# Bonnard vs Omni: MCP server features compared

> Bonnard and Omni MCP servers compared: what the agent knows about your data, how wrong answers get fixed, who can connect and pricing.

With Omni (omni.co), each query selects fields from your Omni model, and Omni's AI writes most of them. With Bonnard (bonnard.ai), the AI client writes SQL on your database from context your team adds.

## Five differences

### What the agent knows about your data

Bonnard gives its context to the AI client the person already uses. `explore_schema` searches table names, descriptions, column comments, enum labels, metrics and business terms, and returns up to 10 tables. For each table the agent gets the keys, row count and sample rows from the database, plus what your team adds: descriptions, joins, metrics, business terms and the values of columns you mark as searchable ([context](/features/context-engine)). A metric is its calculation in SQL, with instructions. The agent reads it and writes the query. Bonnard does not rewrite the query to apply it.

Omni keeps its context in a semantic model. A topic groups the views, joins, dimensions and measures for one use case ([topics](https://docs.omni.co/modeling/topics)). Omni sends field descriptions, synonyms and `ai_context` from the model to the LLM ([AI usage](https://docs.omni.co/ai/settings/usage)). A topic can also hold sample queries ([AI optimization](https://docs.omni.co/modeling/develop/ai-optimization)), and an Organization Admin can add Markdown files that the Omni Agent reads across all models ([global context](https://docs.omni.co/ai/settings/global-context)).

Omni's MCP tools give the model to outside AI clients too. `listModelTopics` lists the topics. `getModelTopic` returns one topic with its views, joins, dimensions, measures and descriptions. `getModelViews` lists the views and their fields ([tools](https://docs.omni.co/ai/mcp/tools)). These tools need a connection for one user, such as OAuth.

Omni's AI writes most queries. `getData` runs the question against a topic through the same AI pipeline as the Omni Agent. `askOmni` gives a multi-step question to the Omni Agent. An AI client can also build a query in Omni's JSON form and run it with `runQuery`.

Metric definitions are enforced. Each query selects fields from the model, no MCP tool runs SQL on the database, and `runQuery` refuses keys that run raw SQL, for example `userEditedSQL`. Omni's AI can add CTEs and custom fields to a query, and a model's [`ai_settings`](https://docs.omni.co/modeling/models/parameters/ai-settings) can restrict both.

### How wrong answers get found and fixed

Bonnard runs a loop of four steps on how agents use your data. Omni has the same four steps for the Omni Agent, and Organization Admins find them in the [AI Hub](https://docs.omni.co/administration/ai-hub).

[Image: The context loop in four steps: observe, diagnose, improve, verify.]

**Observe.** Bonnard records each tool call with its SQL, status and error, from every AI client your people use.

Omni's [Analytics](https://docs.omni.co/administration/analytics) section logs AI prompts, responses and sessions. The AI Hub classifies each AI session for intent, outcome and sentiment. From the AI client, `submitFeedback` records a thumbs up or down on an `askOmni` answer ([tools](https://docs.omni.co/ai/mcp/tools)).

**Diagnose.** Bonnard reads that record and finds what is wrong: definitions that differ between people, searches that found nothing, sessions that took many calls, repeated errors and tables that stopped updating. Where the data cannot settle a question, Bonnard asks your data team.

[Image: Bonnard's activity record over 30 days. It finds three definitions of net revenue across eight people, a search for gift cards that found nothing, sessions that took nine calls, an undefined column error and a table that stopped in May.]

Omni's [Suggestions](https://docs.omni.co/ai/suggestions) run once a day on a schedule that an admin enables for a model. They read the last 30 days of chat sessions that carry feedback, detected sentiment or an outcome such as stuck or abandoned. Each suggestion proposes a change to `ai_context`, a description, synonyms or sample values. [Learn from conversation](https://docs.omni.co/ai/learn-from-conversation) proposes model changes from one chat. Ask Omni whether `getData` calls from an AI client count as sessions for Suggestions.

**Improve.** Your data team's answer goes into a draft of the context.

On Omni, an admin implements each suggestion through Omni's Modeling Agent or ignores it. A Querier or higher accepts, edits or rejects the changes from Learn from conversation. Model changes go through branches, and through pull requests when the model is connected to git ([Branch Mode](https://docs.omni.co/content/develop/branch-mode)).

**Verify.** Evals run the same questions against the draft and the live version, and show which answers got better. A person then publishes the draft, and Bonnard keeps each version.

[Image: Three questions, each run five times against the live context and against the draft. Two get better and one shows no clear difference.]

Omni's [Evals](https://docs.omni.co/ai/evals) run a prompt set of up to 25 questions against a model branch or `main`. An LLM judge that Omni sets gives each answer a pass or a fail, and two runs of the same prompt set show side by side. You run them in the AI Hub, through the API or with `omni ai-eval` in Omni's CLI ([CLI](https://docs.omni.co/developers/cli/commands/ai-eval)).

