---
title: Connectors
description: How connectors and connections give agents scoped access to external tools.
---

A connector links a project to an external tool or service. The agent
calls it as a tool. Beeuni brokers each call, so the sandbox never holds the
connector credential.

You declare most connectors in `beeuni.yaml`. See the
[manifest reference](/docs/project/manifest) for every field. Beeuni declares
channel and computer connectors when you connect a chat platform or a
machine.

## Browse and add a connector

Open **Connectors** to browse the managed catalog. Its default list contains
managed-provider toolkits connectable with provider-managed authentication or an
enabled custom authentication configuration. It does not require an existing
connection in your project. A toolkit that needs an unverified custom OAuth
configuration stays hidden until that configuration can be verified.

For direct sources, enable **Connectors API Discover** in the project's feature
flags, then select **API / MCP** on the same page. Enabling the flag does not
replace the managed default. The direct catalog groups published OpenAPI, MCP,
GraphQL, Postman, and other API surfaces. Select a card, choose a published
surface, and complete its connection form. Documentation-only surfaces open the
provider's documentation; they are not presented as a ready-to-connect template.
Use **Add → Manual** for a raw API or a schema that the catalog does not contain.
Direct discovery also works without a configured managed provider.

## Connectors, connections, and accounts

A connector is the agent-facing reach package: a declared capability (which
actions, how to reach the service). It is not a role, and it holds no Beeuni
permission: an agent reaches a connector only when its manifest grant lists the
slug and the role verdict allows the call. See
[One vocabulary, two bindings](/docs/accounts#one-vocabulary-two-bindings). A
connector contains:

- a project-unique slug
- a display name
- a provider app
- connector policies

A connection is one **account** — one authorized identity — for the
connector: a credential, an OAuth grant, or an API key. A connector can hold
several accounts side by side. Every account uses the connector's policies.
Each account's `owner_type` decides who may run a call as it:

- `project` — a **shared** account. Reachable by anyone the connector is
  granted to, human or service account (agent, trigger).
- `member` — a **private** account, owned by one project member
  (`owner_id`). Reachable only by that member, and only in a **private**
  session. A service account (an agent or a trigger acting unattended) can
  never run as a member's private account.

Multiple connectors can reference the same provider app. Use separate
connectors when one app needs different policies.

### Install a connector

1. Open **Customize → Connectors**.
2. Find the app on the **All** tab.
3. Click **Install** on its card and choose who the account is for:
   - **Only you** — only you can use it, in your private sessions.
   - **Everyone in the project** — every project member's sessions can use it.
4. Sign in to the app when its window opens. An app that uses an API key asks for the key instead.

Beeuni opens the connector's page when the install finishes.

A member who cannot manage the project's connections sees one **Install** button. It installs a private account.

When the catalog lists an MCP server for an app, **Install** uses it. To use another surface, such as the REST API, open the app's page and pick it under **Ways to connect**.

### Manage a connector

Each connector has its own page with three tabs. **Tools** and **Settings** show only to someone who can change the project's connectors.

- **Accounts** — the logins this connector can run as. **Add account** asks only who the account is for. To limit a shared account to specific people or groups, use **Share** on its row.
- **Tools** — which tools the agent may call, and which need approval.
- **Settings** — the connection details, and **Remove connector**.

Installing an app that is already in the project adds an account to the existing connector. It does not create a second connector.

When an agent needs an account, it posts a **Connect** card in the chat. The
card opens a dialog, with the name the agent suggests already filled in
and the audience it asked for preselected. Beeuni creates a new account, never
re-authorizes an existing one, and tells the agent the new account's name so it
can run calls as that account.

### Choose who can use a shared account

A shared account is usable by everyone in the project until you narrow it.
Select **Share** on the account card. The dialog is the same **Grant access**
dialog used for agents. It lists who can use the account now, and you add:

- **Everyone in the project** — the default.
- **Groups** — every member of each group.
- **People** — one member each. Pick only yourself to keep the account to you.
- **Agents** — every session of that agent, triggers and shared sessions
  included. Anyone who can run the agent can use the account through it.

