Beeminder MCP integration for AI agents.
Connect AI agents to Beeminder through 8 structured actions, including get goal, create datapoint, and delete datapoint. Review authentication, inputs, workf…
- 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 Beeminder integration exposes
The Beeminder Agent App exposes 8 provider-backed actions for productivity and finance work. Its current contract lets an authorized agent read one beeminder goal, optionally including its datapoints, create one datapoint on a beeminder goal, and delete one beeminder datapoint by id. 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 Beeminder account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Beeminder capabilities.
Showing 8 of 8 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_goalREADRead one Beeminder goal, optionally including its datapoints.
INPUTS: username / goal_slug / datapoints
create_datapointWRITECreate one datapoint on a Beeminder goal.
INPUTS: username / goal_slug / value / timestamp / daystamp
delete_datapointHIGH IMPACTDelete one Beeminder datapoint by ID.
INPUTS: username / goal_slug / datapoint_id
get_userREADGet Beeminder user information, including goals and optional diff-based goal details.
INPUTS: username / associations / diff_since / skinny / datapoints_count
list_archived_goalsREADList archived Beeminder goals for a user.
INPUTS: username
list_datapointsREADList datapoints for one Beeminder goal with optional count or page parameters.
INPUTS: username / goal_slug / count / page / per
list_goalsREADList active Beeminder goals for a user.
INPUTS: username
update_datapointWRITEUpdate one Beeminder datapoint by ID.
INPUTS: username / goal_slug / datapoint_id / value / timestamp
INPUT CONTRACTS
Know what the action needs before it runs.
get_goal
usernameREQUIRED- The Beeminder username, or me for the authenticated user.
goal_slugREQUIRED- The Beeminder goal slug.
datapointsOPTIONAL- Whether Beeminder should include datapoints in the goal response.
create_datapoint
usernameREQUIRED- The Beeminder username, or me for the authenticated user.
goal_slugREQUIRED- The Beeminder goal slug.
valueREQUIRED- The datapoint value.
timestampOPTIONAL- A Unix timestamp in seconds.
daystampOPTIONAL- The datapoint daystamp in YYYYMMDD format.
delete_datapoint
usernameREQUIRED- The Beeminder username, or me for the authenticated user.
goal_slugREQUIRED- The Beeminder goal slug.
datapoint_idREQUIRED- The Beeminder datapoint ID.
get_user
usernameOPTIONAL- The Beeminder username, or me for the authenticated user.
associationsOPTIONAL- Whether to include full goal and datapoint objects instead of only goal slugs.
diff_sinceOPTIONAL- A Unix timestamp in seconds.
skinnyOPTIONAL- Whether to return slimmer goal attributes and only each goal's latest datapoint with diff_since.
datapoints_countOPTIONAL- Number of the most recently added datapoints to include for each goal.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Goal
Read one Beeminder goal, optionally including its datapoints. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_goalControl Create Datapoint
Create one datapoint on a Beeminder goal. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_datapointVerify with Get User
Get Beeminder user information, including goals and optional diff-based goal details. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_userSAFETY BOUNDARY
Operate Beeminder with explicit limits
- Authorize Beeminder with API key and grant only the provider access required by the selected actions.
- 3 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_datapoint` 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 Beeminder rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Beeminder task completed successfully.
CONNECTION MODEL
API key
Beeminder personal auth token passed as auth_token. View or create it after signing in at https://www.beeminder.com/api/v1/auth_token.json.
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
- 5
- WRITE SIGNALS
- 2
- HIGH IMPACT
- 1
- 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 Beeminder.