> ## Documentation Index
> Fetch the complete documentation index at: https://docs.go.aiinsurance.io/llms.txt
> Use this file to discover all available pages before exploring further.
# MCP Connector (Beta)
> Use your AI Insurance data and actions directly from Claude with the AI Insurance MCP connector
The **AI Insurance MCP connector** lets you work with your AI Insurance data from
[Claude](https://claude.ai) — in a conversation, you can ask Claude to look up a
submission, summarize a policy's endorsement history, bind a prepared quote,
create a task, draft a note on a claim, or export your exposures to a table, and
Claude does it against your live AI Insurance account.
It's built on the [Model Context Protocol (MCP)](https://modelcontextprotocol.io),
an open standard for connecting AI assistants to external systems. You add AI
Insurance as a **custom connector** in Claude.ai or Claude Desktop, sign in once
with your normal AI Insurance account, and Claude gains a set of tools for
reading and writing your data — acting **as you**, with exactly the permissions
your user has.
**The MCP connector has not been released yet.** This page documents the
connector ahead of its launch — the connector URL below will not accept
connections until the rollout completes. Watch the
[changelog](/api-reference/changelog) for the release announcement.
**The MCP connector is in beta.** Once released, it may need to be enabled for
your company before the connector will accept connections. If you can't
connect, reach out via the
[support portal](https://support.aiinsurance.io/customer-portal) or your AI
Insurance contact to get access.
## Adding the connector
The connector URL is:
```
https://mcp.go.aiinsurance.io/mcp
```
In **Claude.ai**, go to **Settings → Connectors** and choose **Add custom
connector**. In **Claude Desktop**, the same option lives under **Settings →
Connectors**. (Custom connectors require a Claude plan that supports them;
see Claude's own documentation for plan availability.)
Give the connector a name (for example, "AI Insurance") and paste the URL
`https://mcp.go.aiinsurance.io/mcp`. No API key or other credentials are
entered here — authentication happens in the next step.
The first time you connect, a browser window opens asking you to sign in to
AI Insurance. Use the **same account you use for the web app** at
[go.aiinsurance.io](https://go.aiinsurance.io). Once you approve, Claude is
connected — you won't need to sign in again unless your session expires or
you disconnect.
Start a conversation and ask something like *"Which AI Insurance companies
can I access?"* or *"Find the submission for Acme Manufacturing and
summarize where it stands."* A good first prompt is to ask Claude to call
the connector's `get_started` tool — it teaches Claude how your data model
works before it starts reading and writing.
## How access and permissions work
The connector acts **on your behalf**:
* **You sign in as yourself.** There are no shared credentials and no API keys —
each user connects with their own AI Insurance login.
* **Claude can do what you can do — no more.** Every request is checked against
your user's role and permissions, per company, exactly as in the web app and
the REST API. If your role can't delete quotes, Claude can't either.
* **Multi-company users pick a company.** If your account spans several
companies, Claude first lists the companies you can act on and works within
the one you choose.
* **Everything is logged.** Actions taken through the connector are recorded in
the same audit log as other API activity.
Claude's writes are real. When you ask Claude to create, update, or delete a
record through the connector, it changes your live data — the same as making
the edit in the app. Claude will treat a clear, specific request as
confirmation to proceed, so be deliberate when asking for deletions or bulk
changes.
## What Claude can do
Once connected, Claude has tools covering your core records, policies, tasks,
and notes.
### Orientation
| Tool | What it does |
| ---------------- | ------------------------------------------------------------------------------------------------------------------ |
| `get_started` | Teaches Claude your data model — entity types, how they relate, how option values work — before it starts working. |
| `whoami` | Confirms who Claude is signed in as (your name and email). |
| `list_companies` | Lists the companies your account can act on. |
### Records (submissions, quotes, events, exposures, people, organizations)
| Tool | What it does |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `list_entity_types` | Shows which record types exist for a company and which actions your role permits on each. |
| `get_entity_schema` | Reads the fields configured for one record type, so Claude fills in valid data. |
| `search_entities` | Searches records of one type by free text or structured filters. |
| `get_entity` | Reads one record in full. |
| `create_entity` | Creates a record. |
| `update_entity` | Updates specific fields on a record (fields you don't mention are left alone). |
| `delete_entity` | Deletes one specific record. There is no bulk delete through the connector. |
| `export_entities` | Exports records of one type as a spreadsheet-style table (large exports are truncated in chat; use the [REST export endpoints](/api-reference/entities/overview) for complete files). |
| `describe_option_set` | Looks up the allowed values of a dropdown/option field, searchable for large sets. |
| `validate_entity_data` | Checks whether stored records still conform to your current configuration — useful after imports or config changes. Read-only. |
### Binding quotes
| Tool | What it does |
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `bind_quote` | Binds a prepared quote and links it to the resulting policy. Works for every quote type: a new-business or renewal quote creates a new policy; an endorsement, cancellation, or reinstatement applies its change to the existing policy. A quote that's already bound isn't re-bound — Claude reports the policy it's already on. |
### Policies (read-only)
Policies are managed through their transaction lifecycle (bind, endorse, cancel,
reinstate, renew), so the policy tools themselves are **read-only** — Claude can
analyze your book, and the one way it changes a policy is by binding a prepared
quote with [`bind_quote`](#binding-quotes) above.
