# clariBI (remote · claribi.com)

AI business intelligence: sign up, ingest data, run analyses, generate reports from any MCP client.

- Trust score: 65/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `claribi.com`: 65/100 (this document), [markdown](https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1.md), [page](https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1)
- remote · `claribi.com`: 25/100, [markdown](https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1-sse.md), [page](https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1-sse)

## Channel facts

- Endpoint: `https://claribi.com/mcp/v1/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 14 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3157 tokens (~121/item across 26 items; 26 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-claribi-mcp-server https://claribi.com/mcp/v1/
```

### Codex

```toml
[mcp_servers.com-claribi-mcp-server]
url = "https://claribi.com/mcp/v1/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-claribi-mcp-server": {
      "type": "remote",
      "url": "https://claribi.com/mcp/v1/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-claribi-mcp-server --url https://claribi.com/mcp/v1/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-claribi-mcp-server:
    url: "https://claribi.com/mcp/v1/"
```

### Other

```json
{
  "mcpServers": {
    "com-claribi-mcp-server": {
      "type": "http",
      "url": "https://claribi.com/mcp/v1/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 63, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 60)

First indexed and scored.

## MCP tools (26)

### `check_integration_status` (~72 tokens)

Poll an OAuth handoff initiated by request_oauth_integration_url. Returns the current status (pending, connected, failed, expired) and, when connected, the data_source_id you can pass to run_analysis.

Input parameters:

- `handoff_id` (string, required): The id returned by request_oauth_integration_url.

Output parameters:

- `completed_at` (string|null)
- `connection_id` (string|null)
- `created_at` (string|null)
- `data_source_id` (string|null): The created data source, present once status is "connected".
- `error` (string|null): Failure reason when status is "failed".
- `handoff_id` (string)
- `integration_type` (string)
- `provider` (string)
- `status` (string): One of pending, connected, failed, expired.

### `check_pricing` (~61 tokens)

List clariBI subscription tiers with prices, AI credits, data source limits, user limits, and headline features. No authentication required.

Input parameters:

- `tier` (string): Optional. Return only this tier (free, trial, lite, starter, professional, enterprise).

Output parameters:

- `billing_url` (string)
- `currency` (string): ISO currency code, always "USD".
- `tiers` (array)

### `create_checkout_session` (~70 tokens)

Create a Stripe Checkout URL the user can open in a browser to upgrade their clariBI subscription. Payment cannot happen inside the LLM; this tool returns a URL.

Input parameters:

- `billing_period` (string): Billing cadence for the checkout. Defaults to monthly.
- `tier` (string, required): Target subscription tier.

Output parameters:

- `billing_period` (string): monthly or yearly.
- `checkout_url` (string): Stripe Checkout URL. Open in a browser to complete payment.
- `session_id` (string): Stripe Checkout Session id.
- `tier` (string)

### `create_forecast` (~632 tokens)

Bind a forecast to a metric in your workspace. Stores the configuration, sets up the schedule, and resolves the source binding immediately so a bad source_id or metric_path errors out before any credits are spent. Run the forecast with run_forecast.

Input parameters:

- `aggregation` (string): How multiple raw points falling into the same bucket are combined. Auto picks sum for additive metrics, mean otherwise. Use Mean for rates (CTR, conversion, latency).
- `description` (string)
- `granularity` (string): Bucket size for the time series. Hourly requires an hourly data source; the engine refuses to fabricate hourly buckets from daily data.
- `horizon_days` (integer): How many BUCKETS ahead to project. The per-granularity cap applies: hourly 168, daily 90, weekly 52, monthly 24, quarterly 8, annual 5. The field name is "_days" for backwards compatibility — it coun…
- `include_anomalies` (boolean)
- `include_changepoints` (boolean)
- `include_correlations` (boolean)
- `method_override` (string): Force a specific forecasting method instead of auto-selecting via walk-forward CV. Valid names: naive, seasonal_naive, moving_average, drift, linear_trend, ar_p, holt_winters, holt_winters_multiplica…
- `metric_path` (string, required): Dot-path to the numeric column. For data_source: the metric key (e.g. "revenue"). For goal: "value" or "percentage". For report: the path inside the insights JSON. For dashboard: "widget_id:metric_na…
- `name` (string, required)
- `narration_enabled` (boolean): When true, every completed run gets an AI-generated narrative attached (summary, highlights, risks, recommendations, methodology). Costs 1-2 extra AI credits per run.
- `non_negative` (boolean): When true, point + lower band clamped at zero. Omit to let the engine heuristic decide (via non_negative_auto=true).
- `non_negative_auto` (boolean): When true (default), the backend heuristic owns non_negative and re-evaluates per run based on the metric path. Set false alongside non_negative to lock the choice.
- `schedule_day_of_month` (integer)
- `schedule_day_of_week` (integer)
- `schedule_frequency` (string): How often the forecast re-runs. Manual schedules only run when called explicitly via run_forecast.
- `source_id` (string, required): UUID of the report, dashboard, goal, or data source.
- `source_type` (string, required): Which clariBI artifact the metric lives on. Most callers should start with data_source for raw connector metrics or goal to forecast a tracked KPI.
- `transform` (string): Series transform applied before fitting. Log helps revenue/traffic series with growing variance. Auto detects when log is beneficial; none forces raw scale.

