Placid MCP integration for AI agents.
Connect AI agents to Placid through 5 structured actions, including get image, create image, and delete image. Review authentication, inputs, workflows, and…
- ACTION CONTRACTS
- 5
- 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 Placid integration exposes
The Placid Agent App exposes 5 provider-backed actions for design & media and developer tools work. Its current contract lets an authorized agent get the current placid image generation status for one image identifier and return the finished image url when available, queue one placid image generation request from a template uuid and dynamic layer payload, then return the image handle for polling, and delete one placid image request by identifier and return whether the delete succeeded. 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 Placid account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Placid capabilities.
Showing 5 of 5 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_imageREADGet the current Placid image generation status for one image identifier and return the finished image URL when available.
INPUTS: image_id
create_imageWRITEQueue one Placid image generation request from a template UUID and dynamic layer payload, then return the image handle for polling.
INPUTS: template_uuid / webhook_success / create_now / passthrough / errors
delete_imageHIGH IMPACTDelete one Placid image request by identifier and return whether the delete succeeded.
INPUTS: image_id
get_templateREADGet one Placid template by UUID and return its dynamic layer metadata for downstream image generation.
INPUTS: template_uuid
list_templatesREADList Placid templates for the connected project with optional collection, title, tag, ordering, or next-page URL filters.
INPUTS: collection_id / title_filter / tag / order_by / page_url
INPUT CONTRACTS
Know what the action needs before it runs.
get_image
image_idREQUIRED- The Placid image identifier returned by create_image.
create_image
template_uuidREQUIRED- The Placid template UUID to render.
webhook_successOPTIONAL- Optional webhook URL that Placid should call after the image is generated.
create_nowOPTIONAL- Whether Placid should try to render the image immediately instead of queueing it.
passthroughOPTIONALerrorsOPTIONAL- Optional error handling flags forwarded to Placid.
delete_image
image_idREQUIRED- The Placid image identifier to delete.
get_template
template_uuidREQUIRED- The Placid template UUID to retrieve.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Image
Get the current Placid image generation status for one image identifier and return the finished image URL when available. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_imageControl Create Image
Queue one Placid image generation request from a template UUID and dynamic layer payload, then return the image handle for polling. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_imageVerify with Get Template
Get one Placid template by UUID and return its dynamic layer metadata for downstream image generation. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_templateSAFETY BOUNDARY
Operate Placid with explicit limits
- Authorize Placid with API key and grant only the provider access required by the selected actions.
- 2 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_image` 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 Placid rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Placid task completed successfully.
CONNECTION MODEL
API key
Placid project API token used with the Authorization Bearer header. Sign in, open your project, then copy the token from API Tokens: https://placid.app/app/projects
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
- 3
- WRITE SIGNALS
- 1
- 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 Placid.