Nothing changes until you select **Save**. Removing the last group or person
makes the account usable by everyone again; the dialog states the result before
you save.

A narrowed account follows the private-account rules, with its audience in
place of the owner:

- A person in the audience can use it, and only in a private session.
- An agent in the audience can use it in every one of its sessions.
- Any other agent, and a trigger of any other agent, never uses it.
- A session that binds it cannot be shared, unless the account is shared with
  that session's own agent.
- Only a person changes who can use an account. An agent session gets `403`.

A person outside the audience does not see the account. A person who manages
the project's connections still sees it, marked **Not shared with you**, so
they can change who can use it.

### Share your own private account

Your own **Only you** account has a **Share** button too. Sharing it turns it
into a shared account for the people and groups you pick (you stay on it unless
you remove yourself), or for everyone in the project. From then on it is a
shared account: people who manage the project's connections can manage it too.

- Sharing needs `project.connector.connections.manage`, the same right as
  adding a shared account. Without it the button is disabled and says why.
- Beeuni writes the grants first and turns the account shared in one update,
  so it is never open to the whole project in between.
- A shared account of the same name on the connector blocks it (`409`): rename
  one first.

```text
POST /projects/{projectId}/connections/{connectionId}/share
     {"principals": [{"principal_type": "group", "principal_id": "<group-id>"}]}
```

An empty `principals` list shares it with everyone. From the CLI:
`beeuni connectors connections share <connection-id> --group <group-id>`
(also `--user <email|id>`, repeatable, or `--everyone`).

Each audience entry is one `connection` object assignment in the grant store:

```text
POST   /accounts/{accountId}/iam/assignments
       {"principal_type": "group", "principal_id": "<group-id>",
        "role_key": "agent-user", "scope_type": "project", "scope_id": "<project-id>",
        "object_type": "connection", "object_id": "<connection-id>"}
DELETE /accounts/{accountId}/iam/assignments/{assignmentId}
```

From the CLI, the same writes are:

```bash
beeuni access grant --group <group-id> --connection <connection-id>
beeuni access grant --everyone --connection <connection-id>
beeuni access revoke <assignment-id>
beeuni connectors connections ls   # the WHO CAN USE column
```

- `principal_type` is `user`, `group`, or `project` (everyone in the project;
  `principal_id` is the project id).
- Granting or revoking one needs `project.connector.connections.manage`.
- Only a shared account can be narrowed through these grants. A private account,
  or an id that is not a connection in this project, answers `404`; share your
  own private account with the `share` route above instead.
- `GET /projects/{projectId}/connections` returns each shared account's grants
  in `shared_with`, and `usable: false` on an account the caller sees only to
  manage it. The session picker offers only usable accounts.

### Which identity an account acts as

An account's `label` is a name chosen before authorization. It does not say
which login was used. `connected_as` does: the email, login, or display name
the provider reports for the authorized account.

- Beeuni reads it when a managed authorization finalizes: first the connected
  account's display name, then the toolkit's "who am I" tool (Gmail, Google
  Calendar, Google Drive, Linear, GitHub, Slack, Notion, Outlook, Microsoft
  Teams, HubSpot, Jira, Asana, Figma, Airtable, Salesforce, Trello, Dropbox,
  Calendly). Google Docs and Google Sheets expose no such tool, so their
  `connected_as` stays `null`.
- An account still carrying a default label (`Private connection`,
  `Project connection`, or the connector name) is relabelled to that identity.
  A label someone chose is never replaced.
- The connect page shows "Connected as …" the moment the account lands, so a
  shared account authorized with a personal login is visible right away.
- `connected_as` is on every connection (`GET /projects/{projectId}/connections`),
  on the accounts list, in `beeuni connectors accounts <slug>` and
  `beeuni connectors connections ls` (the `CONNECTED AS` column), and on the
  account rows in **Customize → Connectors**.