Output parameters:

- `granularity` (string)
- `horizon_days` (integer)
- `id` (string)
- `metric_label` (string)
- `name` (string)
- `next_run_at` (string|null)
- `schedule_frequency` (string)
- `web_url` (string)

### `generate_report` (~115 tokens)

Create a new generated report in your clariBI organization. Returns the report id you can poll via get_report, plus a download URL once status reaches "completed".

Input parameters:

- `output_format` (string): Output format. Must match one of ``GeneratedReport.OUTPUT_FORMATS``.
- `template_id` (string): Optional registry ID of the marketplace template to render. If omitted, an empty report shell is created and you can attach a template later from the web app.
- `title` (string, required): Display title for the generated report.

Output parameters:

- `report_id` (string)
- `status` (string): Initial status, normally "pending". Poll get_report for progress.
- `web_url` (string)

### `get_analysis_status` (~45 tokens)

Check the status of a previously-dispatched run_analysis job. Returns the analysis result if completed.

Input parameters:

- `job_id` (string, required): job_id returned by a prior run_analysis call.

Output parameters:

- `current_step` (string)
- `error` (string): Failure reason. Present when status is "failed".
- `job_id` (string)
- `progress` (number): Completion fraction or percentage reported by the job.
- `result` (object): Analysis envelope. Present when status is "completed".
- `status` (string)

### `get_billing_status` (~25 tokens)

Get the organization's billing status — tier, renewal date, and upgrade options.

Output parameters:

- `billing_url` (string)
- `price_monthly_usd` (number)
- `price_yearly_usd` (number)
- `subscription_status` (string)
- `subscription_tier` (string)
- `trial_ends_at` (string|null)

### `get_dashboard` (~43 tokens)

Fetch one dashboard by ID. Includes widget definitions, the most recent refresh data, and the web URL.

Input parameters:

- `dashboard_id` (string, required): UUID of the dashboard to fetch.

Output parameters:

- `analysis_metadata` (object): AnalysisEngine envelope captured when the dashboard was created.
- `configuration` (object): Dashboard layout and widget configuration.
- `created_at` (string|null)
- `description` (string)
- `id` (string)
- `is_public` (boolean)
- `last_refresh` (string|null)
- `name` (string)
- `status` (string): Dashboard lifecycle status.
- `updated_at` (string|null)
- `web_url` (string)

### `get_data_source_schema` (~100 tokens)

Fetch the column schema for a data source. Useful before asking run_analysis about specific columns. The schema is derived from the preprocessing metadata clariBI extracted when the source was last synced. Poll this after upload_data_source / ingest_url_data_source until the returned status flips to "active" — that means preprocessing has finished and run_analysis will see the data.

Input parameters:

- `data_source_id` (string, required): UUID of the data source to fetch the schema for.

Output parameters:

- `id` (string)
- `last_sync_at` (string|null)
- `name` (string)
- `schema` (object): Schema-shaped fields the preprocessing pipeline wrote into the source metadata (columns, column_types, sample_rows, row_count, ...). Empty until preprocessing has run or for source types with no colu…
- `source_type` (string)
- `status` (string)

### `get_forecast` (~30 tokens)

Fetch one forecast configuration by ID.

Input parameters:

- `forecast_id` (string, required): UUID of the forecast to fetch.