Two warnings also reach the agent as it works. A result over the row limit tells the agent not to sum or average it. On PostgreSQL, a join that could count rows twice gets a warning.

Omni's evals score the Omni Agent, the engine behind `askOmni`. Bonnard's loop improves what Claude, ChatGPT or Cursor read before they write a query.

### What you need first

Bonnard starts from your database. Add it as a data source through a read-only credential, then give people access. The agent reads the table comments, keys and enum values that the database declares, and the context your team adds in Bonnard.

Omni starts from a connected database and an Omni model with topics ([topics](https://docs.omni.co/modeling/topics)). The MCP server queries only topics, unless the model's [`query_all_views_and_fields`](https://docs.omni.co/modeling/models/parameters/ai-settings) setting and the `X-MCP-Query-All-Views` header permit all views ([Claude guide](https://docs.omni.co/ai/mcp/claude-desktop)). The answers are as good as the descriptions, synonyms and `ai_context` your team has written in the model.

An Organization Admin must set **Enable AI** and **Omni Agent** to on ([MCP docs](https://docs.omni.co/ai/mcp)). **MCP server** is on by default, and three more settings control groups of tools ([MCP settings](https://docs.omni.co/ai/settings/mcp)).

### Who can connect

A Bonnard workspace has unlimited users, your customers' users included. Each customer's query runs as that customer's tenant (the value that marks its data in your database). A customer with no tenant gets no data. Isolation uses the database: row-level security on PostgreSQL, Redshift and SQL Server, or one dataset or database for each tenant on BigQuery and Azure SQL Database ([tenancy](/docs/access/tenancy)).

With OAuth, each person signs in to Omni with an Omni account, and each MCP query uses that person's Omni permissions. A connection with an API key uses the permissions of the key's creator ([authentication](https://docs.omni.co/ai/mcp/authentication)). The AI client lists only the tools that the person's roles allow ([tools](https://docs.omni.co/ai/mcp/tools)).

For embed users, Omni documents a chat agent that you build. Embed users do not sign in to Omni, so your backend mints a token for each one with `createEmbedMcpToken`, and your agent sends it to the MCP server ([embed MCP](https://docs.omni.co/embed/customization/ai-chat/your-agent-mcp)). Each query then runs with that user's Omni permissions. Omni's [embed guide](https://docs.omni.co/guides/embed/ai-chat-agent) recommends its AI Jobs API over MCP for this route.

### How you pay

Bonnard bills for each call, with no seats or minimums. Free includes 3,000 calls a month, then USD 0.95 for each 100 calls once an admin turns on extra usage ([pricing](/pricing)).

Omni publishes no licence prices. Its site offers a demo and a free trial through a request form ([free trial](https://omni.co/demo)), and fees are set in an Order Form ([terms](https://omni.co/terms)). Omni's licences have three tiers: Viewer, Standard and Administrator/Developer ([licence types](https://docs.omni.co/administration/users/permissions#license-types)). External users count towards licence usage.

A Viewer can run only the queries of published content, and gets no `getData` ([authentication](https://docs.omni.co/ai/mcp/authentication)). The lowest role that queries topics, Restricted Querier, has a Standard licence.

MCP use also draws AI credits ([AI usage](https://docs.omni.co/ai/settings/usage)). The LLMs that Omni hosts are billed in credits, except Omni AI, which is in early access. On an Omni Enterprise plan, an organisation can connect its own LLM provider key ([model providers](https://docs.omni.co/ai/settings/model-providers)). After an Organization Admin accepts overage billing, usage over the allotment in your plan costs USD 1.00 for each credit. Ask Omni for the allotment in your plan.

## Side by side

Table: Bonnard and Omni MCP servers, verified 16 Nov 2026

| Feature | Bonnard | Omni |
| --- | --- | --- |
| Who answers | The AI client the person uses, with Bonnard's context | Omni's AI writes the query for `getData` and `askOmni`. The AI client can build one for `runQuery` |
| Context the agent reads | Schema, descriptions, joins, metrics, business terms, searchable values | Topics, views, joins, dimensions, measures, descriptions, synonyms, `ai_context` |
| Context through MCP | `explore_schema`, for any AI client | `listModelTopics`, `getModelTopic` and `getModelViews`, for any AI client |
| Metric definitions | The agent reads the SQL and writes the query | Enforced. Queries select fields from the model, and no MCP tool runs raw SQL |
| Observe | Records each tool call, from any AI client | AI session logs with intent, outcome, sentiment and feedback |
| Diagnose | Finds what is wrong in the activity record | Suggestions, once a day from chat sessions. Learn from conversation |
| Improve | The data team's answer goes into a draft | An admin implements or ignores each suggestion. Branches, and git with pull requests |
| Verify | Evals: the draft against the live version | Evals with an LLM judge, on a branch or `main` |
| Run a query | `sql_query`, one read-only statement on your database | `getData` or `askOmni` through Omni's AI, or `runQuery` with a JSON query |
| Charts and dashboards | `render_chart` and `render_dashboard`, in the AI client | `showApp` shows a saved Omni app in the AI client. `askOmni` creates dashboards in Omni |
| Who can connect | Unlimited users, your customers' users included | Omni users. New queries need Restricted Querier or higher. Embed users through a chat agent that you build |
| Needed first | A data source: your database, or the sample data | A connected database and an Omni model with topics |
| Databases and warehouses | 7, plus PostHog | 15 |
| Tools for the agent | Up to 17 | 34 |
| How you pay | For each call, no seats | User licences and AI credits. Licence prices are not published |
| Free plan | 3,000 calls a month | A free trial on request |