### Rename an account

Rename an account without re-authorizing it:

```text
PUT /projects/{projectId}/connections/{connectionId}/label   {"label": "Support inbox"}
beeuni connectors connections rename <connection-id> Support inbox
```

In the dashboard, open the connector, then **⋯ → Rename** on the account row.
Only the label changes. The authorized account, its owner, its default flag,
and the provider state stay as they are. The same gate applies as for
disconnect: your own private account, or `project.connector.connections.manage`
for a shared one.

A rename is refused with `400` for `me`, `project`, or a UUID-shaped label,
because `--account` resolves those before labels. It is refused with `409` when
another account of the same owner already has that label, compared
case-insensitively.

### Connect a different account

A connect link for a slot that already holds an active account does not
re-authorize it. The provider reuses the account, and the connect page shows
**Already connected**. To use a different login, add a new account on the
connector, make it the default, then disconnect the old one.

A call that names no account resolves to the caller's own default private
account first, then the project's default shared account. Every call result
echoes which account it ran as (`account: { connection_id, label,
owner_type }`), so the transcript always shows the identity a tool call used.
List the accounts a connector can be called as, default first, with
`GET /connectors/projects/{projectId}/connectors/{slug}/accounts`.

> **Warning**
>
> `authorization_strategy` (`project` | `user`) was a connector-level MODE that
> made project-owned and member-owned accounts mutually exclusive — a
> `user`-strategy connector could offer no shared account, so it had no connect
> flow anywhere a service account could use. It is deprecated: the manifest and
> `PUT .../authorization-strategy` still accept it and answer without error, but
> nothing reads it any more. `owner_type` on each connection is the whole access
> rule now.

## Providers

A connector uses one provider type:

- **composio** — managed OAuth for supported SaaS apps
- **pipedream** — legacy managed OAuth, kept for rollback only
- **openapi**, **postman**, **graphql**, **http** — direct API connectors
- **mcp** — a remote MCP server over HTTP or SSE
- **channel** — a chat platform connection
- **computer** — each member's connected machine is one account

See [Slack and channels](/docs/connect/slack) and
[Computers](/docs/connect/computers) for the managed provider flows.

<a id="apps-that-need-your-own-oauth-app"></a>

### App availability

The connector catalogue shows the apps currently available to connect. Some apps require additional authentication setup and may not appear until that setup is complete.

## Authentication and policy

A connection authenticates with:

- Managed OAuth, a channel install, or a native OAuth2 grant
- an API key or token entered through the dashboard

Beeuni encrypts connection data and resolves it server-side for each tool
call. The agent requests an action. Beeuni attaches the credential, checks the
agent grant and connector-connection policy, calls the external API, and returns
the result.

Connector policies belong to the connector. A connection cannot
override them. Project guardrails apply above connector-connection policies.

By default, an unmatched connector action runs without approval. Set
`policy.default_mode: risk` to require approval for unmatched write and
destructive actions. Set `sensitive: true` to make `require_approval` the
connector's unmatched-action default, including reads. Explicit project
or connector-connection rules still apply first.

### Approve one governed call

`require_approval` creates one decision for one connector call. The Connector
returns `202 pending_approval` with `approval_url`, `approval_summary`, and
`execution_id`. It does not keep an HTTP request open.

Share `approval_url` with any teammate. The URL identifies the request but does
not grant authority. The page requires a signed-in Beeuni account. Beeuni then
verifies that the account can access and approve actions in the project.

The approval page shows the redacted parameters that the connector will receive.
A caller can add `approval_context` (CLI: `--reason`) to describe the effect.
Use it when the parameters are only references: `gmail.send_draft` takes a
draft id, so the agent states the recipient, subject, and body. The page shows
this text as the agent's description, not verified. The parameters remain the
evidence. Beeuni never sends `approval_context` to the provider.