Output parameters:

- `aggregation` (string): auto / sum / mean / last / max
- `created_at` (string|null)
- `description` (string)
- `granularity` (string): One of: hourly, daily, weekly, monthly, quarterly, annual.
- `horizon_days` (integer)
- `id` (string)
- `include_anomalies` (boolean)
- `include_changepoints` (boolean)
- `include_correlations` (boolean)
- `is_active` (boolean)
- `latest_run_id` (string|null)
- `latest_run_status` (string|null): pending, running, completed, failed, refunded.
- `method_override` (string)
- `metric_label` (string)
- `metric_path` (string)
- `name` (string)
- `narration_enabled` (boolean)
- `next_run_at` (string|null)
- `non_negative` (boolean)
- `non_negative_auto` (boolean)
- `schedule_frequency` (string|null): daily, weekly, monthly, or manual.
- `source_id` (string)
- `source_type` (string): One of: report, dashboard, goal, data_source.
- `transform` (string): auto / none / log
- `updated_at` (string|null)
- `web_url` (string)

### `get_forecast_run` (~98 tokens)

Fetch one run of a forecast by ID, or pass run_id="latest" for the most recent run. Returns the full forecast envelope: target series + 30-day projection, correlated drivers (with lag and bootstrap stability), anomalies, structural changes, and credit accounting.

Input parameters:

- `forecast_id` (string, required)
- `run_id` (string, required): UUID of the run. Pass 'latest' to fetch the most recent run for the forecast.

Output parameters:

- `completed_at` (string|null)
- `created_at` (string|null)
- `credits_consumed` (integer)
- `credits_refunded` (integer)
- `duration_ms` (integer)
- `error_message` (string)
- `forecast_id` (string)
- `id` (string)
- `narration` (object|null): Peer of result.narration for convenience. Null when the run pre-dates narration OR was gated out (insufficient credits, org disabled, etc.).
- `result` (object): Forecast envelope. Contains keys: target, correlations, anomalies, changepoints, meta, and (when narration ran) narration. `target` carries lower/upper plus calibrated lower_50/upper_50, lower_80/upp…
- `status` (string)
- `trigger` (string)

### `get_forecast_trust` (~82 tokens)

Returns per-past-run accuracy for a forecast. Each row compares a prior run's projection against the actuals that have materialized since. Use this to see whether your forecasts have been getting MORE or LESS accurate over time, or to spot when a backtest sMAPE was systematically optimistic vs. realised performance.

Input parameters:

- `forecast_id` (string, required)

Output parameters:

- `runs` (array): Per-past-run accuracy ordered oldest-first. Each row compares one prior run's forecast against actuals that have since materialized.

### `get_report` (~29 tokens)

Fetch one generated report by ID.

Input parameters:

- `report_id` (string, required): UUID of the report to fetch.

Output parameters:

- `completed_at` (string|null)
- `created_at` (string|null)
- `data_quality_metrics` (object): Per-source data-quality stats captured at generation time.
- `description` (string)
- `download_url` (string|null): Present only once status is "completed".
- `id` (string)
- `insights` (object): Narrative insight blocks, when generated.
- `output_file_path` (string)
- `output_format` (string)
- `report_period_end` (string|null)
- `report_period_start` (string|null)
- `status` (string)
- `title` (string)
- `web_url` (string)

### `get_usage` (~29 tokens)

Get the organization's current AI credit usage, data source count, user count, and rate-limit headroom.

Output parameters:

- `ai_credits_limit` (integer)
- `ai_credits_remaining` (integer)
- `ai_credits_used` (integer)
- `data_sources_limit` (integer)
- `data_sources_used` (integer)
- `max_users` (integer)
- `storage_gb_limit` (number)
- `subscription_status` (string)
- `subscription_tier` (string)
- `trial_ends_at` (string|null)

### `ingest_url_data_source` (~215 tokens)

Create a new data source by fetching a public URL on the server side. Handles CSV, TSV, JSON, Excel, TXT, and PDF. Private networks (RFC 1918, loopback, cloud metadata) are blocked. Returns the data_source_id once preprocessing has started. Use this for files larger than the 25 MB inline upload cap.

Input parameters:

- `description` (string): Optional human note stored on the data source.
- `format` (string): Optional format hint. If omitted, the server infers it from the Content-Type header and URL extension.
- `name` (string, required): Display name for the new data source.
- `url` (string, required): Public http(s) URL of the file to ingest. The server fetches it once at call time; the URL is not re-fetched on subsequent analyses. Private networks (RFC 1918, loopback, link-local, cloud metadata)…
- `wait_seconds` (integer): Seconds to block waiting for preprocessing before returning. 0 returns immediately.

Output parameters:

- `bytes_fetched` (integer)
- `data_source_id` (string)
- `format` (string): Detected file format (csv, json, xlsx, ...).
- `name` (string)
- `raw_data_id` (string)
- `status` (string): Preprocessing status. Poll get_data_source_schema until "active".
- `web_url` (string|null)

### `list_dashboards` (~75 tokens)

List dashboards in your clariBI organization. Returns id, name, status, last refresh, and a URL you can open in a browser.

