JigsawStack MCP integration for AI agents.
Connect AI agents to JigsawStack through 6 structured actions, including check profanity, summarize text, and check spam. Review authentication, inputs, work…
- ACTION CONTRACTS
- 6
- 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 JigsawStack integration exposes
The JigsawStack Agent App exposes 6 provider-backed actions for ai, developer tools, and data work. Its current contract lets an authorized agent check text for profanity with jigsawstack and return detected occurrences, summarize text or a provider-accessible pdf document with jigsawstack, and check whether one string or an array of strings is spam with jigsawstack. 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 JigsawStack account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real JigsawStack capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
check_profanityREADCheck text for profanity with JigsawStack and return detected occurrences.
INPUTS: text / censorReplacement
summarize_textREVIEWSummarize text or a provider-accessible PDF document with JigsawStack.
INPUTS: text / url / fileStoreKey / type / maxPoints
check_spamREADCheck whether one string or an array of strings is spam with JigsawStack.
INPUTS: text
get_search_suggestionsREADGet JigsawStack search suggestions for a query prefix.
INPUTS: query
search_webREADSearch the web with JigsawStack AI Search and return normalized result data.
INPUTS: query / aiOverview / safeSearch / spellCheck / byoUrls
translate_textREVIEWTranslate one string or an array of strings with JigsawStack.
INPUTS: text / targetLanguage / currentLanguage
INPUT CONTRACTS
Know what the action needs before it runs.
check_profanity
textREQUIRED- The text to check for profanity.
censorReplacementOPTIONAL- The character or string to replace profanity with.
summarize_text
textOPTIONAL- The text content to summarize, up to 300000 characters.
urlOPTIONAL- A provider-accessible PDF document URL for JigsawStack to summarize.
fileStoreKeyOPTIONAL- A JigsawStack file-store key for a stored PDF document.
typeOPTIONAL- The summary format to return.
maxPointsOPTIONAL- The maximum number of bullet points to generate.
check_spam
textOPTIONAL- The text to check for spam.
get_search_suggestions
queryOPTIONAL- The query prefix to get suggestions for, up to 200 characters.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Check Profanity
Check text for profanity with JigsawStack and return detected occurrences. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
check_profanityVerify with Check Spam
Check whether one string or an array of strings is spam with JigsawStack. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
check_spamSAFETY BOUNDARY
Operate JigsawStack with explicit limits
- Authorize JigsawStack with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned JigsawStack data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in JigsawStack rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the JigsawStack task completed successfully.
CONNECTION MODEL
API key
JigsawStack secret API key sent in the x-api-key header. Create or manage keys from the Keys tab in the official dashboard: https://jigsawstack.com/dashboard.
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
- 4
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- 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 JigsawStack.