| Tool | What it does |
| ------------------------- | -------------------------------------------------------------------------------------------------------------------- |
| `list_policies` | Lists or searches the book of business — each policy at its latest version, with number, insured, term, and premium. |
| `get_policy` | Reads one policy — its current version or its full version history. |
| `get_policy_transactions` | The change log for a policy: every action taken on it, and the field-level changes any one transaction made. |
### Tasks and notes
| Tool | What it does |
| ------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------- |
| `list_tasks` / `create_task` / `update_task` / `delete_task` | Work with to-dos — create follow-ups, assign them, link them to a submission or claim, mark them complete. |
| `list_notes` / `create_note` / `update_note` / `delete_note` | Work with the free-text notes on a record — read the notes on a claim, add a new one, edit or remove one. |
## The configuration connector
Alongside the data connector, there is a second, separate connector for
**editing your company's configuration** — the fields, option sets, custom
objects, and page layouts that define how your app works (see
[Configuration Management](/api-reference/configuration/overview) for the
equivalent REST surface). Its URL is:
```
https://mcp.go.aiinsurance.io/mcp/config
```
Add it the same way as the data connector. Because both use the same sign-in,
you won't be asked to log in a second time.
Its tools let Claude **inspect** your configuration (`describe_config`,
`describe_entity`, `describe_fields`, `describe_field_types`,
`describe_option_set`, `describe_cards`, `describe_card`,
`describe_placement_options`), **change** it with precise, single-purpose
operations (`add_field`, `update_field`, `delete_field`, `create_option_set`,
`add_option_set_option`, `update_option_set_option`, `delete_option_set`,
`delete_option_set_option`, `create_custom_object`, `delete_custom_object`,
`add_card`, `update_card`, `delete_card`, `add_field_to_card`,
`update_field_on_card`, `remove_field_from_card`, `relayout_card`, or
`apply_changes` for a multi-part change committed atomically), and **bootstrap
a new company** from starter modules (`list_starter_modules`,
`seed_configuration`).
Configuration changes are higher-stakes than data entry, so this connector is
built around a **validate-first** workflow: every change supports a dry run
that checks the full result without committing anything, and Claude is
instructed to confirm destructive changes with you before applying them.
The configuration connector is an earlier-stage beta than the data connector
and is enabled separately. If the URL returns "not found", it isn't enabled
for your environment yet — contact support to request access.
## Tips for good results
* **Start with `get_started`.** Asking Claude to call it first gives much better
results — it learns your entity types and how option values work.
* **Be specific about records.** "Delete the duplicate exposure for 123 Main
St" works better than "clean up the exposures" — Claude confirms with you when
a request is ambiguous or implies a bulk change.
* **Let Claude read the schema before writing.** For creates and updates, Claude
reads the configured fields first so the data it writes matches your setup.
If a value is rejected, the error names the exact field so it can fix and
retry.
## Troubleshooting
| Symptom | What it usually means |
| ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| The connector can't be added or never responds | The beta may not be enabled for your company or environment yet — [contact support](https://support.aiinsurance.io/customer-portal). |
| The sign-in window never completes, or Claude reports it isn't authenticated | Disconnect the connector in Claude's settings and reconnect to sign in again. Make sure you're signing in with your AI Insurance account — the one you use at [go.aiinsurance.io](https://go.aiinsurance.io). |
| Tools fail with a permission error (403) | Your role doesn't have that permission for that record type or company. An administrator can adjust your role — see [Users and roles](/app/admin/users-roles). |
| `list_companies` returns nothing | Your account isn't a member of any company, or your session is stale — reconnect and try again. |
| The configuration connector URL returns "not found" | The configuration endpoint is gated separately and isn't enabled for your environment. The data connector keeps working regardless. |
| Claude seems confused about field names or option values | Ask it to call `get_started`, then `get_entity_schema` for the record type it's working with. |
## Related
* [API overview](/api-reference/overview) — the REST API the connector is built on.
* [Generating API keys](/api-reference/authentication) — for direct, non-Claude integrations. The connector itself never uses API keys.
* [Entities overview](/entities/overview) — the data model Claude works with.