Input parameters:

- `limit` (integer): Page size (1–100).
- `offset` (integer): Row offset for pagination.
- `search` (string): Optional substring match against dashboard name.

Output parameters:

- `items` (array)
- `limit` (integer)
- `offset` (integer)
- `total` (integer): Total dashboards matching the query.

### `list_data_sources` (~98 tokens)

List the data sources connected to your clariBI organization. Returns id, name, source_type, status, last sync time, and the number of rows (when known).

Input parameters:

- `limit` (integer): Page size (1-100).
- `offset` (integer): Row offset for pagination.
- `source_type` (string): Filter by source_type (csv, postgresql, google_ads, meta_ads, jira, mcp, …).

Output parameters:

- `items` (array)
- `limit` (integer)
- `offset` (integer)
- `total` (integer): Total data sources matching the query.

### `list_forecasts` (~96 tokens)

List metric forecasts in your clariBI organization. Each row covers one metric: its source binding, horizon, schedule, and the latest run status. Use get_forecast_run to fetch the full forecast result.

Input parameters:

- `is_active` (boolean): Filter by active forecasts. Omit to include both active and paused.
- `limit` (integer): Page size (1-100).
- `offset` (integer): Row offset for pagination.

Output parameters:

- `items` (array)
- `limit` (integer)
- `offset` (integer)
- `total` (integer)

### `list_reports` (~76 tokens)

List generated reports in your clariBI organization. Returns id, title, status, output format, and download URL.

Input parameters:

- `limit` (integer): Page size (1-100).
- `offset` (integer): Row offset for pagination.
- `status` (string): Filter by status (pending, generating, completed, failed, cancelled).

Output parameters:

- `items` (array)
- `limit` (integer)
- `offset` (integer)
- `total` (integer): Total reports matching the query.

### `regenerate_forecast_narrative` (~112 tokens)

Re-run ONLY the AI narration step against an existing completed forecast run. Costs 1-2 AI credits (no engine work). Returns the new narration; the old one is overwritten in the run record. Refuses when the run is not yet complete or when narration_enabled=false on the forecast.

Input parameters:

- `forecast_id` (string, required)
- `run_id` (string, required): UUID of a COMPLETED run. Use get_forecast_run with run_id='latest' first if you want the most recent.

Output parameters:

- `narration` (object): Narration payload (summary, highlights, risks, recommendations, methodology_note, credits_consumed, model_used, generated_at, fallback_reason). fallback_reason is null on success; one of 'insufficien…

### `register_account` (~147 tokens)

Begin clariBI account signup. Validates the email + organization name, emails a 6-digit verification code, and returns a pending_id. Call verify_email(pending_id, code) within 10 minutes to finish signup and receive an API key.

Input parameters:

- `accept_terms` (boolean, required): Must be true. By passing true the user agrees to https://claribi.com/terms and https://claribi.com/privacy.
- `email` (string, required): Work email for the new account.
- `first_name` (string): User's first name (optional).
- `last_name` (string): User's last name (optional).
- `organization_name` (string, required): Display name for the organization workspace.

Output parameters:

- `email` (string)
- `expires_in_seconds` (integer)
- `next_step` (string): Next tool to call: "verify_email" for a fresh signup, else "check_inbox".
- `pending_id` (string|null): Pass to verify_email. Null when no new registration was created.

### `request_oauth_integration_url` (~195 tokens)

Initiate an OAuth handoff to a vendor integration (Google Ads, GA4, Search Console, Sheets, Drive, BigQuery, Meta Ads, Jira, Confluence). Returns an authorization URL the user opens in a browser. After the user clicks Allow, the connection is created and you can poll check_integration_status(handoff_id) to find out when the data is ready.

Input parameters:

- `integration_type` (string): Per-provider sub-type. Google accepts google_ads, gsheets, ga4, gsc, gdrive, bigquery, gcs, gcp, basic. Meta accepts ads or basic. Jira and Confluence accept basic. Defaults to basic.
- `provider` (string, required): OAuth provider to authorize. Currently supports the native-OAuth catalog: Google (Ads, Analytics 4, Search Console, Sheets, Drive, BigQuery), Meta Ads, and Atlassian Jira / Confluence.

Output parameters:

- `authorize_url` (string): Open in a browser to grant consent.
- `expires_in_seconds` (integer)
- `handoff_id` (string)
- `integration_type` (string)
- `next_step` (string): Tool to call next, normally "check_integration_status".
- `provider` (string)

### `run_analysis` (~162 tokens)

Run a natural-language analytics question against your connected data sources. Consumes AI credits. Returns either the completed analysis result inline OR a job_id you can poll with get_analysis_status. If list_data_sources returns an empty list, ingest data first with upload_data_source (inline base64), ingest_url_data_source (public URL), or request_oauth_integration_url (Google / Meta / Jira / Confluence).