Approve or deny the call once. Add an optional message to the decision. The
message goes back to the agent with the decision, so a deny can say what to do
instead.

Every pending call also appears in **Review → Needs you** for the project. Open
**Review** from the sidebar; its count shows how many items wait for you. A
call opens in the same approval view as its approval link, so you see the
connector, the parameters, and the agent's description before you decide.

When the call comes from a Slack or Teams session, Beeuni posts an approval
card in that thread. The card shows the agent's description, the parameters,
and **Approve** / **Deny**. In Slack, **Reply…** opens a box for a message to
the agent; in Teams, the card has the message box inline. Only a project
manager or the person who started the session can decide. A decision made
anywhere (the thread, Beeuni, or the approval page) replaces the card's
buttons with the outcome, and the agent continues in the same thread. Beeuni sends the decision back into the session
through a durable callback. An approval applies only to the exact request
digest. A changed recipient, subject, body, channel, URL, or other parameter
requires a new decision.

Open the session's **Audit** panel to use the same parameter view. Historical
entries remain read-only. There is no session-wide approval option. Use an
explicit `always_run` policy only when a connector action must run unattended.

## Connect with OAuth

1. **Open the project's Connectors page**

    Open the project. Select **Connectors**, then select the app.

2. **Select the account scope**

    Select **Project** for a shared account, reachable by anyone the connector is
    granted to. Select **User** for a private account, owned by you and reachable
    only by you, only in a private session.

3. **Complete authorization**

    Complete the OAuth flow. Beeuni stores the connected account as a connection.

## Connect an MCP server that uses OAuth 2.1

Beeuni implements the MCP authorization specification. Open the connector,
select **Add credential**, then select the **OAuth 2.0** tab. Beeuni probes the
server and reads its metadata:

1. The unauthenticated probe returns `401` with
   `WWW-Authenticate: Bearer resource_metadata="…"`.
2. Beeuni reads the protected resource metadata (RFC 9728) at that URL, or at
   `/.well-known/oauth-protected-resource`.
3. Beeuni reads the authorization server metadata (RFC 8414 or OpenID Connect
   discovery) for the first authorization server the resource names.

When that server advertises `registration_endpoint`, Beeuni registers itself as
an OAuth client (RFC 7591) and shows one button: **Connect &lt;server&gt;**. You
create no application, and you copy no client ID or secret. Beeuni then runs
Authorization Code with PKCE (S256) and binds the token to the server with the
`resource` parameter (RFC 8707).

Register this redirect URI when a server needs one in advance:

```text
https://api.beeuni.ai/v1/connectors/oauth2/callback
```

When the server publishes endpoints but no `registration_endpoint`, Beeuni
prefills the authorization URL, token URL, and scopes. Enter the client ID of an
app you create with that provider. When the server publishes no metadata, enter
every field.

Beeuni keeps the MCP session: it runs `initialize` and
`notifications/initialized` on demand, then sends `Mcp-Session-Id` on later
calls. A server that answers without a session never sees the handshake.

Beeuni binds each connection to the authorization server that issued it. When
the callback carries an `iss` parameter (RFC 9207), Beeuni rejects it unless it
matches the recorded issuer — a code minted by a different server is refused
before it is redeemed.

