WeCom Bot MCP integration for AI agents.

Connect AI agents to WeCom Bot through 54 structured actions, including change todo user status, add schedule attendees, cancel meeting, and call tool. Revie…

ACTION CONTRACTS
54
AUTHENTICATION
API key + Custom credentials
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the WeCom Bot integration exposes

The WeCom Bot Agent App exposes 54 provider-backed actions for communication and productivity work. Its current contract lets an authorized agent change one follower's status on a wecom todo, add attendees to a wecom schedule, and cancel a scheduled wecom meeting. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key and Custom credentials. 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 WeCom Bot account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real WeCom Bot capabilities.

Showing 12 of 54 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

change_todo_user_statusREAD

Change one follower's status on a WeCom todo.

INPUTS: todoId / userId / userStatus

add_schedule_attendeesWRITE

Add attendees to a WeCom schedule.

INPUTS: scheduleId / userIds

cancel_meetingHIGH IMPACT

Cancel a scheduled WeCom meeting.

INPUTS: meetingId

call_toolREVIEW

Call a dynamically discovered WeCom MCP tool that does not have a curated action yet.

INPUTS: category / toolName / arguments

cancel_scheduleHIGH IMPACT

Cancel a WeCom schedule.

INPUTS: scheduleId

check_availabilityREAD

Read busy time slots for up to 10 WeCom members.

INPUTS: userIds / startTime / endTime

create_docWRITE

Create an empty WeCom document, online sheet, or smart sheet.

INPUTS: documentType / name

create_meetingWRITE

Create a scheduled WeCom meeting.

INPUTS: title / startTime / durationSeconds / description / location

create_scheduleWRITE

Create a WeCom schedule with attendees and reminders.

INPUTS: startTime / endTime / summary / description / location

create_todoWRITE

Create a WeCom todo with followers, deadline, and reminders.

INPUTS: content / followers / endTime / reminderTypes

del_schedule_attendeesWRITE

Remove attendees from a WeCom schedule.

INPUTS: scheduleId / userIds

delete_todoHIGH IMPACT

Delete a WeCom todo.

INPUTS: todoId

INPUT CONTRACTS

Know what the action needs before it runs.

change_todo_user_status

todoIdOPTIONAL
The todo ID.
userIdOPTIONAL
A WeCom user ID returned by a contact lookup.
userStatusOPTIONAL
The follower status: `0` rejected, `1` accepted, or `2` completed.

add_schedule_attendees

scheduleIdOPTIONAL
The schedule ID.
userIdsOPTIONAL
The WeCom user IDs to add.

cancel_meeting

meetingIdOPTIONAL
The meeting ID.

call_tool

categoryOPTIONAL
The official WeCom MCP business category.
toolNameOPTIONAL
The exact tool name returned by `list_tools`.
argumentsOPTIONAL
The arguments validated against the tool's current input schema.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Change Todo User Status

Change one follower's status on a WeCom todo. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

change_todo_user_status

Control Add Schedule Attendees

Add attendees to a WeCom schedule. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.

add_schedule_attendees

Verify with Check Availability

Read busy time slots for up to 10 WeCom members. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

check_availability

SAFETY BOUNDARY

Operate WeCom Bot with explicit limits

  • Authorize WeCom Bot with API key and Custom credentials and grant only the provider access required by the selected actions.
  • 32 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
  • Treat `cancel_meeting`, `cancel_schedule`, and `delete_todo` 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 WeCom Bot rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the WeCom Bot task completed successfully.

CONNECTION MODEL

API key + Custom credentials

Paste the key query value from the WeCom group bot webhook URL. The full webhook URL is also accepted. Create a group bot and copy its webhook URL from https://developer.work.weixin.qq.com/document/path/91770.

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
20
WRITE SIGNALS
25
HIGH IMPACT
7
REVIEW SIGNALS
2

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 WeCom Bot.

Official WeCom Bot website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS