADList TextPeak streams in the CommPeak account.
INPUTS: page / itemsPerPage
INPUT CONTRACTS
Know what the action needs before it runs.
get_stream
streamIdREQUIRED- The numeric TextPeak stream ID.
send_sms
streamIdREQUIRED- The numeric TextPeak stream ID.
senderOPTIONAL- The top-level sender applied to every message. Omit it when each message has its own sender.
messagesREQUIRED- The SMS messages to send. TextPeak supports up to 250 per request.
get_stream_token
streamIdREQUIRED- The numeric TextPeak stream ID.
list_domains
pageOPTIONAL- The 1-based page number to request.
itemsPerPageOPTIONAL- The number of items to request per page.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Stream
Retrieve one TextPeak stream by ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_streamControl Send Sms
Send one or more SMS messages through a TextPeak stream, fetching the stream token with the API key before sending. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
send_smsVerify with Get Stream Token
Retrieve the stream token used to call TextPeak messaging endpoints. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_stream_tokenSAFETY BOUNDARY
Operate CommPeak with explicit limits
- Authorize CommPeak 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 CommPeak rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the CommPeak task completed successfully.
CONNECTION MODEL
API key
CommPeak TextPeak API key sent as the raw Authorization header value. Create or view API keys in TextPeak Settings > API Keys: https://docs.commpeak.com/docs/api-keys
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
- 7
- 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 CommPeak.