### Authorize from the CLI

The dashboard is one way to run this flow, not the only one. Declare the
connector in `beeuni.yaml`, then authorize it from a terminal or an agent
session:

```yaml
connectors:
  - slug: read-ai
    name: Read AI
    provider: mcp
    url: 'https://api.read.ai/mcp'
    auth:
      type: bearer
```

```text
beeuni connectors authorize read-ai --json
```

The command creates the connection, runs the discovery chain, registers Beeuni
as a client when the server supports RFC 7591, and returns the URL to approve:

```json
{
  "connection_id": "7b1a16b2-...",
  "registered": true,
  "scopes": ["openid", "offline_access", "mcp:execute", "meeting:read"],
  "authorization_url": "https://authn.read.ai/oauth2/auth?response_type=code&...",
  "expires_at": "2026-08-19T14:48:26.345Z"
}
```

An agent returns `authorization_url` to the person it is working with. After
they approve, the agent confirms:

```text
beeuni connectors authorize read-ai --status
```

The command exits non-zero while the status is `error`. Use `--scope` to narrow
what is requested. Use `--client-id` and `--client-secret` for a server that
does not support dynamic client registration.

Beeuni refetches the connector's tool catalog as soon as authorization
completes, so the connector leaves the `error` state without a manual sync.

## Connect a direct API with OAuth2

Direct connectors support:

- client credentials
- authorization code with PKCE
- device authorization
- dynamic client registration (RFC 7591)

For client credentials, enter the token URL, client ID, scopes, and client
secret. You can use `client_secret_basic`, `client_secret_post`,
`client_secret_jwt`, or `private_key_jwt` token-endpoint authentication.

For authorization code, enter the authorization URL and token URL. For device
authorization, enter the device-authorization URL and token URL. An RFC 8414
discovery URL can provide these endpoints.

Beeuni encrypts the OAuth2 configuration and tokens. It refreshes access tokens
before expiry, and it stores each rotated refresh token. Revoking the connection
blocks the next connector call.

For Microsoft Graph, use:

```text
https://login.microsoftonline.com/{tenant_id}/oauth2/v2.0/token
https://graph.microsoft.com/.default
```

For direct SharePoint REST calls, use the SharePoint resource scope:

```text
https://{tenant}.sharepoint.com/.default
```

## Connect with an API key

1. **Declare the connector**

    ```yaml
    connectors:
      - slug: stripe-read
        name: Stripe read access
        provider: openapi
        spec: 'https://raw.githubusercontent.com/stripe/openapi/master/openapi/spec3.json'
        auth:
          type: bearer
        policies:
          - match: 'get_*'
            action: always_run
          - match: '*'
            action: block
    ```

    The manifest still accepts an `authorization_strategy` key for backward
    compatibility. Beeuni ignores it: set the owner (shared or private) per
    connection instead, when you add its credential.

2. **Merge the change request**

    Beeuni reads the manifest from the default branch. The connector becomes
    active after the change request merges.

3. **Add the connection**

    Open the connector and set its credential. Beeuni stores the value
    encrypted. It does not write the value to the manifest.

## Grant an agent access

Add the connector slug to the agent's `connectors` field:

```yaml
agents:
  release-bot:
    connectors: [stripe-read]
```

Omit `connectors`, and the agent gets `none`. Merge the change before it takes
effect.

`connectors_required` is deprecated. The manifest still accepts it, but
nothing reads it: a session is never refused at create time for a connector
with no usable account. A session-create refusal for a missing connector was
unreachable in practice — a private-only connector had no shared account to
offer, so the refusal had no remedy the caller could act on. The gate is now
the connector **call**: an agent granted `stripe-read` can start its turn
immediately, and only a call that actually needs the connector is denied (see
[When a call is denied](#when-a-call-is-denied)) — with a remedy attached.

## Select an account

Two independent ways to pick which account a call runs as — pin one for the
whole session, or name one on a single call.

### Pin a session-wide default

A session can override the connector's default account for every call it
makes:

```json
{
  "connector_bindings": {
    "stripe-read": {
      "connection_id": "00000000-0000-4000-8000-000000000000"
    }
  }
}
```

The binding key is the connector slug. The value is an account (connection)
this session's caller is entitled to reach.

Use `GET /projects/{projectId}/sessions/{sessionId}/scope` to read the
effective binding. Use `PUT` on the same path to replace it. The replacement
applies to the next tool call without restarting the session.

### Name an account on one call

List the accounts a connector can be called as — default first — with:

```text
GET /connectors/projects/{projectId}/connectors/{slug}/accounts
```

```json
{
  "connector": "stripe-read",
  "accounts": [
    { "connection_id": "...", "label": "Shared workspace", "owner_type": "project", "is_default": true, "connected_as": "billing@example.com" },
    { "connection_id": "...", "label": "My Stripe", "owner_type": "member", "is_default": false, "connected_as": null }
  ]
}
```

Then name one on the call, by connection id or by label (case-insensitive), or
with the two selector words `me` (your own default private account) and
`project` (the project's default shared account):

```text
beeuni connectors call stripe-read get_balance '{}' --account me
beeuni connectors call stripe-read get_balance '{}' --account "Shared workspace"
```

A call that names no account resolves to the caller's own default private
account first, then the project's default shared account — unchanged from
before a connector could hold more than one account. A named account that does
not resolve is **denied**, never silently substituted onto a different one
(see [When a call is denied](#when-a-call-is-denied)). Every successful call
result echoes which account it ran as: `account: { connection_id, label,
owner_type }`.

## Use a connector in a session

Inside a session, use the Connector CLI:

```text
beeuni connectors ls
beeuni connectors accounts stripe-read
beeuni connectors call stripe-read <action> '<json-args>' [--account <id|label|me|project>]
```

`connectors` lists the connectors in scope. `accounts` lists the accounts this
caller may call `stripe-read` as — default first, shared before private within
each group. `call` runs one action, as the named `--account` or, when omitted,
the same default resolution used before a connector could hold more than one
account.

### Large results

A list or search call can return more than a model can read: tool output
above ~50 KB is truncated. Save the result to a file and work through it with
code:

```text
beeuni connectors call linear graphql.issues '{"first":250}' --out /workspace/output/issues.json
# → { "ok": true, "account": …, "saved_to": "/workspace/output/issues.json",
#     "bytes": 93037, "shape": { "issues": { "nodes": "array(250) of {id,title,…}",
#     "pageInfo": { "hasNextPage": true, "endCursor": "…" } } } }
jq '.data.issues.nodes[] | {id, title}' /workspace/output/issues.json
```

`--out` writes the full JSON result, creating parent directories. Stdout gets
the call envelope without `data`, plus `saved_to`, `bytes`, and `shape`: the
outline of `data` (keys, array lengths, and every `pageInfo`). The exit code is
unchanged.

### Attach files

A call never carries file bytes in its arguments. Stage the file, then put its
reference in the arguments. The gateway reads the bytes server-side and writes
them into the request.

```text
beeuni connectors call microsoft-graph.sendmail @mail.json \
  --attach /workspace/artifacts/report.pdf
```

`--attach` stages the file and appends a reference to the action's attachments
array. The array is found in the action's input schema: `attachments` for the
Email channel, `body.message.attachments` for Microsoft Graph `sendMail`. Name
it with `--attach-path body.message.attachments` when the schema is unusual.
Large JSON arguments go in a file (`@mail.json`) or on stdin (`-`).

To place a file yourself, stage it first:

```text
beeuni connectors upload /workspace/artifacts/report.pdf --connector microsoft-graph
# → { "attachment_id": "…", "ref": { "$beeuni_attachment": "…" }, … }
```

Put `ref` anywhere in the arguments. The gateway replaces it by position:

| Position of `ref` | Replaced with |
| --- | --- |
| An element of an attachments array whose items are objects | The provider's attachment item. The item schema selects the shape: Microsoft Graph `fileAttachment` (`name` + `contentBytes` or `@odata.type`), Postmark (`Name` + `Content`), Mailjet (`Filename` + `Base64Content`), SendGrid and Resend (`filename` + `content`), Brevo (`name` + `content`). Any other item shape is refused with `attachment_item_shape_unknown`. |
| A string field, e.g. `contentBytes` or a GitHub file `content` | The file's base64. |
| The Email channel's `attachments[]` | A signed download URL for the Email provider. |