## When Omni is stronger

- You want the semantic layer enforced: through Omni's MCP server, each query selects fields from the model and no tool runs raw SQL. Bonnard gives the agent the metric's SQL and does not rewrite the query.
- You review context changes in git: Omni syncs a model to Azure DevOps, Bitbucket, GitHub or GitLab, and a setting requires a pull request for each model change ([git](https://docs.omni.co/integrations/git)).
- You want a correction in a chat to become a model change: Learn from conversation drafts the YAML for a Querier or higher to review.
- You want the Omni Agent in the AI client: `askOmni` creates dashboards and routines in Omni. A routine delivers a scheduled prompt by email or Slack ([tools](https://docs.omni.co/ai/mcp/tools)).
- You need a dashboard as a file: `startDashboardDownload` starts a PNG or PDF export, and `fetchDashboardDownload` returns the file.
- You build custom apps in Omni: `showApp` renders a saved [app](https://docs.omni.co/visualize-present/apps) with live data in Claude Desktop, ChatGPT and VS Code with Copilot.
- Your database is one Bonnard does not connect to: Omni lists 15 ([databases](https://docs.omni.co/connect-data/setup)).

## Add each server to your AI client

**Bonnard.** Create a workspace, add Bonnard to your AI client, then add a data source ([quickstart](/docs/get-started/quickstart)). Use the install links for Claude, Cursor and ChatGPT in the console at `app.bonnard.ai`, or add this URL.

```text
https://app.bonnard.ai/mcp
```

**Omni.** An Organization Admin sets the AI settings to on ([MCP docs](https://docs.omni.co/ai/mcp)). In Claude, add the Omni Analytics connector ([Claude guide](https://docs.omni.co/ai/mcp/claude-desktop)). In ChatGPT, add the Omni Analytics app ([ChatGPT guide](https://docs.omni.co/ai/mcp/chatgpt)). Each person completes the setup. Other clients use this URL, and each person signs in through OAuth.

```text
https://callbacks.omniapp.co/callback/mcp
```

A connection with an API key uses `https://<your-instance>/mcp/https` instead ([authentication](https://docs.omni.co/ai/mcp/authentication)).

Verified 16 Nov 2026 against Omni's [MCP docs](https://docs.omni.co/ai/mcp), [tools](https://docs.omni.co/ai/mcp/tools), [MCP settings](https://docs.omni.co/ai/settings/mcp), [authentication](https://docs.omni.co/ai/mcp/authentication), [Claude guide](https://docs.omni.co/ai/mcp/claude-desktop), [ChatGPT guide](https://docs.omni.co/ai/mcp/chatgpt), [AI Hub](https://docs.omni.co/administration/ai-hub), [Analytics](https://docs.omni.co/administration/analytics), [Suggestions](https://docs.omni.co/ai/suggestions), [Learn from conversation](https://docs.omni.co/ai/learn-from-conversation), [Evals](https://docs.omni.co/ai/evals), [CLI](https://docs.omni.co/developers/cli/commands/ai-eval), [AI optimization](https://docs.omni.co/modeling/develop/ai-optimization), [global context](https://docs.omni.co/ai/settings/global-context), [`ai_settings`](https://docs.omni.co/modeling/models/parameters/ai-settings), [Branch Mode](https://docs.omni.co/content/develop/branch-mode), [git](https://docs.omni.co/integrations/git), [AI usage](https://docs.omni.co/ai/settings/usage), [model providers](https://docs.omni.co/ai/settings/model-providers), [licence types](https://docs.omni.co/administration/users/permissions#license-types), [embed guide](https://docs.omni.co/guides/embed/ai-chat-agent), [embed MCP](https://docs.omni.co/embed/customization/ai-chat/your-agent-mcp), [topics](https://docs.omni.co/modeling/topics), [apps](https://docs.omni.co/visualize-present/apps), [databases](https://docs.omni.co/connect-data/setup), [free trial](https://omni.co/demo) and [terms](https://omni.co/terms).