mymind MCP integration for AI agents.
Connect AI agents to mymind through 28 structured actions, including get object, add object tags, delete link, and pin object. Review authentication, inputs…
- ACTION CONTRACTS
- 28
- AUTHENTICATION
- 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 mymind integration exposes
The mymind Agent App exposes 28 provider-backed actions for productivity work. Its current contract lets an authorized agent get one mymind object with its title, summary, tags, spaces, notes, and source, add tags to a mymind object, and delete a manual link. a wiki-style link cannot be deleted directly; remove the reference from the source note instead. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses 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 mymind account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real mymind capabilities.
Showing 12 of 28 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_objectREADGet one mymind object with its title, summary, tags, spaces, notes, and source.
INPUTS: objectId
add_object_tagsWRITEAdd tags to a mymind object.
INPUTS: objectId / tags
delete_linkHIGH IMPACTDelete a manual link. A wiki-style link cannot be deleted directly; remove the reference from the source note instead.
INPUTS: linkId
pin_objectREVIEWPin a mymind object, optionally into a specific slot.
INPUTS: objectId / position
add_object_to_spaceWRITEPut a mymind object into a space.
INPUTS: spaceId / objectId
create_linkWRITELink one mymind object to another.
INPUTS: sourceId / targetId
create_noteWRITECreate a note in a mind from markdown content.
INPUTS: content / title / tags / spaceIds
create_object_noteWRITEAttach a markdown note to a mymind object.
INPUTS: objectId / content
create_spaceWRITECreate a mymind space, optionally seeded with objects.
INPUTS: name / color / objectIds
delete_objectHIGH IMPACTSoft-delete a mymind object. Use restore_object to bring it back.
INPUTS: objectId
delete_object_noteHIGH IMPACTDelete a note attached to a mymind object.
INPUTS: objectId / noteId
delete_spaceHIGH IMPACTDelete a mymind space. The objects it held stay in the mind.
INPUTS: spaceId
INPUT CONTRACTS
Know what the action needs before it runs.
get_object
objectIdOPTIONAL- The mymind object identifier.
add_object_tags
objectIdOPTIONAL- The mymind object identifier.
tagsOPTIONAL- Tag names.
delete_link
linkIdOPTIONAL- The link identifier.
pin_object
objectIdREQUIRED- The mymind object identifier.
positionOPTIONAL- The zero-based slot to pin the object into.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Object
Get one mymind object with its title, summary, tags, spaces, notes, and source. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_objectControl Add Object Tags
Add tags to a mymind object. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
add_object_tagsVerify with Add Object Tags
Add tags to a mymind object. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
add_object_tagsSAFETY BOUNDARY
Operate mymind with explicit limits
- Authorize mymind with Custom credentials and grant only the provider access required by the selected actions.
- 17 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_link`, `delete_object`, and `delete_object_note` as high-impact operations and require an explicit approval boundary.
- The sampled contract declares provider scopes including `full_access` and `read_only`; verify the complete action contract before execution.
- After a call, inspect the structured result and execution record before reporting that the mymind task completed successfully.
CONNECTION MODEL
Custom credentials
mymind uses Custom credentials. Connection requirements and availability are determined by the provider and the Working Machines deployment.
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
- 8
- WRITE SIGNALS
- 11
- HIGH IMPACT
- 6
- REVIEW SIGNALS
- 3
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 mymind.