Rules:

- Files come from `/workspace/output`, `/workspace/artifacts`,
  `/workspace/reports`, or `/workspace/deliverables`. Symbolic links and hard
  links are refused. Copy a file there first.
- One call carries up to 20 files and 25 MiB in total. The upstream API can
  set a lower limit: Microsoft Graph documents 3 MB as the largest file one
  `sendMail` request can attach.
- A staged file is private to the session that staged it, used once, and
  deleted after 24 hours. A failed call releases it for a retry.
- The audit record, the approval preview, and the model see only the
  reference, never the bytes. An upstream error that echoes the file has the
  base64 removed.
- Managed connectors do not accept staged files
  (`connector_attachments_unsupported`).

The MCP server offers the same flow: `call` takes `attachment_files` (and an
optional `attachment_path`), and `upload_attachment` returns a `ref`. The SDK
equivalent is `connectors.uploadAttachment(bytes, { filename, contentType,
connector })`, which returns `ref`.

### Call results

`POST /connectors/projects/{projectId}/call` answers one JSON object. These
fields are the same for every binding (OpenAPI, HTTP, MCP, GraphQL, `composio`,
`pipedream`, computers):

| Field | On | Value |
| --- | --- | --- |
| `data` | 200 | The raw upstream answer, unchanged. |
| `output` | 200 | The payload without the binding's envelope: `composio` `data.result`, MCP `result.structuredContent ?? result.content`, GraphQL `data.data`. Absent when it equals `data` (OpenAPI, HTTP, Postman, channel, `pipedream` and computer calls), so the body carries the payload once: read `output ?? data`. The SDK fills it in. |
| `binding` | 200, 500, 429, 503 | The binding that ran the call: `openapi`, `http`, `mcp`, `graphql`, `composio`, `pipedream`, `pipedream_proxy`, `postman`, `tunnel`. `null` on an error before the action resolved. |
| `upstream_status` | 200, 500, 429, 503 | The upstream HTTP status. `null` when no upstream answered (a timeout, a refused request, a computer). `composio` and `pipedream` report a provider failure inside a 200, so Beeuni sets `502` for it (`400` for a rejected Linear query, `429` for a rate limit). |
| `upstream_error` | 200 | Present when the upstream reported a failure inside a 2xx answer: an MCP tool result with `isError: true` or a JSON-RPC error, or GraphQL `errors` with no data. The call still counts as run: `ok` stays `true`. |
| `retry_after_seconds` | 429, 503 | The upstream's `Retry-After`, in seconds, when it sent one. The response also carries the `Retry-After` header. |

The HTTP status of a failed call:

- An upstream `429` answers `429`. An upstream `503` answers `503`. Wait
  `retry_after_seconds` (or back off) and call again.
- Every other upstream failure answers `500` with the cause in `reason`.
- An upstream answer larger than 64 MiB answers `500` with
  `reason: "upstream_response_too_large: …"`. Beeuni stops reading at the
  limit. Ask for a smaller page or a filter.
- An upstream that does not answer within the deadline answers `500` with
  `reason: "upstream_timeout: …"`. The deadline is 60 seconds
  by default. Set a client
  timeout above it, so the gateway always answers first.

A connector call is not idempotent. Beeuni does not deduplicate a repeated
call. After `upstream_timeout` or a client-side abort, the call may have run
upstream: check its effect before you repeat a write (a sent email, a created
record).

