The Swarm MCP integration for AI agents.
Connect AI agents to The Swarm through 5 structured actions, including get credit usage, fetch companies, and fetch profiles. Review authentication, inputs…
- 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 The Swarm integration exposes
The The Swarm Agent App exposes 5 provider-backed actions for data and social work. Its current contract lets an authorized agent get the current the swarm api credit usage for the authenticated team, fetch the swarm company records by company ids or linkedin company identifiers, and fetch the swarm profile records by profile ids or linkedin identifiers. 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 The Swarm account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real The Swarm capabilities.
Showing 5 of 5 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_credit_usageREADGet the current The Swarm API credit usage for the authenticated team.
fetch_companiesREVIEWFetch The Swarm company records by company IDs or LinkedIn company identifiers.
INPUTS: ids / linkedinNames / linkedinIds / fields
fetch_profilesREVIEWFetch The Swarm profile records by profile IDs or LinkedIn identifiers.
INPUTS: ids / linkedinNames / linkedinIds / linkedinEntityIds / fields
search_companiesREADSearch The Swarm companies with an Elasticsearch Query DSL query and return company IDs.
INPUTS: query / limit / paginationToken / stablePagination
search_profilesREADSearch The Swarm profiles with an Elasticsearch Query DSL query and return profile IDs.
INPUTS: query / limit / paginationToken / stablePagination / inNetworkOnly
INPUT CONTRACTS
Know what the action needs before it runs.
fetch_companies
idsOPTIONAL- The Swarm company IDs to fetch.
linkedinNamesOPTIONAL- LinkedIn company slugs to fetch.
linkedinIdsOPTIONAL- LinkedIn numeric identifiers accepted by The Swarm.
fieldsOPTIONAL- Company sections to include in the response.
fetch_profiles
idsOPTIONAL- The Swarm profile IDs to fetch.
linkedinNamesOPTIONAL- LinkedIn profile URL slugs to fetch.
linkedinIdsOPTIONAL- LinkedIn numeric identifiers accepted by The Swarm.
linkedinEntityIdsOPTIONAL- LinkedIn alphanumeric entity IDs to fetch.
fieldsOPTIONAL- Profile sections to include in the response.
search_companies
queryREQUIRED- The Elasticsearch Query DSL query object sent to The Swarm.
limitOPTIONAL- The maximum number of results to return. Use exactly 1000 when stablePagination is true.
paginationTokenOPTIONAL- The pagination token returned by a previous The Swarm search response.
stablePaginationOPTIONAL- Whether The Swarm should keep pagination stable while retrieving large result sets.
search_profiles
queryREQUIRED- The Elasticsearch Query DSL query object sent to The Swarm.
limitOPTIONAL- The maximum number of results to return. Use exactly 1000 when stablePagination is true.
paginationTokenOPTIONAL- The pagination token returned by a previous The Swarm search response.
stablePaginationOPTIONAL- Whether The Swarm should keep pagination stable while retrieving large result sets.
inNetworkOnlyOPTIONAL- Whether to restrict results to profiles connected to your team's network.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Credit Usage
Get the current The Swarm API credit usage for the authenticated team. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_credit_usageVerify with Search Companies
Search The Swarm companies with an Elasticsearch Query DSL query and return company IDs. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
search_companiesSAFETY BOUNDARY
Operate The Swarm with explicit limits
- Authorize The Swarm with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned The Swarm 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 The Swarm rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the The Swarm task completed successfully.
CONNECTION MODEL
API key
The Swarm API key sent with the x-api-key header. Generate it from the Team Settings API page.
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
- 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 The Swarm.