Chattermill MCP integration for AI agents.
Connect AI agents to Chattermill through 22 structured actions, including get attribute, create response, and delete response. Review authentication, inputs…
- ACTION CONTRACTS
- 22
- 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 Chattermill integration exposes
The Chattermill Agent App exposes 22 provider-backed actions for data and marketing work. Its current contract lets an authorized agent get a chattermill attribute by id, create a response in a chattermill project, and permanently delete a chattermill response 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 Chattermill account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Chattermill capabilities.
Showing 12 of 22 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_attributeREADGet a Chattermill attribute by ID.
INPUTS: project / id
create_responseWRITECreate a response in a Chattermill project.
INPUTS: project / response
delete_responseHIGH IMPACTPermanently delete a Chattermill response by ID.
INPUTS: project / responseId
get_categoryREADGet a Chattermill category by ID.
INPUTS: project / id
get_data_sourceREADGet a Chattermill data source by ID.
INPUTS: project / id
get_data_typeREADGet a Chattermill data type by ID.
INPUTS: project / id
get_metricREADGet a Chattermill metric value for a project.
INPUTS: project / type
get_projectREADGet a Chattermill project by project ID.
INPUTS: id
get_responseREADGet a single Chattermill response by ID.
INPUTS: project / id
get_tagREADGet a Chattermill tag by ID.
INPUTS: project / id
get_themeREADGet a Chattermill theme by ID.
INPUTS: project / id
list_attributesREADList attributes for a Chattermill project.
INPUTS: project
INPUT CONTRACTS
Know what the action needs before it runs.
get_attribute
projectREQUIRED- Chattermill project key or identifier used in the API path.
idREQUIRED- Chattermill resource identifier used in the API path.
create_response
projectREQUIRED- Chattermill project key or identifier used in the API path.
responseREQUIRED- Raw Chattermill object.
delete_response
projectREQUIRED- Chattermill project key or identifier used in the API path.
responseIdREQUIRED- Chattermill resource identifier used in the API path.
get_category
projectREQUIRED- Chattermill project key or identifier used in the API path.
idREQUIRED- Chattermill resource identifier used in the API path.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Attribute
Get a Chattermill attribute 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_attributeControl Create Response
Create a response in a Chattermill project. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_responseVerify with Get Category
Get a Chattermill category by ID. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_categorySAFETY BOUNDARY
Operate Chattermill with explicit limits
- Authorize Chattermill 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_response` 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 Chattermill rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Chattermill task completed successfully.
CONNECTION MODEL
API key
Chattermill API key sent as a Bearer token in the Authorization header. Create or copy it from the Chattermill API settings page: https://app.chattermill.com/settings/api.
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
- 19
- 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 Chattermill.