### Typed calls from code

`beeuni connectors types` writes a TypeScript declaration file for every
action you can call. Each action gets its argument type from its input schema
and its result type from its output schema. The result type describes the
call's `output` field.

```sh
beeuni connectors types --out src/beeuni-connectors.d.ts
beeuni connectors types --connector linear,github --out src/beeuni-connectors.d.ts
```

Include the file in your `tsconfig.json`. Then call through `callAction`:

```ts
import { createBeeuni } from '@beeuni/sdk';

const connectors = createBeeuni({ backendUrl, getToken }).project(projectId).connectors;
const result = await connectors.callAction('linear', 'list_issues', { team: 'CORE' });
if (result.ok) console.log(result.output?.issues.length);
```

The connector handle reads the same file, and `run` returns the typed output
itself or throws a typed error (see Connectors from code):

```ts
const issues = await createBeeuni({ backendUrl, getToken })
  .project(projectId)
  .connector('linear')
  .run('list_issues', { team: 'CORE' });
```

`callAction(slug, action, args, options)` sends the same request as
`call('<slug>.<action>', args, options)` and returns the same result. Only
the types differ: a missing or unknown argument is a compile error, and
`output` has the generated type. An action that is not in the file accepts
any object and returns `output: unknown`.

- OpenAPI, HTTP, MCP and GraphQL connectors publish an output schema when
  their source declares one. A GraphQL result is typed as an object.
- Managed connectors publish no output schema. Their
  result is `unknown`. The CLI names them after it writes the file.
- Each `$defs` entry becomes one named type (`BeeuniConnectorDef<n>_<name>`),
  so a recursive schema stays finite. A schema that cannot compile (a union
  that contains itself) or whose types pass 256 KB for one action becomes
  `unknown`.
- Re-run the command after you add a connector or it syncs a new version.
- The catalog returns output schemas only on request:
  `GET /connectors/projects/{projectId}/catalog?include_output_schemas=true`
  adds `outputSchema` to each action (`null` when none is stored).

### When a call is denied

A denied call answers `{ ok: false, status: "denied", reason, hint }`. `reason` is a stable code; `hint` says what to do.

| `reason` | HTTP | Meaning | Also in the body |
| --- | --- | --- | --- |
| `connector_not_assigned` | 403 | The running agent's `connectors:` grant in `beeuni.yaml` does not include this connector. | `agent`, `granted` (the list or `"all"`), `manifest_revision` and `manifest_commit` (the manifest the grant came from). |
| `connector_not_connected` | 403 | No usable account for this call. Either the connector has no account at all for this caller (no stored credential, or the app was never authorized — `beeuni connectors ls` shows it as `needs_auth`), or `--account` named one that did not resolve. | `connect_url` — a hosted link to authorize an account, when the caller can mint one — when nothing is connected. `requested_account` and `available_accounts` — the name that did not resolve and the names that were — when `--account` named one. |
| `connector_disabled` | 403 | The connector is declared but disabled. | — |
| `connector_not_found` | 404 | No connector with this slug is declared in the project. | — |
| `action_not_found` | 404 | The connector has no such action. | — |

`connect_url` is the whole remedy for an unconnected connector: a session is
never refused up front for one (see [Grant an agent
access](#grant-an-agent-access)), so the denial itself carries the fix. The
agent surfaces the link verbatim; the web transcript renders it as a one-click
Connect button. The link authorizes a private account for the human who opens
it by default — connecting a shared account is an explicit choice
(`beeuni connectors connect stripe-read --owner project`, gated on
`project.connector.write`).

The channel connector that created a session (Slack, Teams, email) is always callable from that session, whatever the agent's grant says, so the agent can always report in the thread it was asked from.

A session's grant follows `beeuni.yaml`: a change to the running agent's `connectors:` (including `beeuni connectors add --apply`) applies on the next call. The grant records which manifest blob and commit it came from; a read that would replace it from the same blob is confirmed by a second read first, and a read from an older commit never replaces it.

Slack and Microsoft Teams connect from the dashboard the same way as OAuth apps. Connecting Slack writes a `channel` connector to `beeuni.yaml` for you. See [Slack & channels](/docs/connect/slack).