AgentMail MCP integration for AI agents.
Connect AI agents to AgentMail through 102 structured actions, including batch get messages, create api key, delete api key, and forward message. Review auth…
- ACTION CONTRACTS
- 102
- 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 AgentMail integration exposes
The AgentMail Agent App exposes 102 provider-backed actions for communication and productivity work. Its current contract lets an authorized agent fetch multiple messages from a specific agentmail inbox by message id, create an agentmail api key, and delete an agentmail api key. 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 AgentMail account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real AgentMail capabilities.
Showing 12 of 102 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
batch_get_messagesREADFetch multiple messages from a specific AgentMail inbox by message ID.
INPUTS: inbox_id / message_ids
create_api_keyWRITECreate an AgentMail API key.
INPUTS: name / permissions
delete_api_keyHIGH IMPACTDelete an AgentMail API key.
INPUTS: api_key_id
forward_messageREVIEWForward a specific AgentMail message.
INPUTS: inbox_id / message_id / labels / reply_to / to
create_domainWRITECreate an AgentMail domain.
INPUTS: domain / feedback_enabled
create_draftWRITECreate a draft in a specific AgentMail inbox.
INPUTS: inbox_id / labels / reply_to / to / cc
create_inboxWRITECreate a new AgentMail inbox.
INPUTS: username / domain / display_name / client_id / metadata
create_inbox_api_keyWRITECreate an API key scoped to a specific AgentMail inbox.
INPUTS: inbox_id / name / permissions
create_inbox_list_entryREADCreate an allow or block list entry scoped to a specific AgentMail inbox.
INPUTS: inbox_id / direction / type / entry / reason
create_list_entryREADCreate a global AgentMail allow or block list entry.
INPUTS: direction / type / entry / reason
create_podWRITECreate an AgentMail pod.
INPUTS: name / client_id
create_pod_api_keyWRITECreate an API key scoped to a specific AgentMail pod.
INPUTS: pod_id / name / permissions
INPUT CONTRACTS
Know what the action needs before it runs.
batch_get_messages
inbox_idOPTIONAL- The AgentMail inbox identifier.
message_idsOPTIONAL- Message IDs to fetch.
create_api_key
nameOPTIONAL- Name of the API key.
permissionsOPTIONAL- Granular AgentMail API key permissions.
delete_api_key
api_key_idOPTIONAL- The AgentMail API key identifier.
forward_message
inbox_idREQUIRED- The AgentMail inbox identifier.
message_idREQUIRED- The AgentMail message identifier.
labelsOPTIONAL- Labels used to filter or apply to a record.
reply_toOPTIONAL- Email address or email address list.
toOPTIONAL- Email address or email address list.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Batch Get Messages
Fetch multiple messages from a specific AgentMail inbox by message ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
batch_get_messagesControl Create Api Key
Create an AgentMail API key. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_api_keyVerify with Create Api Key
Create an AgentMail API key. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
create_api_keySAFETY BOUNDARY
Operate AgentMail with explicit limits
- Authorize AgentMail with API key and grant only the provider access required by the selected actions.
- 40 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_api_key`, `delete_domain`, and `delete_draft` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in AgentMail rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the AgentMail task completed successfully.
CONNECTION MODEL
API key
AgentMail API key used with the Authorization Bearer header. Create it in the AgentMail Console API Keys section.
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
- 58
- WRITE SIGNALS
- 24
- HIGH IMPACT
- 16
- REVIEW SIGNALS
- 4
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 AgentMail.