The Swarm integration for AI agents.
The Swarm integration for AI agents with secure authentication and server-side credential injection. Open Connector runs the OAuth, seals the token in an encrypted vault, and serves The Swarm tools to your agent over MCP or a typed API — credentials injected server-side, every call audited, nothing leaving your infrastructure. Open source (AGPL-3.0) and self-hostable.
Real The Swarm actions, managed and audited.
Your user connects The Swarm once; your agent can then use The Swarm to search profiles and companies, fetch social posts, map networks, manage team connector flows, and inspect credits usage — scoped to the OAuth permissions you grant and the tool allowlist you configure. Every action is least-privilege and written to a tamper-evident audit trail.
- 1
Your user grants The Swarm access once (OAuth) — the token lands in the vault.
- 2
Your agent calls a tool over MCP or the typed API; Open Connector injects the credential server-side.
- 3
Every routed call appends a hash-chained audit record — nothing leaves your infra.
Supported The Swarm tools.
26 tools are generated from the published The Swarm catalog. Descriptions are plain text; each action remains subject to its configured authentication and tool allowlist.
Showing 26 tools. All published catalog entries are included in this page's server-rendered HTML.
- Add connector(s) to the team
- Add one or more LinkedIn users as connectors to the team
- teams
- Aggregate profile field values
- Return distinct values for a single profile field matching a text query (e.g. autocomplete for locations or current job titles).
- profiles
- Create a child team
- Create a new child team under the authenticated team
- teams
- Fetch companies with corresponding data
- Fetch companies with corresponding data (e.g. tags)
- companies
- Fetch companies with corresponding data
- Fetch companies with corresponding data (e.g. tags)
- companies
- Fetch profiles with corresponding data
- Fetch profiles with corresponding data (e.g. connections, lists, tags)
- profiles
- Fetch profiles with corresponding data
- Fetch profiles with corresponding data (e.g. lists, tags)
- profiles
- Get company posts
- Fetch LinkedIn posts published by a company
- social
- Get credits usage
- Retrieve your team's current billing period credit usage. The API identifies your team from the API key, fetches the meter usage for the active billing period, and returns the number of credits already consumed.
- credits
- Get partner network mapping status
- Check the status of an async partner network mapping task
- network-mapper
- Network Mapper (Partner) Status
- Poll the status of a long-running Network Mapper (Partner) v3 task. Partner permission required.
- network-mapper
- Get post comments
- Fetch comments on a LinkedIn post
- social
- Get post reactions
- Fetch reactions on a LinkedIn post
- social
- Get post reshares
- Fetch reshares of a LinkedIn post
- social
- Get profile posts
- Fetch LinkedIn posts published by a person
- social
- Fetch a refreshed profile
- Fetch up-to-date profile data for a given LinkedIn URL slug
- profiles
- MCP endpoint
- Model Context Protocol (MCP) endpoint for AI assistant integrations
- mcp
- Find connected profiles (network mapper)
- Find connected profiles, with it's connection details
- network-mapper
- Get network mapper task status
- Check the status of a network mapper task started by POST /v2/profiles/network-mapper
- network-mapper
- Trigger partner network mapping
- Initiate network mapping for a given company. Returns data immediately if already mapped, or returns a task ID to poll for results.
- network-mapper
- Network Mapper (Partner) — v3
- Partner-permission endpoint for mapping connections across the partner network. Calls from API keys not tied to a team with the partner permission in Stripe return 403 Forbidden. Costs 1 credit per non-empty response.
- network-mapper
- Relationships
- Find connected profiles with their connection details. Renamed from Network Mapper in v3.
- network-mapper
- Search for companies ids
- Search for companies ids using the [ElasticSearch Query DSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html) format
- companies
- Search for companies ids
- Search for companies ids using the [ElasticSearch Query DSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html) format
- companies
- Search for profiles ids
- Search for profiles ids using the [ElasticSearch Query DSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html) format
- profiles
- Search for profiles ids
- Search for profiles ids using the [ElasticSearch Query DSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html) format
- profiles
The Swarm integration, answered
- How do AI agents use The Swarm through Open Connector?
- Your user connects The Swarm once with one of its cataloged authentication methods. Open Connector stores the credential in an encrypted vault and exposes The Swarm tools to your agent over MCP or a typed API, with credentials injected server-side on each call.
- Is this a The Swarm MCP server?
- Yes. Open Connector can serve The Swarm as a named MCP server with a scoped allowlist and a per-user connection URL, so any MCP client can call The Swarm actions with credentials injected server-side.
- Where do The Swarm credentials live?
- In your own infrastructure. Open Connector keeps credentials in its own vault and injects them at call time, so they never leave your environment.
Give your agents The Swarm — keep the keys.
Open source, self-hostable, with The Swarm credentials that never leave your infrastructure. Run it from source today.