Connections
A connection is one system your agents may reach: an MCP server, the credentials it is called with, and a mode for each tool it offers.
Adding one
- 1
Pick it from the catalog, or paste a URL
The catalog carries the endpoint and auth style for the systems we have checked. Anything else works too. Paste the MCP server URL and Tier Two probes it for its transport, its auth requirement, and its tool list.
- 2
Choose how it authenticates
Either each person signs in with their own account, or the workspace provisions one shared key. This is the single most consequential choice on the page. See below.
- 3
Tier Two pins the tools
The tool list is read once and stored, so a server that adds a tool tomorrow does not silently widen what your agents can do. Refresh tools when you want the new ones, and review the diff.
- 4
Apply a posture
Recommended is pre-selected: reads run, writes wait for a person. You can change any single tool afterwards.
Who the call runs as
| Auth | The call runs as | Use it when |
|---|---|---|
| Sign in with your account | the person using the agent | everyone has their own seat downstream, and you want that system's own permissions to keep applying |
| Shared key | one workspace credential, forwarded server-side | seats are scarce or setup per person is not worth it. Tier Two's modes become the only limit, so keep them tight |
| Personal API key | the person's own key for that system | the system has no OAuth but people do have individual keys |
What we have checked
The catalog records how each entry was verified (a live probe, the vendor’s own documentation, or a secondary source) and the date. Entries we have not been able to verify say so in the product rather than quietly failing later.
| System | Auth | Verified |
|---|---|---|
| PostHog | Sign in with your account | docs · 2026-09-07 |
| Linear | Sign in with your account | docs · 2026-09-02 |
| Sentry | Sign in with your account | docs · 2026-09-02 |
| GitHub | Sign in with your account | docs · 2026-09-02 |
| Notion | Sign in with your account | docs · 2026-09-02 |
| Atlassian | Sign in with your account | docs · 2026-09-02 |
| Stripe | Sign in with your account | docs · 2026-09-02 |
| Cloudflare | Sign in with your account | docs · 2026-09-02 |
| Supabase | Sign in with your account | docs · 2026-09-02 |
| Neon | Sign in with your account | docs · 2026-09-02 |
| Figma | Sign in with your account | docs · 2026-09-02 |
| Metabase | Shared key | probe · 2026-09-02 |
| Hugging Face | Personal API key | docs · 2026-09-02 |
| Context7 | Personal API key | docs · 2026-09-02 |
| Vercel | Sign in with your account | not verified yet |
| HubSpot | Sign in with your account | not verified yet |
Naming and slugs
- A connection’s slug is what the agent sees:
linear__create_issuecomes from the sluglinear. - Renaming the display name is safe; changing a slug changes every tool name with it.
- Disabling a connection hides its tools from every agent immediately, without deleting its history.