Input parameters:

- `question` (string, required): Natural language question to analyze. E.g. "What was revenue last quarter by region?".
- `session_id` (string): Optional existing conversation session UUID.
- `wait_seconds` (integer): How long (seconds) to wait for the job to finish before returning a job_id for polling. 0 = always return immediately.

Output parameters:

- `ai_credits_limit` (integer)
- `ai_credits_used` (integer)
- `job_id` (string)
- `poll_url` (string): Present when the job is still running. Poll get_analysis_status instead for structured progress.
- `result` (object): Analysis envelope (headline metric, chart data, follow-ups). Present when status is "completed".
- `status` (string): Job status, e.g. "completed", "running", "queued".

### `run_forecast` (~104 tokens)

Run a forecast now. Reserves AI credits up front, dispatches the backtest + projection + correlation pipeline, and returns either the completed result inline (wait_seconds > 0 and the run finishes in time) or a run_id you can poll with get_forecast_run.

Input parameters:

- `forecast_id` (string, required)
- `wait_seconds` (integer): Seconds to wait for the run to finish before returning a poll handle. 0 = return immediately with the run_id.

Output parameters:

- `credits_consumed` (integer)
- `credits_refunded` (integer)
- `credits_reserved` (integer)
- `poll_tool` (string): Tool to poll if the run is still running ("get_forecast_run").
- `result` (object): Present when status reaches "completed".
- `run_id` (string)
- `status` (string): pending while queued, running mid-execution, completed/failed/refunded when terminal.

### `upload_data_source` (~272 tokens)

Create a new data source from an inline base64-encoded file (CSV, TSV, JSON, Excel, TXT, PDF). The file goes through the same validation and preprocessing as a web upload. Returns the data_source_id you can pass to run_analysis as soon as preprocessing completes (poll get_data_source_schema for readiness or pass wait_seconds to block here).

Input parameters:

- `data_base64` (string, required): Base64-encoded file contents. Maximum 25 MB encoded (~18 MB raw). For larger payloads, host the file at a public URL and use ingest_url_data_source.
- `description` (string): Optional human-readable description. Surfaces in the web app and in get_data_source_schema.
- `format` (string, required): File format. Drives MIME detection and the preprocessing route inside clariBI. csv covers comma-separated; tsv is tab-separated; xlsx is modern Excel; json must be a top-level array of objects or a s…
- `name` (string, required): Display name for the new data source. Shown in the web app and in subsequent list_data_sources calls.
- `wait_seconds` (integer): How long (seconds) to wait for preprocessing to finish before returning. 0 returns immediately with status="preprocessing"; the caller polls get_data_source_schema or list_data_sources.

Output parameters:

- `bytes_uploaded` (integer)
- `data_source_id` (string)
- `format` (string): Detected file format (csv, json, xlsx, ...).
- `name` (string)
- `raw_data_id` (string)
- `status` (string): Preprocessing status. Poll get_data_source_schema until "active".
- `web_url` (string|null)

### `verify_email` (~115 tokens)

Complete clariBI signup by submitting the verification code plus a password. Returns an OAuth access_token for immediate use AND a long-lived MCP API key for persistent configuration. The new organization lands on the Trial tier (50 AI credits, 14 days).

Input parameters:

- `code` (string, required): 6-digit verification code from the email.
- `password` (string, required): A password for the new account. Must be at least 8 characters and pass Django's standard validators.
- `pending_id` (string, required): The pending_id returned by register_account.

Output parameters:

- `access_token` (string): OAuth bearer token for this conversation.
- `expires_in` (integer): Access-token lifetime in seconds.
- `mcp_api_key` (string): Long-lived API key (claribi_mcp_...) for persistent client config.
- `mcp_api_key_id` (string)
- `next_steps` (array)
- `organization_id` (string)
- `scope` (string): Space-separated granted scopes.
- `tier` (string): New organization tier, always "trial".
- `token_type` (string): Always "Bearer".
- `user_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 64
- 2026-08-01: 64
- 2026-07-31: 64
- 2026-07-30: 63
- 2026-07-29: 62
- 2026-07-28: 62
- 2026-07-27: 61
- 2026-07-26: 60

## Links

- Remote endpoint: https://claribi.com/mcp/v1/
- Repository: https://github.com/ICS-cz/Claribi
- Website: https://claribi.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-claribi-mcp-server/mcp-v1